Blog
Blog
Engineering notes on AI agents, automation, and the infrastructure behind them.
September 15, 2026 · 1 minKnowledge Graph Evaluation: Scoring 12 Real Decisions
Knowledge graph evaluation usually measures retrieval. Scoring 12 real decisions against the answer you would have reached anyway shows more.
August 28, 2026 · 3 minState, Not Steps: Why Your Workflow Automation Has No Memory
Memory, approvals, sandboxing and rollback separate a production system from a demo. Three of them are configuration in your workflow tool. The fourth is architecture.
August 25, 2026 · 5 minAgent Memory Approval Gates: What Never Needs a Human
A human gate on agent memory writes is now consensus. The volume reaching it is the unsolved half. Three routing rules that keep the queue readable.
August 11, 2026 · 4 minZerolang: Vercel's Agent-First Language and Your Review Cost
Vercel's Zerolang lets agents patch a compiler graph instead of text. The buying question is not adoption. It is what your code review costs today.
July 28, 2026 · 4 minAI Data Sovereignty in Banking: Draw the Compliance Boundary First
Why AI projects in banking stall at the compliance boundary, not the model, and how boundary-first architecture ships under DORA and the EU AI Act.
July 22, 2026 · 4 minWho Signs Off on Your AI Agent's Code? Two Questions Before It Ships
When an AI agent ships code, who is accountable? A sign-off means little if the AI could rewrite the evidence behind it. Two questions to ask first.
July 7, 2026 · 3 minEdgeHome Harness: Why MiniCPM5-1B Never Touches Your Devices
MiniCPM5-1B runs a smart home because a Rust harness treats it as untrusted input. What EdgeHome Harness owns, why frontier agents need the same.
July 6, 2026 · 4 minWhen Document Parsing Automation Is Worth It (and When to Buy Instead of Building on n8n)
Document parsing on n8n is commoditized. The value is the decision before the build: throughput threshold, build vs buy a parser, and self-hosting for compliance.
July 2, 2026 · 4 minSandboxing an AI Coding Agent: The Harness Owns the Boundaries
How I wrap a coding agent in a sandbox so each risky capability, from model routing to patch approval, sits behind its own boundary.
July 2, 2026 · 4 minPeer-to-Peer Local AI: Edge Agents, No Cloud in the Path
P2P local AI: models arrive like torrents, inference can delegate to peers, no cloud in the path. Tested on a 4-core VPS with no GPU.
June 30, 2026 · 5 minTwo Kinds of Agent Memory: OKF Bundles vs. Codebase Knowledge Graphs
Knowledge graph agent memory comes in two kinds: one half is derivable from your code, one half only people can author. Mixing them wastes both.
June 25, 2026 · 3 minYour AI Agent Makes Four Bad Decisions a Smarter Model Won't Fix
AI agents fail decisions for the same four reasons people do. The WRAP framework, encoded as a system-prompt gate, fixes what a bigger model can't.
Your agents answer from whatever the retriever finds, and too often that is last quarter's truth. I build the context layer they answer and act from: a temporal knowledge graph that keeps every fact with its source and the time it held, reads with each person's own permissions, and writes nothing without a person's approval. On your own tenant, billed by the hour, step by step.