Ctrlk
For the complete documentation index, see llms.txt. This page is also available as Markdown.

Testing & Capstone

Group 8: proving an agent works with a number instead of a feeling, then building one system that pulls every prior group together.

Group 8 of the Copilot Studio course: systematic evaluation of what's already built, then a single capstone build that pulls conversational, autonomous, and multi-agent mechanisms from every prior group into one Northwind Outfitters agent.

  • 8.1 — Evaluating Agents: Test Sets and Evaluation Methods — test sets, the seven evaluation methods, and reading results

  • 8.2 — Conversational Evaluation, Automation & the GitHub Copilot Harness — multi-turn test sets, REST API/connector automation for CI/CD, and the newer harness's own single-method evaluation preview

  • 8.3 — Capstone: The Full Northwind Outfitters Agent — conversational + autonomous + multi-agent, end to end

PreviousALM Automation: Pipelines and CI/CD
NextEvaluating Agents: Test Sets and Evaluation Methods