Writing
-
Audition the voice before you commission the work
A persona config for AI-generated writing is write-only: you describe a tone in prose and find out whether it worked after paying for the full piece. The fix is a preview agent so cheap and so constrained that sampling the voice becomes free.
-
Giving my agent a map of the codebase (drawn partly from its own footsteps)
Every agent session used to start with grep archaeology: rebuilding a mental model of the repo from scratch. Now each project carries a code map fusing static structure, git history, and a signal most tools ignore - which files the agent itself touched together in real sessions.
-
Documentation my agents can trust (and why it made me faster too)
Both of my previous posts were written in an afternoon, weeks after the work, without reconstructing anything. That is not memory. It is a documentation standard designed for agents: immutable decisions, plans with stable task ids, and one authoritative home per question.
-
My agent system dreams at night, and that is where its memory comes from
Durable memory does not come from an agent deciding mid-task what to remember. It comes from a nightly consolidation cycle: cluster the day's events, reflect with an LLM, score, gate hard, and promote very little. The gates are the whole design.
-
How I measure whether my agent's memory works
My coding agent could not recall a fact I had explicitly saved. The root cause was invisible, the obvious fix was wrong, and the measurement that proved the right one nearly lied to me twice.
-
Running parallel agent sessions without them stepping on each other
I run several coding-agent sessions at once, often on the same repo. Two failure modes make that miserable: corrupted shared state and duplicated work. One was solved by construction, the other by presence - and the fix deliberately contains no locks.