FunnyEnough — engineering notes
Notes on building with AI — the patterns that held up, and the ones that bit me.
-
Your agent says the tests passed. It didn’t run them.
Coding agents say “tests pass” after only reading the assertions. A short rules-file contract forces real output, or an honest “NOT RUN”, before anything ships.
-
The First Plausible Answer Is Already a Design Decision
AI is brilliant at removing friction. Some friction is where judgement forms. A field guide, from William James to the Zhuangzi, to what is worth keeping human.
-
I Fixed My Agent’s Guardrails. The Fixes Had Holes Too.
An audit found the holes in my agent’s guardrails. Fixing them was harder: every patch was another claim I had to prove against the running system.
-
I Audited My Most-Governed Project and Found a Deny-List With Holes
Every project rule is either a gate that fails the build or a sentence that hopes you comply. One question separates them, and I learned it the hard way.
-
Receipts for Prompts: Hashing the Bytes an Agent Reads
A hash-verified copy box still handed back a curly quote where a code fence should be. The wptexturize bug behind it, and the byte-receipt system that stops it.
-
The abstention gate: when an AI agent should say nothing
A scheduled agent on stale data won’t crash; it briefs you confidently off it. Here’s a deterministic freshness gate that decides when to stay quiet, and the tests that keep it honest.
-
AI Agent Security Starts at the Context Boundary
Stop treating tool output as plain text. A practical boundary review for MCP servers, traces, red-team tests, and runtime AI-agent supply-chain risk.
-
Lint your agent’s handoff file before it lies
Every long agent session ends with a handoff note, written by an amnesiac for an amnesiac. Mine was wrong before I saved it. Here’s how to make it checkable.
-
Verifying AI Coding Agents: Receipts Beat Vibes
AI coding agents ship plausible work fast. Here’s how to make them prove which app, state, platform and screen they actually tested — receipts, not vibes.
-
I almost shipped a bug report I never tested
A token-saver was blamed for an agent committing a stale file. I wrote it up, then ran the test I’d skipped. The tool was innocent. The real cause was worse.