Step 9 of 9 · planned
Ship it honestly
Make all of this routine: account for noise, block regressions, and know what runs before a prompt change goes out.
What you'll build
A pre-ship check with trials and a regression gate, run through the bt CLI in CI — plus the demo run of show.
Braintrust features
What you'll be able to show
“This is what runs before anyone touches the prompt.”
🐾 Not written yet. Each step is written as the course is actually worked through, so it describes real scores, real regressions and real false alarms rather than a script guessed in advance.