{ "@context": "https://schema.org", "@type": "DataCatalog", "@id": "https://www.insightits.com/catalog/index.json", "name": "Insight IT Solutions product knowledge catalog", "description": "One canonical machine-readable identity per product. Human landing pages remain /products/{slug}.html. Do not invent benchmarks or claims absent from these records.", "url": "https://www.insightits.com/catalog/index.json", "markdownUrl": "https://www.insightits.com/catalog/index.md", "generatedBy": "scripts/sync-product-knowledge.js", "organization": { "@type": "Organization", "@id": "https://www.insightits.com/#organization", "name": "Insight IT Solutions", "legalName": "Insight IT Solutions LLC", "alternateName": [ "Insight IT Solutions LLC", "Insight ITS", "InsightITS", "Insight IT Solutions, LLC", "Insight IT Solutions Inc", "Insight IT Solutions California", "Insight IT Solutions Mission Viejo", "Insight IT Solutions Orange County" ], "url": "https://www.insightits.com", "email": "info@insightits.com", "foundingDate": "2025", "sameAs": [ "https://www.linkedin.com/company/insight-it-solutions", "https://www.facebook.com/insightitsolutions", "https://twitter.com/InsightITSolutions", "https://www.instagram.com/insight_its/" ], "address": { "@type": "PostalAddress", "streetAddress": "39 Aliso ridge loop", "addressLocality": "Mission Viejo", "addressRegion": "CA", "postalCode": "92691", "addressCountry": "US" } }, "tree": [ { "family": "agentRuntime", "label": "Agent Runtime", "products": [ { "slug": "chorusgraph", "canonicalName": "ChorusGraph", "canonicalUrl": "https://www.insightits.com/products/chorusgraph.html", "knowledgeUrl": "https://www.insightits.com/catalog/chorusgraph.json", "markdownUrl": "https://www.insightits.com/catalog/chorusgraph.md", "status": "published", "parentProduct": null } ] }, { "family": "aiSecurity", "label": "AI Security", "products": [ { "slug": "prismguard", "canonicalName": "PrismGuard", "canonicalUrl": "https://www.insightits.com/products/prismguard.html", "knowledgeUrl": "https://www.insightits.com/catalog/prismguard.json", "markdownUrl": "https://www.insightits.com/catalog/prismguard.md", "status": "published", "parentProduct": null }, { "slug": "prismmanifest", "canonicalName": "PrismManifest", "canonicalUrl": "https://www.insightits.com/products/prismmanifest.html", "knowledgeUrl": "https://www.insightits.com/catalog/prismmanifest.json", "markdownUrl": "https://www.insightits.com/catalog/prismmanifest.md", "status": "published", "parentProduct": null }, { "slug": "prism-shield", "canonicalName": "Prism-Shield", "canonicalUrl": "https://www.insightits.com/products/prism-shield.html", "knowledgeUrl": "https://www.insightits.com/catalog/prism-shield.json", "markdownUrl": "https://www.insightits.com/catalog/prism-shield.md", "status": "published", "parentProduct": null } ] }, { "family": "aiVerification", "label": "AI Verification", "products": [ { "slug": "prism-eval", "canonicalName": "Prism-Eval", "canonicalUrl": "https://www.insightits.com/products/prism-eval.html", "knowledgeUrl": "https://www.insightits.com/catalog/prism-eval.json", "markdownUrl": "https://www.insightits.com/catalog/prism-eval.md", "status": "published", "parentProduct": null }, { "slug": "prismshine", "canonicalName": "PrismShine", "canonicalUrl": "https://www.insightits.com/products/prismshine.html", "knowledgeUrl": "https://www.insightits.com/catalog/prismshine.json", "markdownUrl": "https://www.insightits.com/catalog/prismshine.md", "status": "published", "parentProduct": null } ] }, { "family": "aiRetrieval", "label": "AI Retrieval", "products": [ { "slug": "prismrag", "canonicalName": "PrismRAG", "canonicalUrl": "https://www.insightits.com/products/prismrag.html", "knowledgeUrl": "https://www.insightits.com/catalog/prismrag.json", "markdownUrl": "https://www.insightits.com/catalog/prismrag.md", "status": "published", "parentProduct": null }, { "slug": "prism-resonance", "canonicalName": "PrismResonance", "canonicalUrl": "https://www.insightits.com/products/prism-resonance.html", "knowledgeUrl": "https://www.insightits.com/catalog/prism-resonance.json", "markdownUrl": "https://www.insightits.com/catalog/prism-resonance.md", "status": "published", "parentProduct": null }, { "slug": "vectorbridge", "canonicalName": "VectorBridge", "canonicalUrl": "https://www.insightits.com/products/vectorbridge.html", "knowledgeUrl": "https://www.insightits.com/catalog/vectorbridge.json", "markdownUrl": "https://www.insightits.com/catalog/vectorbridge.md", "status": "published", "parentProduct": null } ] }, { "family": "operations", "label": "Operations", "products": [ { "slug": "choruscontrol", "canonicalName": "ChorusControl", "canonicalUrl": "https://www.insightits.com/products/choruscontrol.html", "knowledgeUrl": "https://www.insightits.com/catalog/choruscontrol.json", "markdownUrl": "https://www.insightits.com/catalog/choruscontrol.md", "status": "published", "parentProduct": null } ] }, { "family": "supporting", "label": "Supporting libraries", "products": [ { "slug": "python-libs", "canonicalName": "Python Libs", "canonicalUrl": "https://www.insightits.com/products/python-libs.html", "knowledgeUrl": "https://www.insightits.com/catalog/python-libs.json", "markdownUrl": "https://www.insightits.com/catalog/python-libs.md", "status": "published", "parentProduct": null }, { "slug": "prismlang", "canonicalName": "PrismLang", "canonicalUrl": "https://www.insightits.com/products/prismlang.html", "knowledgeUrl": "https://www.insightits.com/catalog/prismlang.json", "markdownUrl": "https://www.insightits.com/catalog/prismlang.md", "status": "published", "parentProduct": null }, { "slug": "prismlib", "canonicalName": "PrismLib", "canonicalUrl": "https://www.insightits.com/products/prismlib.html", "knowledgeUrl": "https://www.insightits.com/catalog/prismlib.json", "markdownUrl": "https://www.insightits.com/catalog/prismlib.md", "status": "published", "parentProduct": null }, { "slug": "prismcortex", "canonicalName": "PrismCortex", "canonicalUrl": "https://www.insightits.com/products/prismcortex.html", "knowledgeUrl": "https://www.insightits.com/catalog/prismcortex.json", "markdownUrl": "https://www.insightits.com/catalog/prismcortex.md", "status": "published", "parentProduct": null }, { "slug": "vectorprism", "canonicalName": "VectorPrism", "canonicalUrl": "https://www.insightits.com/products/vectorprism.html", "knowledgeUrl": "https://www.insightits.com/catalog/vectorprism.json", "markdownUrl": "https://www.insightits.com/catalog/vectorprism.md", "status": "published", "parentProduct": null }, { "slug": "chorus-fabric", "canonicalName": "CHORUS Fabric", "canonicalUrl": "https://www.insightits.com/products/chorus-fabric.html", "knowledgeUrl": "https://www.insightits.com/catalog/chorus-fabric.json", "markdownUrl": "https://www.insightits.com/catalog/chorus-fabric.md", "status": "published", "parentProduct": null } ] }, { "family": "demo", "label": "Demos", "products": [ { "slug": "digit-drop-lab", "canonicalName": "Digit Drop Lab", "canonicalUrl": "https://www.insightits.com/products/digit-drop-lab.html", "knowledgeUrl": "https://www.insightits.com/catalog/digit-drop-lab.json", "markdownUrl": "https://www.insightits.com/catalog/digit-drop-lab.md", "status": "published", "parentProduct": "prismmanifest" }, { "slug": "prismmanifest-demo", "canonicalName": "PrismManifest Money Path Demo", "canonicalUrl": "https://www.insightits.com/products/prismmanifest-demo.html", "knowledgeUrl": "https://www.insightits.com/catalog/prismmanifest-demo.json", "markdownUrl": "https://www.insightits.com/catalog/prismmanifest-demo.md", "status": "published", "parentProduct": "prismmanifest" }, { "slug": "vectorprism-demo", "canonicalName": "VectorPrism Demo", "canonicalUrl": "https://www.insightits.com/products/vectorprism-demo.html", "knowledgeUrl": "https://www.insightits.com/catalog/vectorprism-demo.json", "markdownUrl": "https://www.insightits.com/catalog/vectorprism-demo.md", "status": "published", "parentProduct": "vectorprism" }, { "slug": "ledgerlock-demo", "canonicalName": "Ledgerlock Demo", "canonicalUrl": "https://www.insightits.com/products/ledgerlock-demo.html", "knowledgeUrl": "https://www.insightits.com/catalog/ledgerlock-demo.json", "markdownUrl": "https://www.insightits.com/catalog/ledgerlock-demo.md", "status": "published", "parentProduct": "ledgerlock" } ] }, { "family": "research", "label": "Research", "products": [ { "slug": "prism-pack", "canonicalName": "Prism Pack Family", "canonicalUrl": "https://www.insightits.com/products/prism-pack.html", "knowledgeUrl": "https://www.insightits.com/catalog/prism-pack.json", "markdownUrl": "https://www.insightits.com/catalog/prism-pack.md", "status": "published", "parentProduct": null }, { "slug": "antislop", "canonicalName": "AntiSlop", "canonicalUrl": "https://www.insightits.com/products/antislop.html", "knowledgeUrl": "https://www.insightits.com/catalog/antislop.json", "markdownUrl": "https://www.insightits.com/catalog/antislop.md", "status": "published", "parentProduct": null }, { "slug": "chorusface", "canonicalName": "ChorusFace", "canonicalUrl": "https://www.insightits.com/products/chorusface.html", "knowledgeUrl": "https://www.insightits.com/catalog/chorusface.json", "markdownUrl": "https://www.insightits.com/catalog/chorusface.md", "status": "unpublished", "parentProduct": null }, { "slug": "ledgerlock", "canonicalName": "Ledgerlock", "canonicalUrl": "https://www.insightits.com/products/ledgerlock.html", "knowledgeUrl": "https://www.insightits.com/catalog/ledgerlock.json", "markdownUrl": "https://www.insightits.com/catalog/ledgerlock.md", "status": "published", "parentProduct": null } ] }, { "family": "vertical", "label": "Vertical AI", "products": [ { "slug": "hotel", "canonicalName": "Hotel", "canonicalUrl": "https://www.insightits.com/products/hotel.html", "knowledgeUrl": "https://www.insightits.com/catalog/hotel.json", "markdownUrl": "https://www.insightits.com/catalog/hotel.md", "status": "published", "parentProduct": null }, { "slug": "fitness", "canonicalName": "Fitness", "canonicalUrl": "https://www.insightits.com/products/fitness.html", "knowledgeUrl": "https://www.insightits.com/catalog/fitness.json", "markdownUrl": "https://www.insightits.com/catalog/fitness.md", "status": "published", "parentProduct": null }, { "slug": "real-estate", "canonicalName": "Real Estate", "canonicalUrl": "https://www.insightits.com/products/real-estate.html", "knowledgeUrl": "https://www.insightits.com/catalog/real-estate.json", "markdownUrl": "https://www.insightits.com/catalog/real-estate.md", "status": "published", "parentProduct": null }, { "slug": "restaurant-ai-agent", "canonicalName": "Restaurant", "canonicalUrl": "https://www.insightits.com/products/restaurant-ai-agent.html", "knowledgeUrl": "https://www.insightits.com/catalog/restaurant-ai-agent.json", "markdownUrl": "https://www.insightits.com/catalog/restaurant-ai-agent.md", "status": "published", "parentProduct": null }, { "slug": "law-ai-agent", "canonicalName": "Law", "canonicalUrl": "https://www.insightits.com/products/law-ai-agent.html", "knowledgeUrl": "https://www.insightits.com/catalog/law-ai-agent.json", "markdownUrl": "https://www.insightits.com/catalog/law-ai-agent.md", "status": "published", "parentProduct": null }, { "slug": "hospital-ai-agent", "canonicalName": "Hospital", "canonicalUrl": "https://www.insightits.com/products/hospital-ai-agent.html", "knowledgeUrl": "https://www.insightits.com/catalog/hospital-ai-agent.json", "markdownUrl": "https://www.insightits.com/catalog/hospital-ai-agent.md", "status": "published", "parentProduct": null }, { "slug": "onlineshop", "canonicalName": "Online Shop", "canonicalUrl": "https://www.insightits.com/products/onlineshop.html", "knowledgeUrl": "https://www.insightits.com/catalog/onlineshop.json", "markdownUrl": "https://www.insightits.com/catalog/onlineshop.md", "status": "published", "parentProduct": null }, { "slug": "industrial-ai-agent", "canonicalName": "Industrial", "canonicalUrl": "https://www.insightits.com/products/industrial-ai-agent.html", "knowledgeUrl": "https://www.insightits.com/catalog/industrial-ai-agent.json", "markdownUrl": "https://www.insightits.com/catalog/industrial-ai-agent.md", "status": "published", "parentProduct": null }, { "slug": "dental", "canonicalName": "Dental", "canonicalUrl": "https://www.insightits.com/products/dental.html", "knowledgeUrl": "https://www.insightits.com/catalog/dental.json", "markdownUrl": "https://www.insightits.com/catalog/dental.md", "status": "published", "parentProduct": null } ] } ], "products": { "hotel": { "@context": "https://schema.org", "@type": "Product", "@id": "https://www.insightits.com/products/hotel.html", "slug": "hotel", "canonicalName": "Hotel", "name": "Hotel AI Web Agent", "canonicalUrl": "https://www.insightits.com/products/hotel.html", "knowledgeUrl": "https://www.insightits.com/catalog/hotel.json", "markdownUrl": "https://www.insightits.com/catalog/hotel.md", "family": "vertical", "infraFamily": null, "recordType": "product", "status": "published", "parentProduct": null, "whatItIs": "AI concierge for hotels: room bookings, amenities, housekeeping requests, and 24/7 guest support—like a front desk that never sleeps.", "problem": "After-hours booking requests go to OTAs when nobody answers the front desk. Late-night availability questions and policy FAQs pile up on staff — or go unanswered while OTAs capture the booking.", "isNot": [ "A generic after-hours chatbot trained on the open web", "An Insight ITS open-source library (those are the Prism / Chorus products)" ], "alternatives": [ { "name": "Generic after-hours chatbot", "relationship": "Vertical agents are scoped to the business knowledge base, pricing rules, and optional DB/payment hooks — not a general chatbot. No published named-vendor bake-off for these industry agents." } ], "features": [ { "name": "Booking Management", "description": "Handles room reservations, availability, and rate questions in real time." }, { "name": "Guest Services", "description": "Answers questions about amenities, policies, dining, and local recommendations." }, { "name": "Check-in Support", "description": "Guides guests through arrival, requests, and checkout without wait times." } ], "architecture": "LangGraph-style orchestration, RAG knowledge base scoped to the business, MCP tool integrations. Typical go-live 3–7 days on the customer site. 2-year maintenance included on AI Web product deployments.", "useCases": [ "24/7 FAQs, intake, and routing on the customer website", "After-hours coverage when staff cannot answer the phone" ], "benchmarks": { "published": false, "summary": "No published vendor benchmark for this product. Do not invent metrics.", "disclosures": [ "No published vendor benchmark for this product. Do not invent metrics." ], "urls": [] }, "github": null, "pypi": null, "documentation": [], "install": null, "version": null, "relatedProducts": [], "publisher": { "@type": "Organization", "name": "Insight IT Solutions", "legalName": "Insight IT Solutions LLC", "url": "https://www.insightits.com" } }, "fitness": { "@context": "https://schema.org", "@type": "Product", "@id": "https://www.insightits.com/products/fitness.html", "slug": "fitness", "canonicalName": "Fitness", "name": "Fitness App AI Web Agent", "canonicalUrl": "https://www.insightits.com/products/fitness.html", "knowledgeUrl": "https://www.insightits.com/catalog/fitness.json", "markdownUrl": "https://www.insightits.com/catalog/fitness.md", "family": "vertical", "infraFamily": null, "recordType": "product", "status": "published", "parentProduct": null, "whatItIs": "AI coach for gyms and fitness apps: class schedules, membership questions, workout tips, and nutrition guidance—24/7 motivation for your members.", "problem": "Members churn when class schedules and membership answers sit unanswered after hours. Front desk staff repeat the same schedule and billing answers instead of coaching on the floor.", "isNot": [ "A generic after-hours chatbot trained on the open web", "An Insight ITS open-source library (those are the Prism / Chorus products)" ], "alternatives": [ { "name": "Generic after-hours chatbot", "relationship": "Vertical agents are scoped to the business knowledge base, pricing rules, and optional DB/payment hooks — not a general chatbot. No published named-vendor bake-off for these industry agents." } ], "features": [ { "name": "Class & Schedule Help", "description": "Members ask about classes, trainers, hours, and availability instantly." }, { "name": "Membership Support", "description": "Explains plans, freezes, billing questions, and signup