Building Flightdeck Tools
Extracting the useful parts of a private agent rig
Why I split a large, machine-shaped agent system into small tools with explicit contracts, synthetic examples, and new histories.
Notes on AI.
Ideas and decisions from the things I’m building.
Building Flightdeck Tools
State that survives the terminal
Four small tools for durable messages, lifecycle history, generation-safe progress, and decisions whose original wording remains intact.
Building Helmsman
Score once, experiment many times
A synthetic identity record traced through the real score store: which change needs new model work, which only reruns deterministic math, and why replaying stored scores does not recover the past.
Building Helmsman
Where the model stops and the code takes over
The contract between model output and deterministic code in Helmsman, traced with synthetic replies: what a model may emit, what the validator rejects, and what happens when the handoff fails.
AI environments
An RL environment is a systems problem
A task, a sandbox, and a score need to agree. The engineering around that contract is where things get interesting.
Building the Skill Registry
A shared memory for agents across repositories
Inside the skill registry: discovery, provenance, verification, and sharing knowledge without copying it into every repo.