§ 001 / TOPIC
AI Agents
128 posts on ai agents, guides and lab notes from real runs on hardware we own. New posts land here automatically. Start anywhere, or grab the copy-paste prompts that ship with them.
- 5 min read
Gemini first for four jobs. One run finished two tasks.
I moved four recurring jobs to Gemini, then checked what actually finished. One recorded run proved progress. The broken queue sweep stayed broken.
- 6 min read
143 pull requests. Zero dollars.
In the week of 2026-08-31 the fleet merged 143 product pull requests. Stripe still read zero. Throughput is the tell, not the win.
- 6 min read
A kill rule that expires is not a kill rule
I wrote a kill rule for a paid-path test. Zero orders landed. The card expired into an archive and the dashboard still said ACTIVE.
- 5 min read
Agent Memory: Test the Answer After a Correction
Our agent-memory replay checks words in a file. I show what that proves, what it misses, and how to test whether an expert correction changes an answer.
- 6 min read
My agent wrote 126 empty pages and every gate passed
One commit wrote 130 knowledge pages. 126 were the same four sentences with the title swapped. Schema checks, link checks and orphan checks all passed.
- 5 min read
3 Tests Before a GGUF Quant Runs Your Coding Agent
A GGUF file fitting in VRAM does not prove it can run your coding agent. Use this local acceptance test for tools, patches, and repeat runs.
- 6 min read
Prime Agent Review: 95.5% on ARC-AGI-3. I Didn't Install It.
Prime Agent beat the 95.4% human-expert baseline on ARC-AGI-3 at launch, MIT-licensed. Why its /refine self-editing loop and no-sandbox kernel kept it off my fleet, and the one component I copied.
- 6 min read
Build Local LLM Eval Data From Real Failures
I show how I turn failed local coding runs into replayable eval rows with the prompt, model output, tests, route, and verifier result intact.
- 6 min read
LM Studio Bionic: The Local Open-Model Agent, Explained (2026)
Is LM Studio Bionic worth a look? It runs code projects on a local folder with GLM 5.2 and Kimi K2.7 Code, local voice via Voxtral, and is free with local models. What shipped, and what it changes.
- 6 min read
Your local LLM benchmark is probably lying to you
A local model pass rate can be true and useless at the same time. Here are the three ways local LLM benchmarks mislead you, drawn from real rows on my RTX 5090.
- 6 min read
Your Agent's Audit Trail Cannot Be Retrofitted
Agent logs show activity. They do not prove the outcome an agent claimed. Here is the verification layer I added after an agent reported two false dones.
- 6 min read
My Agents Have to Prove What They Did
I extracted the claims ledger that runs my agent operation into showwork. Falsifiable claims, deterministic checks, and an exit gate that refuses a false done.
The AI agent build notes
Real costs, real tools, no fluff. One evidence-backed note on Friday when there is something worth sharing.
Get the requested artifact now, then at most one evidence-backed Local AI Lab Note on Friday when there is something worth sharing. One-click unsubscribe. No sponsored placements. Privacy.