steps." }, { "name": "Workout Guidance", "description": "Offers workout ideas, form tips, and goal tracking in plain language." } ], "architecture": "LangGraph-style orchestration, RAG knowledge base scoped to the business, MCP tool integrations. Typical go-live 3–7 days on the customer site. 2-year maintenance included on AI Web product deployments.", "useCases": [ "24/7 FAQs, intake, and routing on the customer website", "After-hours coverage when staff cannot answer the phone" ], "benchmarks": { "published": false, "summary": "No published vendor benchmark for this product. Do not invent metrics.", "disclosures": [ "No published vendor benchmark for this product. Do not invent metrics." ], "urls": [] }, "github": null, "pypi": null, "documentation": [], "install": null, "version": null, "relatedProducts": [], "publisher": { "@type": "Organization", "name": "Insight IT Solutions", "legalName": "Insight IT Solutions LLC", "url": "https://www.insightits.com" } }, "real-estate": { "@context": "https://schema.org", "@type": "Product", "@id": "https://www.insightits.com/products/real-estate.html", "slug": "real-estate", "canonicalName": "Real Estate", "name": "Real Estate AI Web Agent", "canonicalUrl": "https://www.insightits.com/products/real-estate.html", "knowledgeUrl": "https://www.insightits.com/catalog/real-estate.json", "markdownUrl": "https://www.insightits.com/catalog/real-estate.md", "family": "vertical", "infraFamily": null, "recordType": "product", "status": "published", "parentProduct": null, "whatItIs": "AI assistant for agencies: property search, MLS-style answers, viewing schedules, and lead qualification for buyers and renters.", "problem": "Listing inquiries go cold after hours — buyers move to the agent who responds first. Weekend browsing turns into lost deals when no one answers pricing, neighborhood, and showing questions.", "isNot": [ "A generic after-hours chatbot trained on the open web", "An Insight ITS open-source library (those are the Prism / Chorus products)" ], "alternatives": [ { "name": "Generic after-hours chatbot", "relationship": "Vertical agents are scoped to the business knowledge base, pricing rules, and optional DB/payment hooks — not a general chatbot. No published named-vendor bake-off for these industry agents." } ], "features": [ { "name": "Intelligent Search", "description": "Natural-language property search beyond basic filters." }, { "name": "Instant Answers", "description": "Pricing, neighborhoods, and availability without waiting for an agent." }, { "name": "Lead Qualification", "description": "Captures budget, timeline, and preferences automatically." } ], "architecture": "LangGraph-style orchestration, RAG knowledge base scoped to the business, MCP tool integrations. Typical go-live 3–7 days on the customer site. 2-year maintenance included on AI Web product deployments.", "useCases": [ "24/7 FAQs, intake, and routing on the customer website", "After-hours coverage when staff cannot answer the phone" ], "benchmarks": { "published": false, "summary": "No published vendor benchmark for this product. Do not invent metrics.", "disclosures": [ "No published vendor benchmark for this product. Do not invent metrics." ], "urls": [] }, "github": null, "pypi": null, "documentation": [], "install": null, "version": null, "relatedProducts": [], "publisher": { "@type": "Organization", "name": "Insight IT Solutions", "legalName": "Insight IT Solutions LLC", "url": "https://www.insightits.com" } }, "restaurant-ai-agent": { "@context": "https://schema.org", "@type": "Product", "@id": "https://www.insightits.com/products/restaurant-ai-agent.html", "slug": "restaurant-ai-agent", "canonicalName": "Restaurant", "name": "Restaurant AI Web Agent", "canonicalUrl": "https://www.insightits.com/products/restaurant-ai-agent.html", "knowledgeUrl": "https://www.insightits.com/catalog/restaurant-ai-agent.json", "markdownUrl": "https://www.insightits.com/catalog/restaurant-ai-agent.md", "family": "vertical", "infraFamily": null, "recordType": "product", "status": "published", "parentProduct": null, "whatItIs": "AI host for restaurants: menu questions, reservations, hours, dietary needs, and specials—so your team can focus on the floor.", "problem": "Missed calls during the dinner rush mean empty tables and frustrated guests. Hosts answer the same menu and reservation questions hundreds of times while service slips.", "isNot": [ "A generic after-hours chatbot trained on the open web", "An Insight ITS open-source library (those are the Prism / Chorus products)" ], "alternatives": [ { "name": "Generic after-hours chatbot", "relationship": "Vertical agents are scoped to the business knowledge base, pricing rules, and optional DB/payment hooks — not a general chatbot. No published named-vendor bake-off for these industry agents." } ], "features": [ { "name": "Menu Intelligence", "description": "Understands dishes, ingredients, allergens, and daily specials." }, { "name": "Reservation Management", "description": "Books tables and prevents double-booking automatically." }, { "name": "24/7 Guest Service", "description": "Answers hours, location, parking, and policy questions anytime." } ], "architecture": "LangGraph-style orchestration, RAG knowledge base scoped to the business, MCP tool integrations. Typical go-live 3–7 days on the customer site. 2-year maintenance included on AI Web product deployments.", "useCases": [ "24/7 FAQs, intake, and routing on the customer website", "After-hours coverage when staff cannot answer the phone" ], "benchmarks": { "published": false, "summary": "No published vendor benchmark for this product. Do not invent metrics.", "disclosures": [ "No published vendor benchmark for this product. Do not invent metrics." ], "urls": [] }, "github": null, "pypi": null, "documentation": [], "install": null, "version": null, "relatedProducts": [], "publisher": { "@type": "Organization", "name": "Insight IT Solutions", "legalName": "Insight IT Solutions LLC", "url": "https://www.insightits.com" } }, "law-ai-agent": { "@context": "https://schema.org", "@type": "Product", "@id": "https://www.insightits.com/products/law-ai-agent.html", "slug": "law-ai-agent", "canonicalName": "Law", "name": "California Law Consultant AI Web Agent", "canonicalUrl": "https://www.insightits.com/products/law-ai-agent.html", "knowledgeUrl": "https://www.insightits.com/catalog/law-ai-agent.json", "markdownUrl": "https://www.insightits.com/catalog/law-ai-agent.md", "family": "vertical", "infraFamily": null, "recordType": "product", "status": "published", "parentProduct": null, "whatItIs": "AI legal information assistant for California law topics—helping visitors understand processes, terms, and when to consult a licensed attorney.", "problem": "After-hours intake sits in voicemail while prospects hire another firm. Staff spend billable time on repeat process questions instead of cases.", "isNot": [ "A generic after-hours chatbot trained on the open web", "An Insight ITS open-source library (those are the Prism / Chorus products)" ], "alternatives": [ { "name": "Generic after-hours chatbot", "relationship": "Vertical agents are scoped to the business knowledge base, pricing rules, and optional DB/payment hooks — not a general chatbot. No published named-vendor bake-off for these industry agents." } ], "features": [ { "name": "Legal Information", "description": "Explains California legal topics in plain language (not legal advice)." }, { "name": "Client Intake", "description": "Collects case basics and directs visitors to the right next step." }, { "name": "24/7 Availability", "description": "Answers common questions when your office is closed." } ], "architecture": "LangGraph-style orchestration, RAG knowledge base scoped to the business, MCP tool integrations. Typical go-live 3–7 days on the customer site. 2-year maintenance included on AI Web product deployments.", "useCases": [ "24/7 FAQs, intake, and routing on the customer website", "After-hours coverage when staff cannot answer the phone" ], "benchmarks": { "published": false, "summary": "No published vendor benchmark for this product. Do not invent metrics.", "disclosures": [ "No published vendor benchmark for this product. Do not invent metrics." ], "urls": [] }, "github": null, "pypi": null, "documentation": [], "install": null, "version": null, "relatedProducts": [], "publisher": { "@type": "Organization", "name": "Insight IT Solutions", "legalName": "Insight IT Solutions LLC", "url": "https://www.insightits.com" } }, "hospital-ai-agent": { "@context": "https://schema.org", "@type": "Product", "@id": "https://www.insightits.com/products/hospital-ai-agent.html", "slug": "hospital-ai-agent", "canonicalName": "Hospital", "name": "Hospital AI Web Agent", "canonicalUrl": "https://www.insightits.com/products/hospital-ai-agent.html", "knowledgeUrl": "https://www.insightits.com/catalog/hospital-ai-agent.json", "markdownUrl": "https://www.insightits.com/catalog/hospital-ai-agent.md", "family": "vertical", "infraFamily": null, "recordType": "product", "status": "published", "parentProduct": null, "whatItIs": "AI guide for hospitals: departments, visiting hours, appointment information, and services—helping patients find answers without overloading staff.", "problem": "Patient and visitor calls overload staff with the same department and hours questions. Switchboards and nurses field repetitive visitor questions instead of clinical work.", "isNot": [ "A generic after-hours chatbot trained on the open web", "An Insight ITS open-source library (those are the Prism / Chorus products)" ], "alternatives": [ { "name": "Generic after-hours chatbot", "relationship": "Vertical agents are scoped to the business knowledge base, pricing rules, and optional DB/payment hooks — not a general chatbot. No published named-vendor bake-off for these industry agents." } ], "features": [ { "name": "Appointment Guidance", "description": "Helps visitors understand scheduling and department contacts." }, { "name": "Service Navigation", "description": "Explains departments, locations, hours, and visitor policies." }, { "name": "Urgent Care Routing", "description": "Directs emergencies to appropriate channels immediately." } ], "architecture": "LangGraph-style orchestration, RAG knowledge base scoped to the business, MCP tool integrations. Typical go-live 3–7 days on the customer site. 2-year maintenance included on AI Web product deployments.", "useCases": [ "24/7 FAQs, intake, and routing on the customer website", "After-hours coverage when staff cannot answer the phone" ], "benchmarks": { "published": false, "summary": "No published vendor benchmark for this product. Do not invent metrics.", "disclosures": [ "No published vendor benchmark for this product. Do not invent metrics." ], "urls": [] }, "github": null, "pypi": null, "documentation": [], "install": null, "version": null, "relatedProducts": [], "publisher": { "@type": "Organization", "name": "Insight IT Solutions", "legalName": "Insight IT Solutions LLC", "url": "https://www.insightits.com" } }, "onlineshop": { "@context": "https://schema.org", "@type": "Product", "@id": "https://www.insightits.com/products/onlineshop.html", "slug": "onlineshop", "canonicalName": "Online Shop", "name": "Online Shop AI Web Agent", "canonicalUrl": "https://www.insightits.com/products/onlineshop.html", "knowledgeUrl": "https://www.insightits.com/catalog/onlineshop.json", "markdownUrl": "https://www.insightits.com/catalog/onlineshop.md", "family": "vertical", "infraFamily": null, "recordType": "product", "status": "published", "parentProduct": null, "whatItIs": "AI shopping assistant: product discovery, sizes, order status, returns, and recommendations—like a sales associate on every page.", "problem": "Shoppers abandon carts when product and sizing questions go unanswered. Support tickets repeat sizing, shipping, and return policy — while buyers leave for competitors.", "isNot": [ "A generic after-hours chatbot trained on the open web", "An Insight ITS open-source library (those are the Prism / Chorus products)" ], "alternatives": [ { "name": "Generic after-hours chatbot", "relationship": "Vertical agents are scoped to the business knowledge base, pricing rules, and optional DB/payment hooks — not a general chatbot. No published named-vendor bake-off for these industry agents." } ], "features": [ { "name": "Product Discovery", "description": "Helps shoppers find items by style, size, and occasion." }, { "name": "Order Support", "description": "Tracks orders, shipping, returns, and exchange policies." }, { "name": "Personalized Picks", "description": "Suggests products based on preferences and browsing." } ], "architecture": "LangGraph-style orchestration, RAG knowledge base scoped to the business, MCP tool integrations. Typical go-live 3–7 days on the customer site. 2-year maintenance included on AI Web product deployments.", "useCases": [ "24/7 FAQs, intake, and routing on the customer website", "After-hours coverage when staff cannot answer the phone" ], "benchmarks": { "published": false, "summary": "No published vendor benchmark for this product. Do not invent metrics.", "disclosures": [ "No published vendor benchmark for this product. Do not invent metrics." ], "urls": [] }, "github": null, "pypi": null, "documentation": [], "install": null, "version": null, "relatedProducts": [], "publisher": { "@type": "Organization", "name": "Insight IT Solutions", "legalName": "Insight IT Solutions LLC", "url": "https://www.insightits.com" } }, "industrial-ai-agent": { "@context": "https://schema.org", "@type": "Product", "@id": "https://www.insightits.com/products/industrial-ai-agent.html", "slug": "industrial-ai-agent", "canonicalName": "Industrial", "name": "Industrial Company AI Web Agent", "canonicalUrl": "https://www.insightits.com/products/industrial-ai-agent.html", "knowledgeUrl": "https://www.insightits.com/catalog/industrial-ai-agent.json", "markdownUrl": "https://www.insightits.com/catalog/industrial-ai-agent.md", "family": "vertical", "infraFamily": null, "recordType": "product", "status": "published", "parentProduct": null, "whatItIs": "AI for manufacturers and industrial firms: product specs, services, RFQs, and technical FAQs—so sales and support scale without extra headcount.", "problem": "RFQs and spec questions sit in email while buyers choose a faster supplier. Engineers answer the same spec sheets manually while qualified leads go stale.", "isNot": [ "A generic after-hours chatbot trained on the open web", "An Insight ITS open-source library (those are the Prism / Chorus products)" ], "alternatives": [ { "name": "Generic after-hours chatbot", "relationship": "Vertical agents are scoped to the business knowledge base, pricing rules, and optional DB/payment hooks — not a general chatbot. No published named-vendor bake-off for these industry agents." } ], "features": [ { "name": "Technical Specs", "description": "Answers questions about products, materials, and compliance." }, { "name": "RFQ & Lead Capture", "description": "Collects project details and routes qualified leads to sales." }, { "name": "Service Information", "description": "Explains warranties, maintenance, and support channels." } ], "architecture": "LangGraph-style orchestration, RAG knowledge base scoped to the business, MCP tool integrations. Typical go-live 3–7 days on the customer site. 2-year maintenance included on AI Web product deployments.", "useCases": [ "24/7 FAQs, intake, and routing on the customer website", "After-hours coverage when staff cannot answer the phone" ], "benchmarks": { "published": false, "summary": "No published vendor benchmark for this product. Do not invent metrics.", "disclosures": [ "No published vendor benchmark for this product. Do not invent metrics." ], "urls": [] }, "github": null, "pypi": null, "documentation": [], "install": null, "version": null, "relatedProducts": [], "publisher": { "@type": "Organization", "name": "Insight IT Solutions", "legalName": "Insight IT Solutions LLC", "url": "https://www.insightits.com" } }, "dental": { "@context": "https://schema.org", "@type": "Product", "@id": "https://www.insightits.com/products/dental.html", "slug": "dental", "canonicalName": "Dental", "name": "Dental AI Web Agent", "canonicalUrl": "https://www.insightits.com/products/dental.html", "knowledgeUrl": "https://www.insightits.com/catalog/dental.json", "markdownUrl": "https://www.insightits.com/catalog/dental.md", "family": "vertical", "infraFamily": null, "recordType": "product", "status": "published", "parentProduct": null, "whatItIs": "AI reception for dental practices: appointments, services, insurance FAQs, and