הרצאה מתקדמת: איך לשלוט בתהליכי AI

תקציר מקורי באנגליתA batch of 968 sample support traces exposes order lookup failures and broken escalation calls. Doug Guthrie uses those cases to connect Braintrust observability with the work of improving an agent. The workshop starts with a Python support agent built on the OpenAI Agents SDK, adds tracing, establishes an offline evaluation baseline, and publishes custom scorers. Online automations grade incoming traces, while Topics groups patterns in tasks, sentiment, and workflow issues. A custom facet targets failures that the default issue classification misses. Guthrie configures conversation grouping and sampling, imports the sample traces, and inspects the resulting labels and topic maps to find cases worth investigating. The next step is to turn those findings into changes. The embedded Loop assi