ConeheadAI · leftover lesson
SNK3-234 · Curriculum How-to
The audit trail habit
L2–L5 · Capable–Builder (bootstrap — system rebalances) · ~4m
Look for this insight
Logging what an automation did (when, what, result) is the difference between a controlled system and a mystery.
Lesson hook
When someone asks 'why did the customer get that email?', 'the AI did it' is not an answer. A log is: timestamp, input, action, result. If your automation writes no trail, you don't own it — you're just standing near it.
Do this now
For any automation or recurring AI task you use, check: does a log exist showing what ran, when, on what? You're done when you've either found the log or written the one-line request to add one.
Completion check: log_found_or_request_written
Conehead-only — no external link
Staff review Sign in