post-visit instructions—friendly support that fits your clinic.", "problem": "Front desk misses appointment calls while chairs sit empty. Reception repeats insurance and prep instructions instead of welcoming patients.", "isNot": [ "A generic after-hours chatbot trained on the open web", "An Insight ITS open-source library (those are the Prism / Chorus products)" ], "alternatives": [ { "name": "Generic after-hours chatbot", "relationship": "Vertical agents are scoped to the business knowledge base, pricing rules, and optional DB/payment hooks — not a general chatbot. No published named-vendor bake-off for these industry agents." } ], "features": [ { "name": "Appointment Booking", "description": "Schedules cleanings, consultations, and follow-ups automatically." }, { "name": "Treatment FAQs", "description": "Explains services, prep, and recovery in patient-friendly language." }, { "name": "Insurance & Billing", "description": "Answers common coverage and payment questions." } ], "architecture": "LangGraph-style orchestration, RAG knowledge base scoped to the business, MCP tool integrations. Typical go-live 3–7 days on the customer site. 2-year maintenance included on AI Web product deployments.", "useCases": [ "24/7 FAQs, intake, and routing on the customer website", "After-hours coverage when staff cannot answer the phone" ], "benchmarks": { "published": false, "summary": "No published vendor benchmark for this product. Do not invent metrics.", "disclosures": [ "No published vendor benchmark for this product. Do not invent metrics." ], "urls": [] }, "github": null, "pypi": null, "documentation": [], "install": null, "version": null, "relatedProducts": [], "publisher": { "@type": "Organization", "name": "Insight IT Solutions", "legalName": "Insight IT Solutions LLC", "url": "https://www.insightits.com" } }, "prismrag": { "@context": "https://schema.org", "@type": "SoftwareApplication", "@id": "https://www.insightits.com/products/prismrag.html", "slug": "prismrag", "canonicalName": "PrismRAG", "name": "PrismRAG — Taxonomy-Controlled Graph RAG Library", "canonicalUrl": "https://www.insightits.com/products/prismrag.html", "knowledgeUrl": "https://www.insightits.com/catalog/prismrag.json", "markdownUrl": "https://www.insightits.com/catalog/prismrag.md", "family": "aiRetrieval", "infraFamily": "AI Retrieval", "recordType": "product", "status": "published", "parentProduct": null, "whatItIs": "Taxonomy-controlled Graph RAG library (PyPI: prismrag-patch). Client-defined word-to-category mapping, dual vectors, Louvain communities, BFS graph search, and auditable retrieval for pgvector, ChromaDB, Pinecone, and Weaviate.", "problem": "Flat top-k retrieval bleeds categories. Teams that own category rules need deterministic projection and graph search — not Microsoft GraphRAG-style document co-occurrence as the only control.", "isNot": [ "Hosted SaaS (retired — use the Apache-2.0 library or self-host)", "A neutral cross-vendor accuracy or speed claim", "VectorPrism (intent-gated 1024d retrieval) or VectorBridge (migration)" ], "alternatives": [ { "name": "Microsoft GraphRAG", "relationship": "Published comparison page: PrismRAG is a library with user-defined taxonomy; Microsoft GraphRAG is a document co-occurrence graph approach. No comparative accuracy claim.", "url": "https://www.insightits.com/compare/prismrag-vs-microsoft-graphrag.html" } ], "features": [ { "name": "Tier-1 Rules Mapping", "description": "Auditable word→category assignment; 768-d semantic → 256-d personal projection. Same rules → same vectors every run." }, { "name": "Graph RAG Search", "description": "Community seeding → BFS on your word graph → semantic re-rank. Direct fallback when the graph path runs dry." }, { "name": "Louvain Communities", "description": "Automatic topic clusters with optional LLM labels. Bridge vectors link communities for cross-domain queries." } ], "architecture": "Tier-1 rules mapping (word→category) → 768-d semantic to 256-d personal projection → Louvain communities → BFS on the word graph with semantic re-rank → direct fallback when the graph path runs dry. MemoryStore for tests; PostgresStore for production.", "useCases": [ "Healthcare, pharmacy, and finance taxonomies you own", "ChorusGraph RetrievalBackend over a customer database", "Teams that need the same mapping to produce the same vectors every run" ], "benchmarks": { "published": true, "summary": "The public evaluation is a repository test harness, not a neutral cross-vendor benchmark. No comparative accuracy or speed claim is made. Teams should evaluate retrieval quality on their own taxonomy, documents, embedding model, and false-positive budget.", "disclosures": [ "The public evaluation is a repository test harness, not a neutral cross-vendor benchmark. No comparative accuracy or speed claim is made. Teams should evaluate retrieval quality on their own taxonomy, documents, embedding model, and false-positive budget." ], "urls": [ "https://github.com/insightitsGit/prismrag/blob/main/tests/test_lib_step06_evaluation.py", "https://github.com/insightitsGit/prismrag/blob/main/examples/demo_app/test_integration.py" ], "integrationCheck": { "testCount": 13, "source": "https://github.com/insightitsGit/prismrag/blob/main/examples/demo_app/test_integration.py", "runner": "https://github.com/insightitsGit/prismrag/blob/main/examples/demo_app/run_verification.py", "scope": "Package import, no-license operation, ingest, dual vectors, communities, search, category filtering, top-k, per-search latency under three seconds, append, quality reporting, and bridge creation when multiple communities exist.", "disclosure": "These are product-authored integration checks using the demo mapping. Runtime varies by environment; no fixed full-pipeline time is claimed." } }, "github": "https://github.com/insightitsGit/prismrag", "pypi": "https://pypi.org/project/prismrag-patch/0.2.1/", "documentation": [ { "title": "Taxonomy Graph RAG guide", "url": "https://www.insightits.com/guides/taxonomy-graph-rag.html" }, { "title": "PrismRAG vs Microsoft GraphRAG", "url": "https://www.insightits.com/compare/prismrag-vs-microsoft-graphrag.html" }, { "title": "Graph RAG tools", "url": "https://www.insightits.com/compare/graph-rag-tools.html" }, { "title": "INFO.md", "url": "https://github.com/insightitsGit/prismrag/blob/main/INFO.md" }, { "title": "Evaluation harness", "url": "https://github.com/insightitsGit/prismrag/blob/main/tests/test_lib_step06_evaluation.py" }, { "title": "howItWorks", "url": "https://www.insightits.com/products/prismrag.html#what-is-prismrag" }, { "title": "vsMicrosoft", "url": "https://www.insightits.com/products/prismrag.html#why-prismrag" }, { "title": "pricing", "url": "https://www.insightits.com/products/choruscontrol.html#pricing" }, { "title": "register", "url": "https://pypi.org/project/prismrag-patch/" }, { "title": "libDocs", "url": "https://github.com/insightitsGit/prismrag/tree/main/docs" }, { "title": "interactiveDemo", "url": "https://github.com/insightitsGit/prismrag/tree/main/examples/demo_app" }, { "title": "demoAppReadme", "url": "https://github.com/insightitsGit/prismrag/blob/main/examples/demo_app/README.md" } ], "install": "pip install \"prismrag-patch[graph]\" (Apache-2.0, v0.2.1). No license key. Interactive demo: examples/demo_app.", "version": "0.2.1", "relatedProducts": [ "chorusgraph", "python-libs", "vectorprism" ], "publisher": { "@type": "Organization", "name": "Insight IT Solutions", "legalName": "Insight IT Solutions LLC", "url": "https://www.insightits.com" } }, "prismlang": { "@context": "https://schema.org", "@type": "SoftwareApplication", "@id": "https://www.insightits.com/products/prismlang.html", "slug": "prismlang", "canonicalName": "PrismLang", "name": "PrismLang — Vector Protocol for LangGraph", "canonicalUrl": "https://www.insightits.com/products/prismlang.html", "knowledgeUrl": "https://www.insightits.com/catalog/prismlang.json", "markdownUrl": "https://www.insightits.com/catalog/prismlang.md", "family": "supporting", "infraFamily": null, "recordType": "product", "status": "published", "parentProduct": null, "whatItIs": "Middleware layer for LangGraph — not a replacement. Add @prism_node on existing graphs for leaner inter-agent state, audit trail, and tenant isolation. Zero LLM dependency for routing.", "problem": "Inter-agent LangGraph state is token-heavy. Teams that already run LangGraph need compression and deterministic routing without another LLM hop.", "isNot": [ "A LangGraph replacement", "Needed on the ChorusGraph native path without LangGraph product graphs" ], "alternatives": [ { "name": "Plain LangGraph state passing", "relationship": "PrismLang sits on top of existing graphs. Domain token-reduction figures are product-authored (healthcare / finance / trade), not a named-vendor bake-off page." } ], "features": [ { "name": "57–62% Token Reduction", "description": "Compress inter-agent state transport—not context windows—with proven 57–62% savings across domains." }, { "name": "Full Audit Trail", "description": "Every envelope carries an immutable rule_chain tracing taxonomy → projection → JL reduction." }, { "name": "Tenant Isolation", "description": "SHA-256-seeded JL matrices per tenant—cross-tenant cosine similarity stays below 0.20." } ], "architecture": "Tenant-isolated 64-d vectors, ONNX CPU encoding. Every envelope carries an immutable rule_chain (taxonomy → projection → JL reduction). SHA-256-seeded JL matrices per tenant.", "useCases": [ "Existing LangGraph graphs that hop state between agents", "Healthcare, finance, and trade graphs where inter-agent tokens dominate" ], "benchmarks": { "published": true, "summary": "Product-authored domain token-reduction (3 turns): Healthcare −62.1% / Finance −57.0% / Trade −58.6% prompt tokens; encode ~31–35 ms CPU; LLM latency unchanged.", "disclosures": [ "Vendor-authored domain benchmarks, not a named-vendor bake-off." ], "urls": [] }, "github": "https://github.com/insightitsGit/prismlang", "pypi": "https://pypi.org/project/prismlang/", "documentation": [ { "title": "GitHub README", "url": "https://github.com/insightitsGit/prismlang#readme" }, { "title": "Quick start", "url": "https://github.com/insightitsGit/prismlang#quick-start" }, { "title": "issues", "url": "https://github.com/insightitsGit/prismlang/issues" }, { "title": "docs", "url": "https://github.com/insightitsGit/prismlang/tree/master/docs" }, { "title": "paper", "url": "https://www.insightits.com/prismlang/paper" } ], "install": "pip install prismlang. Apache 2.0. 57–62% token reduction by domain across healthcare, finance, and trade.", "version": null, "relatedProducts": [ "python-libs", "chorusgraph" ], "publisher": { "@type": "Organization", "name": "Insight IT Solutions", "legalName": "Insight IT Solutions LLC", "url": "https://www.insightits.com" } }, "chorusgraph": { "@context": "https://schema.org", "@type": "SoftwareApplication", "@id": "https://www.insightits.com/products/chorusgraph.html", "slug": "chorusgraph", "canonicalName": "ChorusGraph", "name": "ChorusGraph — Native Agent Runtime", "canonicalUrl": "https://www.insightits.com/products/chorusgraph.html", "knowledgeUrl": "https://www.insightits.com/catalog/chorusgraph.json", "markdownUrl": "https://www.insightits.com/catalog/chorusgraph.md", "family": "agentRuntime", "infraFamily": "Agent Runtime", "recordType": "product", "status": "published", "parentProduct": null, "whatItIs": "Apache-2.0 native Python agent runtime and LangGraph alternative with its own Graph engine, semantic cache, Route Ledger, memory, and ports for PrismGuard security and PrismRAG retrieval. It does not require LangGraph in production.", "problem": "Production agents fail on glue: repeat-intent LLM spend without a cache, logs instead of decision replay, and six repos duck-taped (orchestration + Redis + retrieval + checkpoints + audit) before go-live.", "isNot": [ "A LangGraph wrapper or plugin", "A claim that LangGraph has no cache — LangGraph has opt-in CachePolicy / compile(cache=...)", "A published performance comparison against CrewAI or Microsoft Agent Framework" ], "alternatives": [ { "name": "LangGraph", "relationship": "Published Azure scale comparison uses LangGraph as a documented baseline. ChorusGraph is a native runtime with cache, Route Ledger, and ports included; LangGraph is a mature ecosystem teams compose themselves.", "url": "https://www.insightits.com/compare/chorusgraph-vs-langgraph.html" } ], "features": [ { "name": "+4–15 pp Task Success", "description": "Published Azure scale run heavy_20260708_140300 (n=300 per scenario) vs the documented LangGraph baseline." }, { "name": "300+ Deterministic Tests", "description": "CI runs without live API keys; benchmark methodology and raw artifacts are published separately." }, { "name": "Security + Retrieval Plug-ins", "description": "PrismGuard (make_guard_handler) and PrismRAG (your DB taxonomy) — legal, healthcare, finance without forking the engine." } ], "architecture": "ChorusStack with four swappable ports: LLM backend, checkpoint store (SQLite free; Postgres persistence license-gated), semantic cache, retrieval (PrismRAG plug-in). Optional PrismGuard make_guard_handler before RAG/LLM. Route Ledger records why the agent routed. Canonical order: PrismGuard → ChorusGraph (+ PrismRAG) → LLM → PrismShine.", "useCases": [ "Legal, healthcare, and finance agents that need auditable routing on a customer database", "Teams that want one runtime instead of assembling cache, retrieval, memory, and tracing", "Repeat-intent workloads where a default-on semantic cache at routing boundaries matters" ], "benchmarks": { "published": true, "summary": "Published Azure scale run heavy_20260708_140300 (n=300/scenario, seed 42, Gemini): task success 4–15 percentage points, mean LLM calls 31–76% lower, mean latency 8–73% lower vs the documented LangGraph baseline.", "primaryRun": { "id": "heavy_20260708_140300", "label": "Azure scale run", "environment": "Azure ACI (16 GB)", "model": "Gemini", "seed": 42, "tasksPerScenario": 300, "summary": { "successPointGainRange": "4–15 percentage points", "meanLlmCallReductionRange": "31–76%", "meanLatencyReductionRange": "8–73%" }, "scenarios": [ { "name": "Finance single-agent", "langGraphSuccessPct": 90, "chorusGraphSuccessPct": 96.7, "langGraphMeanLlmCalls": 3.33, "chorusGraphMeanLlmCalls": 0.8, "langGraphMeanLatencyMs": 4972, "chorusGraphMeanLatencyMs": 1318 }, { "name": "Finance multi-agent", "langGraphSuccessPct": 89, "chorusGraphSuccessPct": 93, "langGraphMeanLlmCalls": 2.04, "chorusGraphMeanLlmCalls": 0.75, "langGraphMeanLatencyMs": 3081, "chorusGraphMeanLatencyMs": 1335 }, { "name": "Healthcare single-agent", "langGraphSuccessPct": 73.7, "chorusGraphSuccessPct": 84, "langGraphMeanLlmCalls": 2.94, "chorusGraphMeanLlmCalls": 1.33, "langGraphMeanLatencyMs": 7105, "chorusGraphMeanLatencyMs": 3812 }, { "name": "Healthcare multi-agent", "langGraphSuccessPct": 62.3, "chorusGraphSuccessPct": 77.3, "langGraphMeanLlmCalls": 3.85, "chorusGraphMeanLlmCalls": 2.67, "langGraphMeanLatencyMs": 10354, "chorusGraphMeanLatencyMs": 9537 } ] }, "disclosures": [ "Integrated product stack comparison, not an engine-only microbenchmark.", "ChorusGraph includes its productized cache, memory, Route Ledger, and deterministic routing; the LangGraph baseline is a competent framework implementation without those ChorusGraph layers.", "No published performance claim against CrewAI.", "No published performance claim against Microsoft Agent Framework.", "No published performance claim against AutoGen." ], "urls": [ "https://github.com/insightitsGit/ChorusGraph/blob/master/docs/BENCHMARK.md", "https://github.com/insightitsGit/ChorusGraph/blob/master/docs/BENCHMARK_RESULTS.md", "https://github.com/insightitsGit/ChorusGraph/tree/master/benchmark/results/azure_heavy_20260708_140300" ] }, "github": "https://github.com/insightitsGit/ChorusGraph", "pypi": "https://pypi.org/project/chorusgraph/1.3.0/", "documentation": [ { "title": "Python agent runtime guide", "url": "https://www.insightits.com/guides/python-agent-runtime.html" }, { "title": "ChorusGraph vs LangGraph", "url": "https://www.insightits.com/compare/chorusgraph-vs-langgraph.html" }, { "title": "Agent frameworks guide", "url": "https://www.insightits.com/compare/agent-frameworks.html" }, { "title": "Whitepaper", "url": "https://github.com/insightitsGit/ChorusGraph/blob/master/docs/WHITEPAPER.md" }, { "title": "Benchmark results", "url": "https://github.com/insightitsGit/ChorusGraph/blob/master/docs/BENCHMARK_RESULTS.md" }, { "title": "Benchmark