Build an AI knowledge fabric for your organisation
summary
Claims an agent‑optimized semantic layer stops LLM hallucination and latency by constraining models with three concrete pillars: engineering defaults, industry context, and institutional pointers. Implementation uses plain Markdown in a Git repo (LLM Wiki / Open Knowledge Format), event‑driven updates via pull requests, text diagrams (Marmel), and links to API specs; a demo with three Markdown files proves a working proof‑of‑concept. Measure success by token cost reduction, developer velocity, and post‑generation trust gains.
AI-written summary · about
chapters (10)
- 0:00The challenge of AI context
- 3:11The concept of knowledge fabric
- 5:10Failures of traditional KM
- 7:47Defining the knowledge fabric
- 8:41The three-layer framework
- 16:18Semantic distribution
- 17:02Building the knowledge fabric
- 19:01Rules for implementation
- 23:42Measuring effectiveness
- 26:16Demonstration and conclusion
related talks
29mBuilding Trust in AI Agents
36mLLMs and AI agents demystified
47mBuilding and Testing AI-Agent Powered LLM Applications: A Live Demonstration
32mTruth-seeker: Using LLM agents to build and verify knowledge bases
41mBringing stories to life with AI, data streaming and generative agents
30mBuilding Robust, Secure LLM and Agentic AI Workflows
46mDemystifying AI Agents
14mFull-Stack AI Engineering from AI-Native Coding to Knowledge, Models, Infrastructure & OSS