Articles for people who
ship the stack
Rewrites on React, Node.js, TypeScript and AI. A translated body is shown when it exists. If it does not, you see the English text and a note that says so.
Tagged: knowledge-management
Agentic Finetuning: Training a Knowledge Wiki Instead of Model Weights
Run the ML training loop on a wiki of learnings mined from company documents: benchmarks built from raw data, secret questions, and a certificate with honest limits.
9 min readBeyond One Retrieval Path: Canonical Knowledge, RAG and Live Queries for Enterprise Agents
Why one retrieval pipeline cannot serve every kind of enterprise knowledge, and how a router can split canonical concepts, RAG discovery and safe live queries.
12 min readProject Cedar: Testing Whether AI Agents Can Maintain a Company Markdown Wiki
A fictional consulting engagement tests an LLM Wiki pattern for company knowledge: what an agent built, why it scored 50 percent, and what access control still needs.
11 min readGoogle OKF, Hermes and Gbrain: Folders as Knowledge Graphs
How Google's Open Knowledge Format differs from MCP and RAG, and how Hermes plus Gbrain turn plain Markdown folders into a knowledge graph agents can reuse.
5 min readOKF + RAG: A Hybrid Architecture for Reliable AI Agents
Google's Open Knowledge Format gives AI agents exact, Git-versioned answers, and RAG covers the messy archives. How a small router combines both in one agent.
6 min readPractical notes: OKF Is More Than Markdown: How I Think About a Portable
Operable walkthrough of Practical notes: OKF Is More Than Markdown: How I Think About a Portable: contracts, checks, and drop-in code slots for teams shipping this pattern.
10 min read
About these articles
Request a 24h estimate
Need the same stack in a production operator layer? Send the brief — estimate within 24 hours.