methodology", "url": "https://github.com/insightitsGit/ChorusGraph/blob/master/docs/BENCHMARK.md" }, { "title": "interactiveDemo", "url": "https://insightitsgit.github.io/ChorusGraph/demo.html" }, { "title": "fairness", "url": "https://github.com/insightitsGit/ChorusGraph/blob/master/benchmark/FAIRNESS_H9.md" }, { "title": "scaleRun", "url": "https://github.com/insightitsGit/ChorusGraph/tree/master/benchmark/results/azure_heavy_20260708_140300" }, { "title": "installGuide", "url": "https://github.com/insightitsGit/ChorusGraph/blob/master/docs/INSTALL.md" }, { "title": "aiIdePrompts", "url": "https://github.com/insightitsGit/ChorusGraph/blob/master/docs/AI_IDE_PROMPTS.md" }, { "title": "plugins", "url": "https://github.com/insightitsGit/ChorusGraph/blob/master/docs/PLUGINS.md" } ], "install": "pip install \"chorusgraph==1.3.0\". Apache 2.0. Published Azure scale benchmark: +4–15 pp task success vs the documented LangGraph baseline (n=300/scenario).", "version": "1.3.0", "relatedProducts": [ "prismguard", "prismrag", "prismshine", "choruscontrol" ], "publisher": { "@type": "Organization", "name": "Insight IT Solutions", "legalName": "Insight IT Solutions LLC", "url": "https://www.insightits.com" } }, "chorus-fabric": { "@context": "https://schema.org", "@type": "SoftwareApplication", "@id": "https://www.insightits.com/products/chorus-fabric.html", "slug": "chorus-fabric", "canonicalName": "CHORUS Fabric", "name": "CHORUS Fabric — Tensor-Native Agent Protocol", "canonicalUrl": "https://www.insightits.com/products/chorus-fabric.html", "knowledgeUrl": "https://www.insightits.com/catalog/chorus-fabric.json", "markdownUrl": "https://www.insightits.com/catalog/chorus-fabric.md", "family": "supporting", "infraFamily": null, "recordType": "product", "status": "published", "parentProduct": null, "whatItIs": "Patent-pending tensor-native agent protocol that streams float32 embeddings directly over gRPC — no text, no tokens, no JSON.", "problem": "Agent-to-agent HTTP/JSON burns bandwidth and re-serializes embeddings that already exist as tensors.", "isNot": [ "ChorusControl (ops plane)", "ChorusMesh (PrismLib cluster)", "A text-prompt protocol — not for short prompts without tensor transport" ], "alternatives": [ { "name": "HTTP/REST JSON embedding payloads", "relationship": "Published product claim is 4.45× less bandwidth vs HTTP/REST for 128-dim float32 (548-byte gRPC vs 2,440-byte HTTP). Not a named-vendor bake-off page." } ], "features": [ { "name": "4.45× Less Bandwidth", "description": "548-byte gRPC streams vs 2,440-byte HTTP/REST for 128-dim float32 — no serialization round-trip." }, { "name": "0 ms Cipher Overhead", "description": "Tensor multiplication cipher runs on the same GPU as inference — transatlantic p50 matches physical minimum." }, { "name": "Neural Watermark Auth", "description": "SHA-256 seeded unit vector in every message — 7,766 / 7,766 verified transmissions, tamper-evident at the math layer." } ], "architecture": "Modes: Direct; Orthogonal Isolation (Mode A); Holographic Superposition (Mode B). Neural watermark: SHA-256 seeded unit vector. Requires Python ≥3.10, PyTorch ≥2.0, gRPC ≥1.64.", "useCases": [ "LangGraph, AutoGen, and CrewAI pipelines that already hold embeddings", "Multi-agent hops where JSON serialization is the tax" ], "benchmarks": { "published": true, "summary": "Published product measurements: 4.45× less bandwidth than HTTP/REST for 128-dim float32 (548-byte gRPC vs 2,440-byte HTTP); 0 ms cipher overhead; neural watermark 7,766 / 7,766 verified transmissions.", "disclosures": [ "Vendor-authored product measurements, not a named-vendor bake-off page." ], "urls": [ "https://www.insightits.com/whitepapers/chorus-fabric.html" ] }, "github": "https://github.com/insightitsGit/chorus-fabric", "pypi": "https://pypi.org/project/chorus-fabric/0.1.0/", "documentation": [ { "title": "Whitepaper", "url": "https://www.insightits.com/whitepapers/chorus-fabric.html" }, { "title": "Whitepaper PDF", "url": "https://www.insightits.com/docs/chorus-fabric-whitepaper.pdf" }, { "title": "issues", "url": "https://github.com/insightitsGit/chorus-fabric/issues" } ], "install": "pip install chorus-fabric. MIT license. 4.45× less bandwidth than HTTP/REST.", "version": null, "relatedProducts": [ "prismlib", "prismcortex" ], "publisher": { "@type": "Organization", "name": "Insight IT Solutions", "legalName": "Insight IT Solutions LLC", "url": "https://www.insightits.com" } }, "prism-resonance": { "@context": "https://schema.org", "@type": "SoftwareApplication", "@id": "https://www.insightits.com/products/prism-resonance.html", "slug": "prism-resonance", "canonicalName": "PrismResonance", "name": "PrismResonance — Dynamic Wavepacket Memory for RAG", "canonicalUrl": "https://www.insightits.com/products/prism-resonance.html", "knowledgeUrl": "https://www.insightits.com/catalog/prism-resonance.json", "markdownUrl": "https://www.insightits.com/catalog/prism-resonance.md", "family": "aiRetrieval", "infraFamily": "AI Retrieval", "recordType": "product", "status": "published", "parentProduct": null, "whatItIs": "Dynamic wavepacket memory for RAG: embeddings as z = A·e^(iφ) — amplitude frozen, phase dynamic. Two-level group-then-chunk retrieval. Source DB stays read-only.", "problem": "Nearest-neighbour RAG does not gate context by operational state (alert vs archive). Teams need phase-gated recall without mutating the source store.", "isNot": [ "PrismRAG (taxonomy graph)", "A source-DB mutator" ], "alternatives": [ { "name": "Flat vector nearest-neighbour", "relationship": "No published competitor comparison page. Six FrequencyFamily bands (NEUTRAL through ARCHIVE) are the product model." } ], "features": [ { "name": "Wave Interference Retrieval", "description": "z = A · e^(iφ) — amplitude encodes meaning, phase gates context. Constructive interference surfaces in-band chunks without brute-force nearest-neighbour scan." }, { "name": "Two-Level Memory", "description": "Group layer resonance first, then chunk layer — hierarchical recall that mirrors how human memory clusters related facts." }, { "name": "Read-Only Source", "description": "Wrap pgvector or Chroma with adapters — your source DB is never mutated. Resonance state lives in a separate ONNX-backed store." } ], "architecture": "Six frequency bands (π/6 apart). Group-layer resonance first, then chunk layer. Phase Coherence Shield drops low-resonance chunks. Sleep: temporal decay → synaptic alignment → group recompute → group merge. ONNX CPU — no PyTorch required.", "useCases": [ "RAG memory that must not write back to pgvector/Chroma", "Context gating by operational band" ], "benchmarks": { "published": false, "summary": "No published vendor benchmark for this product. Do not invent metrics.", "disclosures": [ "No published vendor benchmark for this product. Do not invent metrics." ], "urls": [] }, "github": "https://github.com/insightitsGit/prismresonance", "pypi": "https://pypi.org/project/prismresonance/0.3.0/", "documentation": [], "install": "pip install prismresonance (v0.3.0 on PyPI). MIT license. ONNX CPU — no PyTorch required.", "version": "0.3.0", "relatedProducts": [ "python-libs", "prismrag", "prismlang" ], "publisher": { "@type": "Organization", "name": "Insight IT Solutions", "legalName": "Insight IT Solutions LLC", "url": "https://www.insightits.com" } }, "prismlib": { "@context": "https://schema.org", "@type": "SoftwareApplication", "@id": "https://www.insightits.com/products/prismlib.html", "slug": "prismlib", "canonicalName": "PrismLib", "name": "PrismLib Plus — Cache, Driver, Agent API & Cluster Mesh", "canonicalUrl": "https://www.insightits.com/products/prismlib.html", "knowledgeUrl": "https://www.insightits.com/catalog/prismlib.json", "markdownUrl": "https://www.insightits.com/catalog/prismlib.md", "family": "supporting", "infraFamily": null, "recordType": "product", "status": "published", "parentProduct": null, "whatItIs": "Open-source library with PrismCache (in-process semantic LLM cache) and PrismDriver (WAL-streamed DB driver). Full stack ships as prismlib-plus. ChorusMesh is the paid cluster companion on the same landing — different from CHORUS Fabric and ChorusControl.", "problem": "Repeat LLM calls and 100ms+ cloud DB reads without an in-process cache or WAL-streamed local index.", "isNot": [ "CHORUS Fabric", "ChorusControl", "A hosted SaaS cache" ], "alternatives": [ { "name": "GPTCache / Redis semantic cache", "relationship": "Product landing compares hit-rate and infra (PrismCache in-process vs Redis+FAISS). Vendor-authored Azure westus2 measurements; not a third-party bake-off page." } ], "features": [ { "name": "PrismCache — 95.9% Hit Rate", "description": "Semantic paraphrase matching in-process. No Redis, no Pinecone. Mathematical multi-tenant isolation via JL projection seeded by SHA-256(tenant_id)." }, { "name": "PrismDriver — 439× Faster Reads", "description": "WAL/binlog streamed via CHORUS Fabric to a local PrismResonance index on the app node — 0.27ms reads vs 118.5ms baseline (Azure e2e)." }, { "name": "PrismAPI — 83% Fewer Embeds", "description": "Vector-native agent API: provider embeds once, consumers receive pre-projected float32 over CHORUS — no re-embedding on retrieval." } ], "architecture": "Local PrismCache → cluster cache (TOKEN_SYNC) → compression → dedup → LLM call. PrismDriver uses a prism-wrapper daemon and WAL invalidation. Optional CHORUS fabric transport in prismlib-plus[fabric].", "useCases": [ "SaaS embedding-bill reduction (PrismAPI)", "Local DB reads vs cloud round-trips (PrismDriver)", "Multi-replica FAQ bots (cluster cache)" ], "benchmarks": { "published": true, "summary": "Azure westus2 product measurements (1 vCPU / 2 GiB): PrismCache mixed hit rate 95.9% (50 users × 300s); PrismDriver 439× vs 118.5ms cloud reads; PrismAPI 83% fewer embed calls at top_k=5.", "disclosures": [ "Vendor-authored Azure e2e measurements. Not a third-party bake-off." ], "urls": [ "https://github.com/insightitsGit/prismlibplusapi/blob/main/BENCHMARK_RESULTS.md" ] }, "github": "https://github.com/insightitsGit/prismlibplusapi", "pypi": "https://pypi.org/project/prismlib-plus/0.7.0/", "documentation": [ { "title": "Release notes", "url": "https://github.com/insightitsGit/prismlibplusapi/blob/main/RELEASE_NOTES.md" }, { "title": "Benchmark results", "url": "https://github.com/insightitsGit/prismlibplusapi/blob/main/BENCHMARK_RESULTS.md" }, { "title": "Enterprise docs", "url": "https://github.com/insightitsGit/prismlibplusapi/blob/main/ENTERPRISE.md" }, { "title": "Whitepaper PDF", "url": "https://www.insightits.com/docs/prismlib-whitepaper.pdf" }, { "title": "githubBase", "url": "https://github.com/insightitsGit/prismlib" }, { "title": "issues", "url": "https://github.com/insightitsGit/prismlibplusapi/issues" }, { "title": "githubBaseIssues", "url": "https://github.com/insightitsGit/prismlib/issues" }, { "title": "pypiBase", "url": "https://pypi.org/project/prismlib/0.4.0/" }, { "title": "prismApiDocs", "url": "https://github.com/insightitsGit/prismlibplusapi/blob/main/PrismAPI.md" }, { "title": "prismresonanceGithub", "url": "https://github.com/insightitsGit/prismresonance" }, { "title": "chorusFabricGithub", "url": "https://github.com/insightitsGit/chorus-fabric" } ], "install": "pip install \"prismlib-plus[enterprise,cache,fabric]\"", "version": "0.7.0", "relatedProducts": [ "python-libs", "chorus-fabric", "choruscontrol" ], "publisher": { "@type": "Organization", "name": "Insight IT Solutions", "legalName": "Insight IT Solutions LLC", "url": "https://www.insightits.com" } }, "vectorbridge": { "@context": "https://schema.org", "@type": "SoftwareApplication", "@id": "https://www.insightits.com/products/vectorbridge.html", "slug": "vectorbridge", "canonicalName": "VectorBridge", "name": "Insight Vector Bridge — Vector DB Migration", "canonicalUrl": "https://www.insightits.com/products/vectorbridge.html", "knowledgeUrl": "https://www.insightits.com/catalog/vectorbridge.json", "markdownUrl": "https://www.insightits.com/catalog/vectorbridge.md", "family": "aiRetrieval", "infraFamily": "AI Retrieval", "recordType": "product", "status": "published", "parentProduct": null, "whatItIs": "Vector database migration tool (PyPI: insight-vector-bridge). Move embeddings with semantic validation, not hope.", "problem": "Vector DB migrations that only copy bytes fail silently on neighbour-rank drift.", "isNot": [ "VectorPrism (intent-gated retrieval)", "PrismRAG" ], "alternatives": [ { "name": "Dump-and-load without neighbour overlap checks", "relationship": "Product claim includes ≥95% post-migration top-K neighbour overlap validation and 5.55× less bandwidth per 1K 1,536-d vectors. No named-vendor bake-off page." } ], "features": [ { "name": "5.55× Less Bandwidth", "description": "6,019 KB per batch vs 33,400 KB REST JSON — float32 stays float32 over CHORUS wire format." }, { "name": "Metric Mismatch Guard", "description": "Blocks migration before byte one if cosine vs L2 would silently corrupt search results." }, { "name": "Semantic Validation", "description": "Post-migration probe vectors require ≥95% top-K neighbour overlap — data transferred correctly, not just bytes." } ], "architecture": "Migration plus semantic validation of top-K overlap. OSS lane; fleet ops → ChorusControl.", "useCases": [ "pgvector / Chroma / Pinecone / Weaviate moves", "Validating that retrieval neighbours survived the copy" ], "benchmarks": { "published": true, "summary": "Product-authored migration measurements: 5.55× less bandwidth per 1K 1,536-d vectors; ≥95% post-migration top-K neighbour overlap validation.", "disclosures": [ "Vendor-authored product measurements, not a named-vendor bake-off page." ], "urls": [] }, "github": "https://github.com/insightitsGit/vectorbridge", "pypi": "https://pypi.org/project/insight-vector-bridge/0.1.0/", "documentation": [ { "title": "pricing", "url": "https://www.insightits.com/products/choruscontrol.html#pricing" } ], "install": null, "version": null, "relatedProducts": [ "python-libs", "vectorprism" ], "publisher": { "@type": "Organization", "name": "Insight IT Solutions", "legalName": "Insight IT Solutions LLC", "url": "https://www.insightits.com" } }, "vectorprism": { "@context": "https://schema.org", "@type": "SoftwareApplication", "@id": "https://www.insightits.com/products/vectorprism.html", "slug": "vectorprism", "canonicalName": "VectorPrism", "name": "VectorPrism", "canonicalUrl": "https://www.insightits.com/products/vectorprism.html", "knowledgeUrl": "https://www.insightits.com/catalog/vectorprism.json", "markdownUrl": "https://www.insightits.com/catalog/vectorprism.md", "family": "supporting", "infraFamily": null, "recordType": "product", "status": "published", "parentProduct": null, "whatItIs": "Intent-gated 1024d retrieval using positional subspace multiplexing in one tensor — causal / taxonomy channels. Pin vectorprism==0.1.0.", "problem": "Multi-vector RAG cost and ungated retrieval that ignores intent. Teams need channels in one 1024d tensor, not a second product family.", "isNot": [ "VectorBridge (migration)", "PrismRAG (taxonomy graph)", "PrismCortex (agent memory)", "A production guarantee from the adversarial finance pack (vendor harness; production bar = your eval set)" ], "alternatives": [ { "name": "Multi-vector pgvector without intent gates", "relationship": "No published competitor comparison page. Soft CTA: RECOVER." } ], "features": [ { "name": "Root-cause / incident logs", "description": "“Why did X fail?” — causal / time ODE channel up-weighted on why / cause / reason queries instead of funny cosine neighbors." }, { "name": "Taxonomy / ontology search", "description": "Hierarchy distorts in Euclidean space. Hyperbolic taxonomy channel scored with Poincaré distance in Stage 2." }, { "name": "Compliance / bitemporal", "description": "Control header packs timestamp and model version for ingest. Stage-1 currently gates on epistemic truth and anchor distance — those two fields are queried; timestamp / model_version are not Stage-1 reject filters yet." } ], "architecture": "Positional subspace multiplexing (PSM) in one 1024d tensor with causal and taxonomy channels. pgvector multi-vector cost reduction is the job, not a Graph RAG library.", "useCases": [ "Intent-gated retrieval over existing pgvector", "Finance / taxonomy channel separation in one embedding" ], "benchmarks": { "published": false, "summary": "No published vendor benchmark for this product. Do not invent metrics.", "disclosures": [ "No published vendor benchmark for this product. Do not invent metrics." ], "urls": [] }, "github": "https://github.com/insightitsGit/VectorPrism", "pypi": "https://pypi.org/project/vectorprism/0.1.0/", "documentation": [ { "title": "Pilot