Skip to slide
218 / 221

CH 18 · Reference Architecture and a Design Checklist · 13/16

Read as one page

Observability & quality

  • Do you capture per-turn traces (context, model calls, tokens, tool calls, outcome)? (Ch 15)
  • Is there an eval set run on every prompt/tool/model change, with deterministic checks where possible? (Ch 15)
  • Do you watch production signals (feedback, accept/reject, failures) and feed cases back into evals? (Ch 15)

Finished this idea?

Your learning progress stays in this browser.