Pattern · Process

Feedback flywheel

Eugene Yan

Capturing explicit and implicit signals from users to feed evals, error analysis, fine-tuning data, and reward models.

Signals worth capturing in agentic-coding deployments

Closing the loop. These signals don't just measure — they become the next eval set and the next fine-tune corpus. Without instrumentation up front, the data is gone.

Yan, "Collect User Feedback"

Build the instrumentation as part of the pilot, not after. Cheap version (week 1): structured logs of every agent decision + outcome, tagged with run-id, written to a single table.