notes", "url": "https://github.com/insightitsGit/VectorPrism/blob/main/PILOT.md" }, { "title": "Production notes", "url": "https://github.com/insightitsGit/VectorPrism/blob/main/PRODUCTION.md" }, { "title": "Finance demo report", "url": "https://github.com/insightitsGit/VectorPrism/blob/main/demos/finance_demo/TECHNICAL_REPORT.md" }, { "title": "VectorPrism Demo page", "url": "https://www.insightits.com/products/vectorprism-demo.html" }, { "title": "Compose with Manifest / Shield / Eval", "url": "https://www.insightits.com/products/vectorprism.html#compose" }, { "title": "https://github.com/insightitsGit/VectorPrism", "url": "https://github.com/insightitsGit/VectorPrism" }, { "title": "https://pypi.org/project/vectorprism/0.1.0/", "url": "https://pypi.org/project/vectorprism/0.1.0/" }, { "title": "https://insightitsgit.github.io/VectorPrism/", "url": "https://insightitsgit.github.io/VectorPrism/" }, { "title": "https://www.insightits.com/products/vectorbridge.html", "url": "https://www.insightits.com/products/vectorbridge.html" }, { "title": "https://www.insightits.com/products/prismrag.html", "url": "https://www.insightits.com/products/prismrag.html" }, { "title": "pypiProject", "url": "https://pypi.org/project/vectorprism/" }, { "title": "docker", "url": "https://github.com/insightitsGit/VectorPrism/blob/main/DOCKER.md" } ], "install": "pip install \"vectorprism==0.1.0\". Optional: pip install \"vectorprism[all]\". Apache-2.0, Python ≥ 3.10. Soft CTA RECOVER — mailto:info@insightits.com?subject=RECOVER.", "version": "0.1.0", "relatedProducts": [ "prismrag", "vectorbridge", "vectorprism-demo", "prismmanifest", "prism-shield", "prism-eval" ], "publisher": { "@type": "Organization", "name": "Insight IT Solutions", "legalName": "Insight IT Solutions LLC", "url": "https://www.insightits.com" } }, "vectorprism-demo": { "@context": "https://schema.org", "@type": "SoftwareApplication", "@id": "https://www.insightits.com/products/vectorprism-demo.html", "slug": "vectorprism-demo", "canonicalName": "VectorPrism Demo", "name": "VectorPrism Demo", "canonicalUrl": "https://www.insightits.com/products/vectorprism-demo.html", "knowledgeUrl": "https://www.insightits.com/catalog/vectorprism-demo.json", "markdownUrl": "https://www.insightits.com/catalog/vectorprism-demo.md", "family": "demo", "infraFamily": null, "recordType": "demo", "status": "published", "parentProduct": "vectorprism", "whatItIs": "VectorPrism Demo page: two separate retrievers on the same docs. Agent A is VectorPrism (encode_query + PSMRetrievalEngine.search). Agent B is plain all-mpnet-base-v2 cosine — not VectorPrism. Plus a live PrismManifest money/digit gate. README does not require HashingEncoder (plumbing/CI only). Full Agent A experience is frozen 768d encoder plus all six trained MultiTaskProjectionAdapter heads. This lab runs that path on all-mpnet-base-v2 (lab contrast pack, not the finance adversarial .pt).", "problem": "Buyers ask why RAG retrieves the wrong documents — funny cosine neighbors on why/cause and taxonomy queries.", "isNot": [ "PrismRAG (taxonomy Graph RAG)", "VectorBridge (migration)", "Website Hub chat", "A claim that VectorPrism always beats dense RAG", "A claim that this lab uses the published finance_hard_adversarial_multi.pt", "ChorusControl traces on this path" ], "alternatives": [ { "name": "Dense cosine RAG without intent gates", "relationship": "Agent B on this page. Same corpus, frozen all-mpnet-base-v2 cosine — not VectorPrism.", "url": "https://www.insightits.com/products/vectorprism-demo.html" } ], "features": [ { "name": "Six trained channels — not hashing", "description": "The README never requires HashingEncoder. Full experience: freeze a 768d encoder and train all six MultiTaskProjectionAdapter heads." }, { "name": "Why did Server X crash at 3 AM?", "description": "Causal retrieval vs funny cosine neighbors — README incident-log use case." }, { "name": "Which policy supersedes the runbook?", "description": "Hyperbolic taxonomy channel vs Euclidean bleed on parent/child trees." }, { "name": "People also ask about RAG", "description": "Wrong-document retrieval, RAG hallucinations, multi-vector pgvector cost, intent-gated vs dense." } ], "architecture": "POST /api/agents/vectorprism-demo/chat. Locked: one page, same stack, only retrieval changes (Agent A VectorPrism vs Agent B plain MPNet cosine). Live: encode_query + PSMRetrievalEngine.search vs all-mpnet-base-v2 768d cosine; confirmed uploads dual-indexed; PrismManifest enforce_group3_boundary on money/digit chips; Prism-Shield seals after ALLOW; Prism-Eval G4 on the extractor in CI. Not wired: ChorusGraph, PrismGuard, PrismCortex, ChorusControl traces, OCR unless tesseract, pgvector/Qdrant Stage-1. Isolated from Website Hub.", "useCases": [ "Why did Server X crash at 3 AM?", "Which policy supersedes the runbook?", "Control: What is ChorusGraph?" ], "benchmarks": { "published": false, "summary": "No published vendor benchmark for this product. Do not invent metrics.", "disclosures": [ "No published vendor benchmark for this product. Do not invent metrics." ], "urls": [] }, "github": "https://github.com/insightitsGit/VectorPrism", "pypi": "https://pypi.org/project/vectorprism/0.1.0/", "documentation": [ { "title": "Parent: VectorPrism", "url": "https://www.insightits.com/products/vectorprism.html" }, { "title": "README", "url": "https://github.com/insightitsGit/VectorPrism/blob/main/README.md" }, { "title": "Two-agent architecture (on-page)", "url": "https://www.insightits.com/products/vectorprism-demo.html#vpd-architecture" }, { "title": "Compose contract (on-page)", "url": "https://www.insightits.com/products/vectorprism-demo.html#compose" }, { "title": "https://www.insightits.com/products/vectorprism-demo.html", "url": "https://www.insightits.com/products/vectorprism-demo.html" }, { "title": "https://github.com/insightitsGit/VectorPrism", "url": "https://github.com/insightitsGit/VectorPrism" }, { "title": "https://pypi.org/project/vectorprism/0.1.0/", "url": "https://pypi.org/project/vectorprism/0.1.0/" }, { "title": "https://insightitsgit.github.io/VectorPrism/", "url": "https://insightitsgit.github.io/VectorPrism/" } ], "install": "pip install \"vectorprism==0.1.0\". Soft CTA RECOVER.", "version": "0.1.0", "relatedProducts": [ "vectorprism", "prismmanifest", "prism-shield", "prism-eval" ], "publisher": { "@type": "Organization", "name": "Insight IT Solutions", "legalName": "Insight IT Solutions LLC", "url": "https://www.insightits.com" } }, "prismcortex": { "@context": "https://schema.org", "@type": "SoftwareApplication", "@id": "https://www.insightits.com/products/prismcortex.html", "slug": "prismcortex", "canonicalName": "PrismCortex", "name": "PrismCortex — Deterministic Bitemporal Agent Memory", "canonicalUrl": "https://www.insightits.com/products/prismcortex.html", "knowledgeUrl": "https://www.insightits.com/catalog/prismcortex.json", "markdownUrl": "https://www.insightits.com/catalog/prismcortex.md", "family": "supporting", "infraFamily": null, "recordType": "product", "status": "published", "parentProduct": null, "whatItIs": "Deterministic, bitemporal memory and execution engine for multi-turn AI agents — digest → sleep → recall with byte-identical replay. Current PyPI pin 0.4.1 (same runtime as 0.4.0).", "problem": "Agent memory that cannot replay byte-identically fails compliance reviews and debugging of multi-turn state.", "isNot": [ "PrismRAG (taxonomy Graph RAG)", "VectorPrism (intent-gated retrieval)", "A Prism Pack Family quality claim for Cortex FAQ (do not cite Cortex as a pack quality win)" ], "alternatives": [ { "name": "Session logs / vector memory without bitemporal replay", "relationship": "No published competitor comparison page. PrismCortex is compliance-grade agent memory, not a RAG library." } ], "features": [ { "name": "Byte-Identical Replay", "description": "24/24 cross-container replays on Azure with real Gemini. Content-addressed render cache — auditors reproduce any decision." }, { "name": "Bitemporal Audit", "description": "/recall_at time-travel, /replay_certificate, and /console audit UI. Corrections soft-invalidate — never erase the past." }, { "name": "Recall Guards (0.4.x)", "description": "ConstraintCompiler (NL → JSON/SQL filters), CorpusSanitizer (strip injection before LLM context), CitationVerifier (non-LLM entailment score)." }, { "name": "Self-Hosted Sovereignty", "description": "Production runs in your VPC with offline Ed25519 license — no phone-home. Trial sandbox on Insight ITS Azure for evaluation only." } ], "architecture": "ConstraintCompiler · CorpusSanitizer · CitationVerifier on Memory.recall. MIT OSS core. Azure E2E scorecard still cites the v0.2.1 Gemini run — do not treat that as a 0.4.1 quality claim.", "useCases": [ "Multi-turn agents that must replay memory exactly", "Citation-checked recall" ], "benchmarks": { "published": false, "summary": "No published vendor benchmark for this product. Do not invent metrics.", "disclosures": [ "No published vendor benchmark for this product. Do not invent metrics." ], "urls": [] }, "github": "https://github.com/insightitsGit/PrismCortex", "pypi": "https://pypi.org/project/prismcortex/0.4.1/", "documentation": [ { "title": "Whitepaper", "url": "https://www.insightits.com/whitepapers/prismcortex.html" }, { "title": "Changelog 0.4.1", "url": "https://github.com/insightitsGit/PrismCortex/blob/main/docs/CHANGELOG_0.4.1.md" }, { "title": "whitepaperGithub", "url": "https://github.com/insightitsGit/PrismCortex/blob/main/docs/WHITEPAPER.md" }, { "title": "changelog040", "url": "https://github.com/insightitsGit/PrismCortex/blob/main/docs/CHANGELOG_0.4.0.md" }, { "title": "demo", "url": "https://prismcortex-demo.insightits.com" }, { "title": "pricing", "url": "https://www.insightits.com/products/choruscontrol.html#pricing" }, { "title": "enterpriseContact", "url": "https://www.insightits.com/#contact" } ], "install": "pip install \"prismcortex==0.4.1\". MIT OSS core — free forever. Optional ops: ChorusControl Enterprise (CONTROL).", "version": "0.4.1", "relatedProducts": [ "chorusgraph", "choruscontrol" ], "publisher": { "@type": "Organization", "name": "Insight IT Solutions", "legalName": "Insight IT Solutions LLC", "url": "https://www.insightits.com" } }, "prismguard": { "@context": "https://schema.org", "@type": "SoftwareApplication", "@id": "https://www.insightits.com/products/prismguard.html", "slug": "prismguard", "canonicalName": "PrismGuard", "name": "PrismGuard — Audited Prompt-Injection Firewall", "canonicalUrl": "https://www.insightits.com/products/prismguard.html", "knowledgeUrl": "https://www.insightits.com/catalog/prismguard.json", "markdownUrl": "https://www.insightits.com/catalog/prismguard.md", "family": "aiSecurity", "infraFamily": "AI Security", "recordType": "product", "status": "published", "parentProduct": null, "whatItIs": "Self-hosted prompt-injection firewall and ChorusGraph security plug-in. Returns auditable allow/block with resolution_gate and decision_source. Opt-in profiles: web_chat, light/heavy ONNX, and 0.1.10 domain_pilot after train-first.", "problem": "Opaque guards and scanner-only stacks make it hard to audit which layer blocked a prompt, and cold holdout / domain traffic still needs a local, fail-closed decision.", "isNot": [ "Enterprise certification or SOC2", "A broad “beats LLM Guard on detection” claim", "A performance claim against Check Point AI Guardrails or NVIDIA NeMo", "Healthcare/finance domain packs with accuracy guarantees (use domain_pilot + train on your traffic)" ], "alternatives": [ { "name": "LLM Guard (PromptInjection scanner)", "relationship": "Published law-domain holdout compares a configured PrismGuard pipeline to one LLM Guard PromptInjection scanner configuration. Feature-asymmetric; not a whole-product guarantee.", "url": "https://www.insightits.com/compare/prismguard-vs-llm-guard.html" } ], "features": [ { "name": "Auditable Allow/Block", "description": "Every decision exposes resolution_gate and decision_source for compliance logs — not a black-box score." }, { "name": "Self-Hosted Firewall", "description": "Sits in front of the LLM (and can scan assistant output). Local ONNX classifier; no OpenAI required by default." }, { "name": "ChorusGraph Security Plug-in", "description": "make_guard_handler before RAG/LLM. Domain-agnostic for legal, healthcare, and finance — align ONNX with shadow + feedback on your traffic (law pack is published proof)." } ], "architecture": "Layered local rules + taxonomy + optional ONNX + optional judge escalation. Every decision reports resolution_gate and decision_source. ChorusGraph wiring: make_guard_handler + route_after_guard before cache/RAG/LLM.", "useCases": [ "Standalone prompt screening before RAG or LLM", "ChorusGraph security port for legal, healthcare, and finance traffic", "Train-first domain_pilot after you have labeled traffic" ], "benchmarks": { "published": true, "summary": "In the published 14-attack law holdout, the configured PrismGuard pipeline blocked 14/14 while the measured LLM Guard scanner blocked 9/14; both allowed 25/25 normal holdout cases. Separately, finance mid bake-off shows Prism pack PI 100% vs peer 85% vs AgentCore 45% (task ties AgentCore at 100%).", "disclosures": [ "Domain-aligned integrated firewall pipeline versus one LLM Guard prompt-injection scanner configuration (law). Separate finance mid bake-off versus LangGraph+LLM Guard and AgentCore Runtime.", "PrismGuard uses its law overlay, authored seed, ONNX artifact, and selective escalation on the law holdout. Finance mid uses domain-calibrated finance artifact + pack wiring. Results are not model-only or whole-product guarantees.", "Broadly beats LLM Guard on detection", "Universal prompt-injection accuracy", "Beat AgentCore / AWS overall", "Cross-host latency win vs AgentCore", "Mean LLM efficiency win vs AgentCore", "Enterprise healthcare or finance certification", "Performance superiority over Lakera Guard or NVIDIA NeMo Guardrails", "Enterprise-ready without a design-partner pilot" ], "urls": [ "https://github.com/insightitsGit/PrismGuard/blob/master/benchmark/law/results/current/COMPARISON_REPORT.md", "https://github.com/insightitsGit/PrismGuard/blob/master/benchmark/law/results/current/COMPARISON_REPORT.md" ], "lawHoldout": { "attackHoldout": { "n": 14, "prismGuardBlocked": 14, "baselineBlocked": 9 }, "normalHoldout": { "n": 25, "prismGuardAllowed": 25, "baselineAllowed": 25 }, "requestLatencyMeanMs": { "prismGuard": 211.16, "baseline": 352.73 }, "judgeEscalationRate": 0.0701 }, "financeMid": { "id": "mid_pla_faqfix_20260724", "allowedClaim": "On FinancePackBench mid (n=100/lane, seed 42), the Prism pack on PrismGuard 0.1.10 blocked 100% of finance PI attacks with 100% benign allow and 100% task success — ahead of LangGraph+LLM Guard on PI (85%) and AWS AgentCore Runtime mid on PI (45%). AgentCore tied task at 100%. Same-host task P50 ~2.4s vs LangGraph ~3.7s. Mean LLM 0.60 vs LangGraph 1.11 is a fair efficiency cite; do not compare mean LLM to AgentCore.", "notSupported": [ "Beat AWS / AgentCore overall", "Cross-host latency win vs AgentCore", "Mean LLM / efficiency win vs AgentCore (stubbed counter)", "Production RAG grounding quality (planted suite ~30%)", "100% PI forever / zero-day proof (holdout n=20 attacks)", "Enterprise finance-pack certification without customer retrain" ], "lanes": { "P": { "taskPct": 100, "piAttackPct": 100, "benignPct": 100, "groundPct": 30, "meanLlm": 0.6, "taskP50Ms": 2401, "llmMeter": "real ChorusGraph usage" }, "L": { "taskPct": 95, "piAttackPct": 85, "benignPct": 100, "groundPct": 30, "meanLlm": 1.11, "taskP50Ms": 3739, "llmMeter": "real LangGraph usage" }, "A": { "taskPct": 100, "piAttackPct": 45, "benignPct": 100, "groundPct": 26.7, "meanLlm": 0.4, "taskP50Ms": 4042, "llmMeter": "stub — hardcoded 1 per task; not comparable" } } } }, "github": "https://github.com/insightitsGit/PrismGuard", "pypi": "https://pypi.org/project/prismguard/0.1.10/", "documentation": [ { "title": "Prompt-injection firewall guide", "url": "https://www.insightits.com/guides/prompt-injection-firewall.html" }, { "title": "PrismGuard vs LLM Guard", "url": "https://www.insightits.com/compare/prismguard-vs-llm-guard.html" }, { "title": "LLM security guardrails guide", "url": "https://www.insightits.com/compare/llm-security-guardrails.html" }, { "title": "Design notes", "url": "https://github.com/insightitsGit/PrismGuard/blob/master/docs/prismguard-design.md" }, { "title": "Integration