> For the complete documentation index, see [llms.txt](https://dyns.ntd.asia/power-dynamics/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://dyns.ntd.asia/power-dynamics/artificial-intelligence/study-copilot-studio/testing-and-capstone.md).

# 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