Collection
Make AI work improve from failures instead of accumulating rituals
Use eval-driven development, durable guardrails, clean experiments and reusable research or automation artifacts so everyday AI workflows learn from repeated work rather than restarting from chat every time.
8 elements · Explore in any order.
2 heuristics · 2 principles · 4 protocols
8 elements
Turn a verified AI failure into a regression test
A painful failure should pay rent the second time.
Read the idea HeuristicTurn repeated human corrections into guardrails with wider reach
If humans repeat the same comment every week, the feedback is trapped at the wrong layer.
Read the idea PrincipleOwn the task eval before shopping for a better model
Without your own test, a model leaderboard is somebody else's job description.
Read the idea ProtocolGrade the final state and the agent trajectory separately
The destination can be correct while the route is unacceptable.
Read the idea ProtocolRun AI evals from a clean starting state
A hidden file from yesterday can make today's agent look brilliant.
Read the idea PrincipleUse versioned artifacts as the meeting place for humans and agents
Shared chat is a poor substitute for shared state.
Read the idea HeuristicTurn stable repeated tool sequences into scripts
Do not pay a language model to rediscover a deterministic macro on every run.
Read the idea ProtocolBuild a reusable research wiki when the topic keeps coming back
Deep research is expensive if every question starts by forgetting the last one.
Read the idea