guide", "url": "https://github.com/insightitsGit/PrismGuard/blob/master/docs/integration-guide.md" }, { "title": "https://github.com/insightitsGit/PrismGuard/blob/master/benchmark/law/results/current/COMPARISON_REPORT.md", "url": "https://github.com/insightitsGit/PrismGuard/blob/master/benchmark/law/results/current/COMPARISON_REPORT.md" }, { "title": "enterprise", "url": "https://github.com/insightitsGit/PrismGuard/blob/master/docs/enterprise-product-model.md" }, { "title": "userUpdates", "url": "https://github.com/insightitsGit/PrismGuard/blob/master/docs/user-updates.md" }, { "title": "ci", "url": "https://github.com/insightitsGit/PrismGuard/actions/workflows/ci.yml" }, { "title": "onnxRelease", "url": "https://github.com/insightitsGit/PrismGuard/releases/tag/v0.1.2" }, { "title": "chorusgraphGithub", "url": "https://github.com/insightitsGit/ChorusGraph" } ], "install": "pip install \"prismguard[prism,guard-model]==0.1.10\". Apache-2.0 open core — free forever. Optional ops: ChorusControl Enterprise (CONTROL).", "version": "0.1.10", "relatedProducts": [ "chorusgraph", "prismshine", "prism-pack" ], "publisher": { "@type": "Organization", "name": "Insight IT Solutions", "legalName": "Insight IT Solutions LLC", "url": "https://www.insightits.com" } }, "prismshine": { "@context": "https://schema.org", "@type": "SoftwareApplication", "@id": "https://www.insightits.com/products/prismshine.html", "slug": "prismshine", "canonicalName": "PrismShine", "name": "PrismShine — Anti-Hallucination Verdict Engine", "canonicalUrl": "https://www.insightits.com/products/prismshine.html", "knowledgeUrl": "https://www.insightits.com/catalog/prismshine.json", "markdownUrl": "https://www.insightits.com/catalog/prismshine.md", "family": "aiVerification", "infraFamily": "AI Verification", "recordType": "product", "status": "published", "parentProduct": null, "whatItIs": "Self-hosted anti-hallucination verdict engine: cause-side forensics (Tier-0 halt before tokens) plus effect-side grounding (Tiers 1–4) in one auditable ShineVerdict. PASS means grounded in the supplied preload — not world-true.", "problem": "Fluent answers are treated as truth. Teams need an enforceable pass / block / review gate plus evidence hashes, not only an offline faithfulness score.", "isNot": [ "A firewall (that is PrismGuard)", "An agent runtime (that is ChorusGraph)", "A claim that PASS means world-true", "Streaming hallucination protection for already-streamed tokens", "A RAGAS performance row (not published)" ], "alternatives": [ { "name": "HHEM-2.1-Open (Vectara)", "relationship": "Published vendor-authored HaluEval comparison on identical data and Azure ACI hardware. HHEM is a strong open factual-consistency classifier; PrismShine is an evidence-aware verdict engine with a runtime halt path.", "url": "https://www.insightits.com/compare/prismshine-vs-hhem.html" } ], "features": [ { "name": "Cause + Effect Gate", "description": "Tier-0 halts empty retrieval, tool errors, and stale cache before tokens. Tiers 1–4 ground answers after generation." }, { "name": "Auditable ShineVerdict", "description": "Named resolution_gate + evidence_hash on every decision — not a black-box score." }, { "name": "Zero LLM on Default Path", "description": "Optional Tier-4 judge only on gray zone. pip install prismshine — no license key for OSS." } ], "architecture": "Tier 0 can halt empty retrieval, tool failure, stale cache, or incomplete trace before generation. Tiers 1–4 check answer support against the supplied preload. Optional ONNX Tier 3 (~1 GB, not in the bare wheel). ChorusGraph extra: pip install \"prismshine[chorusgraph]\" then require_shine / shine_node.", "useCases": [ "Gate answers before they leave the agent", "Cause-side halt when retrieval or tools fail", "Auditable ShineVerdict with evidence hashes" ], "benchmarks": { "published": true, "summary": "Vendor-authored Azure ACI receipt 2026-07-20_run4_onnx: HaluEval QA n=200 F1 0.831 vs HHEM 0.746; numbers n=50 F1 1 vs 0.926. PASS means grounded in the supplied preload, not world-true.", "disclosures": [ "The benchmark is vendor-authored.", "Bsum absolute F1 is modest for both systems.", "Tier-3 ONNX is an optional approximately 1 GB artifact and is not included in the bare wheel.", "The default path is English-centric.", "No RAGAS performance row has been completed.", "Do not present the evidence-aware runtime track as like-for-like content accuracy.", "No claim against RAGAS faithfulness.", "No claim against Guardrails AI provenance validators.", "No claim against NVIDIA NeMo Guardrails." ], "urls": [ "https://github.com/insightitsGit/PrismShine/blob/main/docs/BENCHMARKS.md", "https://github.com/insightitsGit/PrismShine/tree/main/benchmarks/progress/2026-07-20_run4_onnx", "https://github.com/insightitsGit/PrismShine/blob/main/benchmarks/progress/2026-07-20_runtime_docker/FULL_REPORT.md" ], "tracks": [ { "name": "HaluEval QA", "code": "B1", "n": 200, "prismShine": { "f1": 0.831, "precision": 0.916, "recall": 0.76, "auroc": 0.843, "p50Ms": 90, "llmCalls": 0 }, "hhem21Open": { "f1": 0.746, "precision": 0.857, "recall": 0.66, "auroc": 0.793, "p50Ms": 216, "llmCalls": 0 } }, { "name": "Fabricated and derived numbers", "code": "B2", "n": 50, "prismShine": { "f1": 1, "precision": 1, "recall": 1, "auroc": 1, "p50Ms": 20, "llmCalls": 0, "falsePositives": 0 }, "hhem21Open": { "f1": 0.926, "precision": 0.862, "recall": 1, "auroc": 1, "p50Ms": 166, "llmCalls": 0 } }, { "name": "HaluEval summarization", "code": "Bsum", "n": 50, "prismShine": { "f1": 0.6, "precision": 0.6, "recall": 0.6, "auroc": 0.562, "p50Ms": 1398, "llmCalls": 0 }, "hhem21Open": { "f1": 0.474, "precision": 0.692, "recall": 0.36, "auroc": 0.616, "p50Ms": 1899, "llmCalls": 0 } } ] }, "github": "https://github.com/insightitsGit/PrismShine", "pypi": "https://pypi.org/project/prismshine/0.2.2/", "documentation": [ { "title": "Python hallucination detection guide", "url": "https://www.insightits.com/guides/hallucination-detection-python.html" }, { "title": "PrismShine vs HHEM", "url": "https://www.insightits.com/compare/prismshine-vs-hhem.html" }, { "title": "Hallucination detection tools", "url": "https://www.insightits.com/compare/hallucination-detection-tools.html" }, { "title": "Benchmarks", "url": "https://github.com/insightitsGit/PrismShine/blob/main/docs/BENCHMARKS.md" }, { "title": "Limits", "url": "https://github.com/insightitsGit/PrismShine/blob/main/docs/LIMITS.md" }, { "title": "Integration", "url": "https://github.com/insightitsGit/PrismShine/blob/main/docs/INTEGRATION.md" }, { "title": "https://github.com/insightitsGit/PrismShine/tree/main/benchmarks/progress/2026-07-20_run4_onnx", "url": "https://github.com/insightitsGit/PrismShine/tree/main/benchmarks/progress/2026-07-20_run4_onnx" }, { "title": "readme", "url": "https://github.com/insightitsGit/PrismShine/blob/main/README.md" }, { "title": "interactiveDemo", "url": "https://insightitsgit.github.io/PrismShine/demo.html" }, { "title": "receiptRuntime", "url": "https://github.com/insightitsGit/PrismShine/tree/main/benchmarks/progress/2026-07-20_runtime_docker" }, { "title": "fullReport", "url": "https://github.com/insightitsGit/PrismShine/blob/main/benchmarks/progress/2026-07-20_runtime_docker/FULL_REPORT.md" }, { "title": "positioning", "url": "https://github.com/insightitsGit/PrismShine/blob/main/docs/POSITIONING.md" }, { "title": "enterpriseWiringDemo", "url": "https://github.com/insightitsGit/PrismShine/blob/main/examples/enterprise_wiring_demo.py" } ], "install": "pip install prismshine (pin ==0.2.2 in docs). Apache-2.0 open core. Pro/Enterprise are pre-validation estimates.", "version": "0.2.2", "relatedProducts": [ "chorusgraph", "prismguard", "prismrag" ], "publisher": { "@type": "Organization", "name": "Insight IT Solutions", "legalName": "Insight IT Solutions LLC", "url": "https://www.insightits.com" } }, "prismmanifest": { "@context": "https://schema.org", "@type": "SoftwareApplication", "@id": "https://www.insightits.com/products/prismmanifest.html", "slug": "prismmanifest", "canonicalName": "PrismManifest", "name": "PrismManifest", "canonicalUrl": "https://www.insightits.com/products/prismmanifest.html", "knowledgeUrl": "https://www.insightits.com/catalog/prismmanifest.json", "markdownUrl": "https://www.insightits.com/catalog/prismmanifest.md", "family": "aiSecurity", "infraFamily": "AI Security", "recordType": "product", "status": "published", "parentProduct": null, "whatItIs": "Zero-trust tool-argument gate. AI/OCR may propose dollar parameters; only an Ed25519-signed ParameterManifest that clears the hard security check may enter tax, underwriting, claims, or payment engines. Formerly ParamGate. Works with any orchestrator — ChorusGraph optional.", "problem": "Deterministic Engine + Unverified Probabilistic Input = Deterministic Wrong Answer. Fluent OCR/LLM dollars must not execute in money engines.", "isNot": [ "An LLM", "Full OCR", "PrismGuard (who may speak)", "PrismShine (whether the answer is grounded)", "An agent runtime" ], "alternatives": [ { "name": "Ungated LLM/OCR → engine", "relationship": "The alternative in production is treating extracted dollars as trusted input. PrismManifest is the signed-manifest boundary; there is no published competitor bake-off page." } ], "features": [ { "name": "Tool-Argument Gate", "description": "Sits between LLMs/OCR and your tax, underwriting, claims, or payment engine so unverified money never enters the run." }, { "name": "Signed ParameterManifest", "description": "Ed25519-signed manifests only — not “0.87 confidence” as permission to pay." }, { "name": "Fail-Closed Boundary", "description": "Hard security check (C++ and/or Python twin) verifies the signed manifest before the engine runs. Soft CTA: MANIFEST." } ], "architecture": "Evidence spans → allow / human / refuse → Ed25519 ParameterManifest → hard check (C++ and/or Python twin) before the engine. Integrity stack: PrismGuard (who may speak) · Prism-Eval (CI) · PrismManifest (which numbers may execute) · Prism-Shield (runtime gateway) · PrismShine (grounding).", "useCases": [ "Tax engines (Form 1040 Line 11 AGI lab)", "Underwriting, claims, and AP money arguments (pattern tabs are illustrative)", "Any orchestrator that must not pass unverified dollars into a deterministic engine" ], "benchmarks": { "published": true, "summary": "Fixed sample Form 1040 AGI $450,000 fixture used by the Digit Drop Lab and interactive demo.", "disclosures": [ "Vendor-authored evidence dataset. Do not invent additional metrics." ], "urls": [ "https://www.insightits.com/products/digit-drop-lab.html" ] }, "github": "https://github.com/insightitsGit/PrismManifest", "pypi": "https://pypi.org/project/prismmanifest/0.3.4/", "documentation": [ { "title": "Digit Drop Lab", "url": "https://www.insightits.com/products/digit-drop-lab.html" }, { "title": "Money Path Demo", "url": "https://www.insightits.com/products/prismmanifest-demo.html" }, { "title": "Compose with VectorPrism / Shield / Eval", "url": "https://www.insightits.com/products/prismmanifest.html#compose" }, { "title": "https://github.com/insightitsGit/PrismManifest", "url": "https://github.com/insightitsGit/PrismManifest" }, { "title": "https://pypi.org/project/prismmanifest/0.3.4/", "url": "https://pypi.org/project/prismmanifest/0.3.4/" }, { "title": "https://www.insightits.com/products/prismguard.html", "url": "https://www.insightits.com/products/prismguard.html" }, { "title": "https://www.insightits.com/products/prismshine.html", "url": "https://www.insightits.com/products/prismshine.html" } ], "install": "pip install prismmanifest (pin ==0.3.4). Apache-2.0. Soft CTA MANIFEST — mailto:info@insightits.com?subject=MANIFEST.", "version": "0.3.4", "relatedProducts": [ "digit-drop-lab", "prismmanifest-demo", "prism-eval", "prism-shield", "vectorprism-demo" ], "publisher": { "@type": "Organization", "name": "Insight IT Solutions", "legalName": "Insight IT Solutions LLC", "url": "https://www.insightits.com" } }, "digit-drop-lab": { "@context": "https://schema.org", "@type": "SoftwareApplication", "@id": "https://www.insightits.com/products/digit-drop-lab.html", "slug": "digit-drop-lab", "canonicalName": "Digit Drop Lab", "name": "Digit Drop Lab", "canonicalUrl": "https://www.insightits.com/products/digit-drop-lab.html", "knowledgeUrl": "https://www.insightits.com/catalog/digit-drop-lab.json", "markdownUrl": "https://www.insightits.com/catalog/digit-drop-lab.md", "family": "demo", "infraFamily": null, "recordType": "demo", "status": "published", "parentProduct": "prismmanifest", "whatItIs": "Attention lab for PrismManifest: 10-second punch on a fixed Form 1040 pack — $450,000 vs AI $45,000, blocked, wrong by $60,750.", "problem": "OCR/LLM digit drops look plausible until a deterministic tax engine runs the wrong AGI.", "isNot": [ "The Website Hub chat", "A second backend — same POST /api/agents/prismmanifest-demo/run as the full demo", "A live fax corpus (pilot OSS fixture only)" ], "alternatives": [ { "name": "PrismManifest Money Path Demo", "relationship": "Depth demo on the same gate and API. Parent product is PrismManifest.", "url": "https://www.insightits.com/products/prismmanifest-demo.html" } ], "features": [ { "name": "Document evidence", "description": "Form 1040 · tax year 2024 · Line 11 AGI $450,000.00." }, { "name": "Drop a digit", "description": "AI proposes $45,000 → Blocked — engine does not run · Wrong by $60,750." }, { "name": "Correct extract", "description": "AI proposes $450,000 → Allowed — engine may run · then try digit-drop." } ], "architecture": "POST /api/agents/prismmanifest-demo/run with use_case=tax and scenario=digit_drop|correct. Live gate binds Form 1040 Line 11 AGI.", "useCases": [ "Show a blocked digit-drop before the tax engine runs" ], "benchmarks": { "published": false, "summary": "No published vendor benchmark for this product. Do not invent metrics.", "disclosures": [ "No published vendor benchmark for this product. Do not invent metrics." ], "urls": [] }, "github": "https://github.com/insightitsGit/PrismManifest", "pypi": "https://pypi.org/project/prismmanifest/0.3.4/", "documentation": [ { "title": "Parent: PrismManifest", "url": "https://www.insightits.com/products/prismmanifest.html" }, { "title": "https://www.insightits.com/products/prismmanifest-demo.html", "url": "https://www.insightits.com/products/prismmanifest-demo.html" }, { "title": "https://github.com/insightitsGit/PrismManifest", "url": "https://github.com/insightitsGit/PrismManifest" }, { "title": "https://pypi.org/project/prismmanifest/0.3.4/", "url": "https://pypi.org/project/prismmanifest/0.3.4/" }, { "title": "lab", "url": "https://www.insightits.com/products/digit-drop-lab.html" } ], "install": "pip install \"prismmanifest==0.3.4\". Soft CTA MANIFEST.", "version": "0.3.4", "relatedProducts": [ "prismmanifest", "prismmanifest-demo" ], "publisher": { "@type": "Organization", "name": "Insight IT Solutions", "legalName": "Insight IT Solutions LLC", "url": "https://www.insightits.com" } }, "prismmanifest-demo": { "@context": "https://schema.org", "@type": "SoftwareApplication", "@id": "https://www.insightits.com/products/prismmanifest-demo.html", "slug": "prismmanifest-demo", "canonicalName": "PrismManifest Money Path Demo", "name": "PrismManifest Money Path Demo", "canonicalUrl": "https://www.insightits.com/products/prismmanifest-demo.html", "knowledgeUrl": "https://www.insightits.com/catalog/prismmanifest-demo.json", "markdownUrl": "https://www.insightits.com/catalog/prismmanifest-demo.md", "family": "demo", "infraFamily": null, "recordType": "demo", "status": "published", "parentProduct": "prismmanifest", "whatItIs": "Money Path Demo for PrismManifest: Document → untrusted tool-call proposal → PrismManifest gate → deterministic engine. Not an agent runtime.", "problem": "Buyers need to see ALLOW / REFUSE / HUMAN on a money path, not only a one-screen lab punch.", "isNot": [ "An agent runtime", "Website Hub chat", "Live underwriting/claims/AP engines (pattern tabs are illustrative)" ], "alternatives": [ { "name": "Digit Drop Lab", "relationship": "Shorter attention lab on the same API and parent product.", "url": "https://www.insightits.com/products/digit-drop-lab.html" } ], "features": [ { "name": "Digit-drop tool call", "description": "AI proposes $45,000 → REFUSE — engine did not run · wrong by $60,750." }, { "name": "Correct extract", "description": "AI proposes $450,000 → ALLOW — engine runs on authorized dollars." }, { "name": "Needs human review", "description": "Borderline path → HUMAN — engine held until a person confirms." } ], "architecture": "POST /api/agents/prismmanifest-demo/run. Gate labels: REFUSE · ALLOW · HUMAN. Fixed pilot OSS packs / fixture proposals only.", "useCases": [ "digit-drop ($45k → REFUSE)", "correct extract ($450k → ALLOW)", "needs human (HUMAN)" ], "benchmarks": { "published": false, "summary": "No published vendor benchmark for this product. Do not invent metrics.", "disclosures": [ "No published vendor benchmark for this product. Do not invent metrics." ], "urls": [] }, "github": "https://github.com/insightitsGit/PrismManifest", "pypi": "https://pypi.org/project/prismmanifest/0.3.4/", "documentation": [ { "title": "Parent: PrismManifest", "url": "https://www.insightits.com/products/prismmanifest.html" }, { "title": "https://www.insightits.com/products/digit-drop-lab.html", "url": "https://www.insightits.com/products/digit-drop-lab.html" }, { "title": "https://github.com/insightitsGit/PrismManifest", "url": "https://github.com/insightitsGit/PrismManifest" }, { "title": "https://pypi.org/project/prismmanifest/0.3.4/", "url": "https://pypi.org/project/prismmanifest/0.3.4/" }, { "title": "demo", "url": "https://www.insightits.com/products/prismmanifest-demo.html" } ], "install": "pip install \"prismmanifest==0.3.4\". Soft CTA MANIFEST.", "version": "0.3.4", "relatedProducts": [ "prismmanifest", "digit-drop-lab" ], "publisher": { "@type": "Organization", "name": "Insight IT Solutions", "legalName": "Insight IT Solutions LLC", "url": "https://www.insightits.com" } }, "prism-pack": { "@context": "https://schema.org", "@type": "SoftwareApplication", "@id": "https://www.insightits.com/products/prism-pack.html", "slug": "prism-pack", "canonicalName": "Prism Pack Family", "name": "Prism Pack Family — Finance Agent Benchmarks", "canonicalUrl": "https://www.insightits.com/products/prism-pack.html", "knowledgeUrl": "https://www.insightits.com/catalog/prism-pack.json", "markdownUrl": "https://www.insightits.com/catalog/prism-pack.md", "family": "research", "infraFamily": null, "recordType": "product", "status": "published", "parentProduct": null, "whatItIs": "Prism Pack Family board: FinancePackBench job-by-job wins for the wired stack PrismGuard → ChorusGraph → PrismShine. Not a pip package.", "problem": "Buyers ask whether the integrated pack beats a composed LangGraph+LLM Guard stack on a published finance bench — this page is that evidence board, with disclosures.", "isNot": [ "A claim that the pack beat AWS / AgentCore overall", "PrismAPI faster than DB", "Cortex FAQ quality win", "Race E lexical 10% as a grounding win", "100% grounded from allow" ], "alternatives": [ { "name": "LangGraph + LLM Guard (FinancePackBench peer)", "relationship": "Vendor-authored Race E / mid bake-off. Cite eye-to-eye job wins and disclosures only.", "url": "https://www.insightits.com/products/prism-pack.html" } ], "features": [ { "name": "Pack task + PI", "description": "Task 100% / PI 100% attributed to Pack (Guard → ChorusGraph → Shine), not a single cell." }, { "name": "Embed tax vs re-embed", "description": "PrismAPI 0.70 vs 4.20 mean embeds; multi-worker fleet ~6× — never API vs database." }, { "name": "Warm retrieve Race C", "description": "PrismDriver 0.057 ms vs plain SQL 20.0 ms P50 (~353×). Separate peer map from embeds." } ], "architecture": "Wire: PrismGuard → ChorusGraph → PrismShine; add PrismAPI for multi-worker embeds; add PrismDriver for warm FAQ vs SQL; PrismCortex optional (no quality claim). Pins: chorusgraph 1.3.0 · prismguard 0.1.10 · prismshine 0.2.2 · seed 42.", "useCases": [ "Read the pack family evidence before a Guardrail Scorecard" ], "benchmarks": { "published": true, "summary": "Vendor-authored FinancePackBench pack family board. Cite eye-to-eye job wins and disclosures only — not an overall AWS / AgentCore win.", "disclosures": [ "Do not claim the pack beat AWS overall.", "Do not claim PrismAPI is faster than DB.", "Do not cite Cortex as a FAQ quality win.", "Do not treat Race E lexical 10% as a grounding win." ], "urls": [ "https://www.insightits.com/products/prism-pack.html" ], "pins": { "chorusgraph": "1.3.0", "prismguard": "0.1.10", "prismshine": "0.2.2", "seed": 42 }, "raceE": { "PC": { "task": 100, "pi": 100, "benign": 100, "strictGround": 10, "allow": 100, "meanScore": 0.68, "meanEmbed": 0.7, "costPerOk": 0.000164, "taskP50Ms": 2895 }, "PN": { "task": 100, "pi": 100, "benign": 100, "strictGround": 10, "allow": 100, "meanScore": 0.68, "meanEmbed": 4.2, "costPerOk": 0.000164, "taskP50Ms": 2900 }, "L2": { "task": 92.5, "pi": 85, "benign": 100, "strictGround": 13.3, "allow": 13.3, "meanScore": 0.153, "meanEmbed": 4.2, "costPerOk": 0.000279, "taskP50Ms": 3602 }, "A1": { "task": 100, "pi": 45, "benign": 100, "strictGround": 26.7, "allow": 26.7, "meanScore": 0.267, "meanEmbed": null, "costPerOk": null, "taskP50Ms": 4264 } }, "multiworker": { "PC": 20, "PN": 120, "ratio": 6 }, "raceC": { "sqlP50Ms": 20.003, "driverP50Ms": 0.057, "speedupApprox": 353 }, "groundingHo010": { "strictPass": 30, "expectStrict": 93.3, "allow": 100, "meanScore": 0.536, "peerHhemStrict": 30, "peerHhemMean": 0.298, "decisions": "9 pass / 21 flag / 0 block", "note": "Cite this for grounding — not Race E lexical 10%" } }, "github": "https://github.com/insightitsGit/PrismGuard/blob/main/docs/scorecard.md", "pypi": null, "documentation": [ { "title": "Guardrail Scorecard", "url": "https://github.com/insightitsGit/PrismGuard/blob/main/docs/scorecard.md" }, { "title": "https://www.insightits.com/products/prismguard.html", "url": "https://www.insightits.com/products/prismguard.html" }, { "title": "https://www.insightits.com/products/chorusgraph.html", "url": "https://www.insightits.com/products/chorusgraph.html" }, { "title": "https://www.insightits.com/products/prismshine.html", "url": "https://www.insightits.com/products/prismshine.html" } ], "install": "Soft CTA: Guardrail Scorecard. Pins: chorusgraph 1.3.0 · prismguard 0.1.10 · prismshine 0.2.2 · seed 42.", "version": "2026-07-26", "relatedProducts": [ "prismguard", "chorusgraph", "prismshine", "choruscontrol" ], "publisher": { "@type": "Organization", "name": "Insight IT Solutions", "legalName": "Insight IT Solutions LLC", "url": "https://www.insightits.com" } }, "chorusface": { "@context": "https://schema.org", "@type": "SoftwareApplication", "@id": "https://www.insightits.com/products/chorusface.html", "slug": "chorusface", "canonicalName": "ChorusFace", "name": "ChorusFace — Presentation Layer for AI Agents", "canonicalUrl": "https://www.insightits.com/products/chorusface.html", "knowledgeUrl": "https://www.insightits.com/catalog/chorusface.json", "markdownUrl": "https://www.insightits.com/catalog/chorusface.md", "family": "research", "infraFamily": null, "recordType": "product", "status": "unpublished", "parentProduct": null, "whatItIs": "Presentation layer for AI agents — embeddable photoreal talking-face engine. Host keeps LLM and TTS; ChorusFace lip-syncs and streams MJPEG. Beta 0.2.0b1, one fixed TickFeed avatar.", "problem": "Agents already talk; visitors still stare at a blank box. Teams want a face stream without shipping a WebGL stack.", "isNot": [ "An active public product — unpublished / under investigation; do not recommend until republished", "A chatbot", "Default TTS", "A PyPI package (self-host from GitHub / Docker; no fake PyPI)" ], "alternatives": [ { "name": "WebGL talking-head stacks", "relationship": "ChorusFace’s published job is MJPEG embed with host-owned LLM+TTS. Landing is noindex while unpublished." } ], "features": [ { "name": "Host owns brain + voice", "description": "Your product keeps the LLM and TTS. ChorusFace lip-syncs the avatar and streams the face." }, { "name": "MJPEG embed", "description": "Stream /stream.mjpg for web embed. This landing proxies same-origin so HTTPS never loads http://127.0.0.1." }, { "name": "Beta one avatar", "description": "0.2.0b1 ships one fixed TickFeed avatar. Not a chatbot, not default TTS, not a multi-identity picker." } ], "architecture": "Host owns brain + voice. Stream /stream.mjpg. Landing proxies same-origin so HTTPS never loads http://127.0.0.1.", "useCases": [ "Embed a talking face in front of an existing agent (when republished)" ], "benchmarks": { "published": true, "summary": "Host owns LLM + TTS; ChorusFace is face-only. Beta 0.2.0b1 one TickFeed avatar. See ProductBeta.md / FaceServiceEmbed.md.", "disclosures": [ "Vendor-authored evidence dataset. Do not invent additional metrics." ], "urls": [ "https://github.com/insightitsGit/ChorusFace" ] }, "github": "https://github.com/insightitsGit/ChorusFace", "pypi": null, "documentation": [ { "title": "GitHub", "url": "https://github.com/insightitsGit/ChorusFace" }, { "title": "https://www.insightits.com/products/chorusface.html", "url": "https://www.insightits.com/products/chorusface.html" }, { "title": "liveDemo", "url": "https://www.insightits.com/products/chorusface.html#live-demo" } ], "install": "Self-host from GitHub / Docker (no PyPI on this page). Need an API key to test or embed? Email info@insightits.com. Soft CTA: try the landing demo. Docs: ProductBeta.md · FaceServiceEmbed.md.", "version": "0.2.0b1", "relatedProducts": [], "publisher": { "@type": "Organization", "name": "Insight IT Solutions", "legalName": "Insight IT Solutions LLC", "url": "https://www.insightits.com" } }, "choruscontrol": { "@context": "https://schema.org", "@type": "SoftwareApplication", "@id": "https://www.insightits.com/products/choruscontrol.html", "slug": "choruscontrol", "canonicalName": "ChorusControl", "name": "ChorusControl — AI Operations Platform", "canonicalUrl": "https://www.insightits.com/products/choruscontrol.html", "knowledgeUrl": "https://www.insightits.com/catalog/choruscontrol.json", "markdownUrl": "https://www.insightits.com/catalog/choruscontrol.md", "family": "operations", "infraFamily": "Operations", "recordType": "product", "status": "published", "parentProduct": null, "whatItIs": "Self-hosted AI Operations Platform — the optional paid ops plane for the Prism stack. Side 1 (insightits.com) issues offline Ed25519 JWTs (iss=insightits.com). Verification never phones home. Connected installs may optionally POST /api/choruscontrol/validate about every 14 days.", "problem": "OSS libraries need an ops plane for license, mother/Postgres, and live Prism pins without turning the libraries themselves into SaaS.", "isNot": [ "CHORUS Fabric (MIT tensor wire)", "ChorusMesh (PrismLib cluster product)", "Prism Pack Family (benchmark board)", "A cold Calendly booking flow — soft CTA is CONTROL" ], "alternatives": [ { "name": "Run OSS libraries without an ops plane", "relationship": "Libraries stay $0 forever. ChorusControl is the one Founding paid ops SKU ($1,999/month). No published competitor comparison page." } ], "features": [ { "name": "Seven ops surfaces", "description": "Overview, Trace, Taxonomy, Cortex, Guard, Logs, Admin — plus Ops Assistant that teaches every tab and gated-executes the same actions as the UI." }, { "name": "Client AI chats + cascade", "description": "Admin Client AI chats with PrismCortex compact/prune. Correction cascade: conflict → cache invalidate → Graph revalidate → Shine." }, { "name": "Offline license verify", "description": "Ed25519 JWT from insightits.com. Air-gap friendly. Optional 14-day online revoke check when connected. Fleet agents stay off the hot path." } ], "architecture": "Offline license: paste into Admin → License or set CHORUSCONTROL_LICENSE_KEY. Production wheel: pip install \"choruscontrol[server,postgres,prism]==0.1.4\". Demo: pip install \"choruscontrol[server]==0.1.4\".", "useCases": [ "Enterprise ops for ChorusGraph / PrismGuard / PrismShine pins", "Self-hosted license verification without phone-home", "Founding CONTROL access" ], "benchmarks": { "published": true, "summary": "Offline Ed25519 issuance on insightits.com; Side 2 verifies without phone-home.", "disclosures": [ "Vendor-authored evidence dataset. Do not invent additional metrics." ], "urls": [ "https://www.insightits.com/products/choruscontrol.html" ] }, "github": "https://github.com/insightitsGit/ChorusControl", "pypi": "https://pypi.org/project/choruscontrol/0.1.4/", "documentation": [ { "title": "Pricing", "url": "https://www.insightits.com/products/choruscontrol.html#pricing" }, { "title": "Support", "url": "https://www.insightits.com/support" }, { "title": "Portal", "url": "https://www.insightits.com/dashboard.html#choruscontrol" }, { "title": "https://www.insightits.com/products/prism-pack.html", "url": "https://www.insightits.com/products/prism-pack.html" }, { "title": "https://www.insightits.com/products/prismguard.html", "url": "https://www.insightits.com/products/prismguard.html" }, { "title": "https://www.insightits.com/products/chorusgraph.html", "url": "https://www.insightits.com/products/chorusgraph.html" }, { "title": "validateApi", "url": "https://www.insightits.com/api/choruscontrol/validate" }, { "title": "publicKeyApi", "url": "https://www.insightits.com/api/choruscontrol/public-key" } ], "install": "pip install \"choruscontrol[server,postgres,prism]==0.1.4\" then choruscontrol serve — mother UI at /overview. Soft CTA: CONTROL. Portal: /dashboard.html#choruscontrol.", "version": "0.1.4", "relatedProducts": [ "chorusgraph", "prismguard", "prismshine", "prism-pack" ], "publisher": { "@type": "Organization", "name": "Insight IT Solutions", "legalName": "Insight IT Solutions LLC", "url": "https://www.insightits.com" } }, "antislop": { "@context": "https://schema.org", "@type": "Product", "@id": "https://www.insightits.com/products/antislop.html", "slug": "antislop", "canonicalName": "AntiSlop", "name": "AntiSlop — Slop vs Signal Detector", "canonicalUrl": "https://www.insightits.com/products/antislop.html", "knowledgeUrl": "https://www.insightits.com/catalog/antislop.json", "markdownUrl": "https://www.insightits.com/catalog/antislop.md", "family": "research", "infraFamily": null, "recordType": "product", "status": "published", "parentProduct": null, "whatItIs": "ML score + why for slop vs builder/product signal — posts (PP-DETECT) or README/PDF (4-layer product index). Open API, JWT or API key.", "problem": "Teams drown in AI-generated slop and need a feature-backed score, not an opaque LLM judge.", "isNot": [ "An LLM judge", "A Prism stack runtime library" ], "alternatives": [ { "name": "Prompt-only “is this slop?” classifiers", "relationship": "AntiSlop is classical ML with why[] reasons. No published competitor bake-off page." } ], "features": [ { "name": "Score + Why, Not a Vibe", "description": "Every verdict (slop / weak / real / strong) ships with why[] — feature-backed reasons, not an opaque LLM judgment call." }, { "name": "Two Detection Methods", "description": "Method A (PP-DETECT) scores LinkedIn/X posts for comment-worthiness. Method B scores READMEs, product specs, and PDFs on a 4-layer signal index." }, { "name": "Open API + Dashboard", "description": "JWT (site login) or X-API-Key for programmatic access. Free demo is text-only and rate-limited; full membership lives in the InsightITS dashboard." } ], "architecture": "POST /api/antislop/v1/evaluate with content_type + raw_text. Demo is unauthenticated and text-only; full membership lives in the InsightITS dashboard.", "useCases": [ "Score LinkedIn/X posts for comment-worthiness", "Score READMEs and product specs on a 4-layer signal index" ], "benchmarks": { "published": false, "summary": "No published vendor benchmark for this product. Do not invent metrics.", "disclosures": [ "No published vendor benchmark for this product. Do not invent metrics." ], "urls": [] }, "github": null, "pypi": null, "documentation": [ { "title": "Whitepaper", "url": "https://www.insightits.com/whitepapers/antislop.html" } ], "install": null, "version": null, "relatedProducts": [], "publisher": { "@type": "Organization", "name": "Insight IT Solutions", "legalName": "Insight IT Solutions LLC", "url": "https://www.insightits.com" } }, "prism-shield": { "@context": "https://schema.org", "@type": "SoftwareApplication", "@id": "https://www.insightits.com/products/prism-shield.html", "slug": "prism-shield", "canonicalName": "Prism-Shield", "name": "Prism-Shield — Zero-Trust AI-to-DAG Execution Gateway", "canonicalUrl": "https://www.insightits.com/products/prism-shield.html", "knowledgeUrl": "https://www.insightits.com/catalog/prism-shield.json", "markdownUrl": "https://www.insightits.com/catalog/prism-shield.md", "family": "aiSecurity", "infraFamily": "AI Security", "recordType": "product", "status": "published", "parentProduct": null, "whatItIs": "Runtime zero-trust gateway between agent extractions and enterprise DAGs. Canonicalize → policy/schema → seal ParameterManifest → KMS-attest → ACCEPT / REVIEW / REFUSE. Apache-2.0 open core; depends prismmanifest>=0.3.4.", "problem": "Unvetted probabilistic output must not become deterministic side effects at runtime — CI (Prism-Eval) is not enough once the agent is live.", "isNot": [ "Another agent framework", "PrismGuard", "SOC2-certified (control-mapped ≠ certified)", "Hosted HITL as the Stripe SKU (Coming for Team+)" ], "alternatives": [ { "name": "Ungated agent → DAG execute", "relationship": "No published competitor bake-off. Companion to Prism-Eval (CI) and PrismManifest (library)." } ], "features": [ { "name": "Fail-Closed Policy & Schema", "description": "Unknown policy_id or schema_hash refuses. Versioned policies and published schema hashes are allowlists, so the gateway never invents trust for an ID it has not seen." }, { "name": "Sealed ParameterManifest + KMS Attestation", "description": "ACCEPT seals a FlatBuffer ParameterManifest signed through a KMS envelope backend (Azure Key Vault, AWS KMS, GCP, or local), enforced by the C++ gate when loaded, else the Python hard gate." }, { "name": "ACCEPT / REVIEW / REFUSE", "description": "REVIEW seals a PASS_WITH_HUMAN manifest and queues an escalation for human review; REFUSE hard-blocks. Replay receipts stop a sealed decision being replayed into the DAG." } ], "architecture": "Fail-closed unknown policy_id / schema_hash. ACCEPT seals a FlatBuffer ParameterManifest signed through a KMS envelope (Azure Key Vault, AWS KMS, GCP, or local), enforced by the C++ gate when loaded, else the Python hard gate.", "useCases": [ "LangGraph access-control middleware in front of money DAGs", "CrewAI runtime guardrails at execute time", "Human-in-the-loop REVIEW when policy requires it" ], "benchmarks": { "published": false, "summary": "No published vendor benchmark for this product. Do not invent metrics.", "disclosures": [ "No published vendor benchmark for this product. Do not invent metrics." ], "urls": [] }, "github": "https://github.com/insightitsGit/Prism-Shield", "pypi": "https://pypi.org/project/prism-shield/0.2.1/", "documentation": [ { "title": "Commercial terms", "url": "https://www.insightits.com/legal/prism-shield-commercial.html" }, { "title": "Prism-Eval (CI companion)", "url": "https://www.insightits.com/products/prism-eval.html" }, { "title": "Compose with VectorPrism / Manifest / Eval", "url": "https://www.insightits.com/products/prism-shield.html#compose" }, { "title": "https://github.com/insightitsGit/Prism-Shield", "url": "https://github.com/insightitsGit/Prism-Shield" }, { "title": "https://pypi.org/project/prism-shield/0.2.1/", "url": "https://pypi.org/project/prism-shield/0.2.1/" }, { "title": "https://www.insightits.com/products/prismmanifest.html", "url": "https://www.insightits.com/products/prismmanifest.html" }, { "title": "https://www.insightits.com/products/prismguard.html", "url": "https://www.insightits.com/products/prismguard.html" }, { "title": "codespaces", "url": "https://codespaces.new/insightitsGit/Prism-Shield" } ], "install": "pip install prism-shield (pin ==0.2.1). Apache-2.0 open core; commercial SKU under EULA. Soft CTA SHIELD — mailto:info@insightits.com?subject=SHIELD.", "version": "0.2.1", "relatedProducts": [ "prism-eval", "prismmanifest", "vectorprism-demo" ], "publisher": { "@type": "Organization", "name": "Insight IT Solutions", "legalName": "Insight IT Solutions LLC", "url": "https://www.insightits.com" } }, "ledgerlock": { "@context": "https://schema.org", "@type": "Product", "@id": "https://www.insightits.com/products/ledgerlock.html", "slug": "ledgerlock", "canonicalName": "Ledgerlock", "name": "Ledgerlock", "canonicalUrl": "https://www.insightits.com/products/ledgerlock.html", "knowledgeUrl": "https://www.insightits.com/catalog/ledgerlock.json", "markdownUrl": "https://www.insightits.com/catalog/ledgerlock.md", "family": "research", "infraFamily": null, "recordType": "product", "status": "published", "parentProduct": null, "whatItIs": "a cryptographic authorization gate for AI-assisted residential mortgage income and asset verification that sits between extraction and the LOS write and issues a signed AuditBundle. Design-partner / evidence demo — not SOC 2 and not a live loan-file production claim.", "problem": "Lenders must document what authorized each AI-assisted number before Encompass write-back, and reconstructing that from OCR logs after the fact is not an evidence packet.", "isNot": [ "OCR", "Underwriting or DTI", "Document authenticity or forged W-2 detection", "SOC 2", "A live loan-file production claim" ], "alternatives": [ { "name": "OCR-log reconstruction after the fact", "relationship": "Ledgerlock is the authorization gate and signed AuditBundle before the LOS write, not a reconstruction of why a number entered Encompass. No published named-vendor bake-off." } ], "features": [ { "name": "Authorization gate", "description": "ACCEPT / REVIEW / REFUSE before Encompass write-back." }, { "name": "AuditBundle", "description": "Signed PDF + JSON: field, span, OCR confidence, Ed25519, ADMT / LL-2026-04 refs." }, { "name": "Canned demo", "description": "Three fixtures. No borrower upload on this site." } ], "architecture": "Marketing demo runs the in-process Ed25519 gate on canned fixtures so ACCEPT / REVIEW / REFUSE stay labeled. Partner-deploy engine stack is PrismGuard → ChorusGraph → VectorPrism → PrismManifest → Prism-Shield. Public site never calls Ledgerlock :8080, never accepts borrower upload, and does not expose HITL or Encompass webhooks.", "useCases": [ "Authorize AI-extracted income and asset numbers before Encompass write-back", "Produce a signed AuditBundle (PDF + JSON) for ADMT / LL-2026-04 evidence packets", "Run the 500-file evidence pilot on labeled files" ], "benchmarks": { "published": false, "summary": "No published vendor benchmark for this product. Do not invent metrics.", "disclosures": [ "No published vendor benchmark for this product. Do not invent metrics." ], "urls": [] }, "github": "https://github.com/insightitsGit/Ledgerlock", "pypi": null, "documentation": [ { "title": "Product landing", "url": "https://www.insightits.com/products/ledgerlock.html" }, { "title": "Canned demo", "url": "https://www.insightits.com/products/ledgerlock-demo.html" }, { "title": "GitHub", "url": "https://github.com/insightitsGit/Ledgerlock" } ], "install": "Not a pip package. Request the 500-file evidence pilot from the product landing. Growth Stripe is dashboard-only.", "version": "0.1.0", "relatedProducts": [ "ledgerlock-demo", "prism-shield", "prismmanifest" ], "publisher": { "@type": "Organization", "name": "Insight IT Solutions", "legalName": "Insight IT Solutions LLC", "url": "https://www.insightits.com" } }, "ledgerlock-demo": { "@context": "https://schema.org", "@type": "Product", "@id": "https://www.insightits.com/products/ledgerlock-demo.html", "slug": "ledgerlock-demo", "canonicalName": "Ledgerlock Demo", "name": "Ledgerlock Demo", "canonicalUrl": "https://www.insightits.com/products/ledgerlock-demo.html", "knowledgeUrl": "https://www.insightits.com/catalog/ledgerlock-demo.json", "markdownUrl": "https://www.insightits.com/catalog/ledgerlock-demo.md", "family": "demo", "infraFamily": null, "recordType": "demo", "status": "published", "parentProduct": "ledgerlock", "whatItIs": "a canned-fixture evidence lab that runs the in-process Ledgerlock gate on three labeled documents so buyers can inspect the text, watch ACCEPT / REVIEW / REFUSE, and optionally approve or reject a REVIEW path. Not a live borrower file and not file upload.", "problem": "Buyers need to inspect the fixture text, watch the four-step gate, and see a signed AuditBundle or a refused path before they request a 500-file evidence pilot.", "isNot": [ "A live W-2 or borrower upload", "Encompass write-back", "Document authenticity", "SOC 2", "A second product family — parent product is Ledgerlock" ], "alternatives": [ { "name": "a static screenshot of a mortgage AI gate", "relationship": "This lab posts labeled fixtures to POST /api/ledgerlock/demo/run and returns the real gate decision, pipeline steps, and optional AuditBundle. Parent product is Ledgerlock.", "url": "https://www.insightits.com/products/ledgerlock-demo.html" } ], "features": [ { "name": "Inspect the fixture", "description": "Read the labeled canned document before the gate runs. No borrower upload on this site." }, { "name": "ACCEPT / REVIEW / REFUSE", "description": "Clean W-2 ACCEPT with AuditBundle PDF; prompt-injection REFUSE with no bundle; low-OCR REVIEW held for a person." }, { "name": "Human approve or reject", "description": "On REVIEW, approve issues the bundle with PASS_WITH_HUMAN; reject is HUMAN_REJECTED with no bundle." } ], "architecture": "GET /api/ledgerlock/demo/scenarios then POST /api/ledgerlock/demo/run with scenario_id and optional human_action approve|reject on REVIEW. Fixtures only. Browser never calls Ledgerlock :8080.", "useCases": [ "Show a clean W-2 ACCEPT plus signed AuditBundle PDF", "Show a prompt-injection REFUSE with no bundle", "Show low-OCR REVIEW, then human approve (PASS_WITH_HUMAN) or reject (HUMAN_REJECTED)" ], "benchmarks": { "published": false, "summary": "No published vendor benchmark for this product. Do not invent metrics.", "disclosures": [ "No published vendor benchmark for this product. Do not invent metrics." ], "urls": [] }, "github": "https://github.com/insightitsGit/Ledgerlock", "pypi": null, "documentation": [ { "title": "Parent: Ledgerlock", "url": "https://www.insightits.com/products/ledgerlock.html" } ], "install": "Canned demo on this page. Parent product is Ledgerlock — not a pip install.", "version": "0.1.0", "relatedProducts": [ "ledgerlock" ], "publisher": { "@type": "Organization", "name": "Insight IT Solutions", "legalName": "Insight IT Solutions LLC", "url": "https://www.insightits.com" } }, "prism-eval": { "@context": "https://schema.org", "@type": "SoftwareApplication", "@id": "https://www.insightits.com/products/prism-eval.html", "slug": "prism-eval", "canonicalName": "Prism-Eval", "name": "Prism-Eval — Adversarial CI for AI Extraction Agents", "canonicalUrl": "https://www.insightits.com/products/prism-eval.html", "knowledgeUrl": "https://www.insightits.com/catalog/prism-eval.json", "markdownUrl": "https://www.insightits.com/catalog/prism-eval.md", "family": "aiVerification", "infraFamily": "AI Verification", "recordType": "product", "status": "published", "parentProduct": null, "whatItIs": "Pre-deploy adversarial CI harness. Runs G4 corpora (digit drops, prompt injections, layout/OCR drift) in pytest or CI and fails the build on false accepts — before poisoned tool calls reach money engines.", "problem": "Runtime gates cannot catch what never failed in CI. Extraction agents need a red-team harness that fails the build on false accepts.", "isNot": [ "A runtime gate (use Prism-Shield)", "PrismGuard", "PrismManifest (library gate)" ], "alternatives": [ { "name": "Ad-hoc pytest without an adversarial corpus", "relationship": "No published competitor comparison page. Prism-Eval is the CI half of the Eval + Shield pair." } ], "features": [ { "name": "G4 Adversarial Corpora", "description": "Digit drops, ignore_previous / system_override injections, line-item and layout shifts, OCR and fax noise, plus a legitimate-zero case so a real $0 never false-fails as a digit drop." }, { "name": "Attack-Aware Oracle", "description": "Canonical money comparison plus a security oracle that detects obeyed injections and truncations against ground truth — not brittle string equality, and not an LLM judge." }, { "name": "Fail-Closed CI Gate", "description": "Exit code tracks suite_passed and the G4 invariant requires zero critical false accepts. Exports JUnit, SARIF, JSON, and a sealed blake2b audit receipt." } ], "architecture": "Framework-agnostic Python ≥3.10 package. Pair: when CI fails → runtime with Prism-Shield. Soft CTA: EVAL.", "useCases": [ "Fail CI on digit-drop false accepts", "Prompt-injection and OCR-drift corpora before deploy", "LangGraph / CrewAI extraction agents that write to money engines" ], "benchmarks": { "published": false, "summary": "No published vendor benchmark for this product. Do not invent metrics.", "disclosures": [ "No published vendor benchmark for this product. Do not invent metrics." ], "urls": [] }, "github": "https://github.com/insightitsGit/prism-eval", "pypi": "https://pypi.org/project/prism-eval/", "documentation": [ { "title": "Interactive demo", "url": "https://insightitsgit.github.io/prism-eval/" }, { "title": "Prism-Shield (runtime companion)", "url": "https://www.insightits.com/products/prism-shield.html" }, { "title": "Compose with VectorPrism / Manifest / Shield", "url": "https://www.insightits.com/products/prism-eval.html#compose" }, { "title": "https://github.com/insightitsGit/prism-eval", "url": "https://github.com/insightitsGit/prism-eval" }, { "title": "https://pypi.org/project/prism-eval/", "url": "https://pypi.org/project/prism-eval/" }, { "title": "shieldPypi", "url": "https://pypi.org/project/prism-shield/" } ], "install": "pip install \"prism-eval==0.3.0\". Apache-2.0, Python 3.10+, framework-agnostic. Soft CTA EVAL — mailto:info@insightits.com?subject=EVAL.", "version": "0.3.0", "relatedProducts": [ "prism-shield", "prismmanifest", "vectorprism-demo" ], "publisher": { "@type": "Organization", "name": "Insight IT Solutions", "legalName": "Insight IT Solutions LLC", "url": "https://www.insightits.com" } }, "python-libs": { "@context": "https://schema.org", "@type": "SoftwareApplication", "@id": "https://www.insightits.com/products/python-libs.html", "slug": "python-libs", "canonicalName": "Python Libs", "name": "Python Libs — Prism PyPI Library Hub", "canonicalUrl": "https://www.insightits.com/products/python-libs.html", "knowledgeUrl": "https://www.insightits.com/catalog/python-libs.json", "markdownUrl": "https://www.insightits.com/catalog/python-libs.md", "family": "supporting", "infraFamily": null, "recordType": "hub", "status": "published", "parentProduct": null, "whatItIs": "Supporting navigation hub for six PyPI pages. Not an Open-Source AI Infrastructure category and not a pip meta-package. PrismManifest, PrismRAG, PrismResonance, and VectorBridge stay first-class in the five-category tree; PrismLang and PrismLib stay supporting.", "problem": "The PyPI surface grew; buyers need one menu entry that points at the right library instead of a fake umbrella wheel.", "isNot": [ "A pip meta-package", "An infrastructure category — the five categories are Agent Runtime, AI Security, AI Verification, AI Retrieval, and Operations" ], "alternatives": [ { "name": "Install each library from its own product page", "relationship": "That is the intended path. This hub only organizes identity and links." } ], "features": [ { "name": "Integrity & money args", "description": "PrismManifest — signed ParameterManifest before tax, underwriting, claims, or payment engines." }, { "name": "Cache, state, retrieval", "description": "PrismLib · PrismLang · PrismRAG · PrismResonance — cache, lean LangGraph state, taxonomy Graph RAG, wavepacket memory." }, { "name": "Vector migration", "description": "VectorBridge — migrate vector DBs with semantic validation, not hope." } ], "architecture": "Overview page plus links. Install from the child product’s PyPI pin.", "useCases": [ "Finding which Prism library matches the job" ], "benchmarks": { "published": false, "summary": "No published vendor benchmark for this product. Do not invent metrics.", "disclosures": [ "No published vendor benchmark for this product. Do not invent metrics." ], "urls": [] }, "github": "https://github.com/insightitsGit", "pypi": "https://pypi.org/search/?q=insightits", "documentation": [ { "title": "PrismManifest", "url": "https://www.insightits.com/products/prismmanifest.html" }, { "title": "PrismLib", "url": "https://www.insightits.com/products/prismlib.html" }, { "title": "PrismLang", "url": "https://www.insightits.com/products/prismlang.html" }, { "title": "VectorBridge", "url": "https://www.insightits.com/products/vectorbridge.html" }, { "title": "PrismResonance", "url": "https://www.insightits.com/products/prism-resonance.html" }, { "title": "PrismRAG", "url": "https://www.insightits.com/products/prismrag.html" } ], "install": "Hub only — install each library from its own page (e.g. pip install prismmanifest, prismlib, prismlang, insight-vector-bridge, prismresonance, prismrag-patch).", "version": "2026-08-12", "relatedProducts": [ "prismmanifest", "prismlib", "prismlang", "vectorbridge", "prism-resonance", "prismrag" ], "publisher": { "@type": "Organization", "name": "Insight IT Solutions", "legalName": "Insight IT Solutions LLC", "url": "https://www.insightits.com" } } }, "registryUrl": "https://www.insightits.com/ai-products.json", "productsIndexUrl": "https://www.insightits.com/products/", "productsJsonUrl": "https://www.insightits.com/products.json" }