Skip to content
GitHub Copilot Train-the-Trainer
Overview

Session M3-02: Copilot cloud agent

Slides in new tab Download PDF

Module: Agentic Workflows

Difficulty: Advanced

Prerequisites: Sessions M1-01 to M1-03, M2-01 to M2-04

Duration: 3 hours (1 hour trainer content + 2 hours lab)

Overview

Take one synthetic issue from its contract to a human review decision. Prepare the repository and start a Copilot cloud agent session. Then inspect the proposed change and run the required tests before deciding whether to approve, request changes, or pause.

Keep the issue fixed throughout the work: reject blank or whitespace-only task titles while preserving valid task creation.

Learning outcomes

  • Write an issue with testable acceptance criteria, allowed files, and non-goals.
  • Review repository instructions and Copilot setup steps before assignment.
  • Monitor an agent session without expanding the issue or its repository access.
  • Compare a proposed change with the issue and allowed file scope.
  • Run and record focused tests.
  • Name the human reviewer and record their decision.

Deliverables

Submit:

  1. the fixed issue contract;
  2. the proposed change;
  3. focused test output;
  4. the review outcome.

Access policy

Learners need Copilot cloud agent access to the training repository, synthetic data, and a human reviewer.

If anything is missing, do not assign the issue. Stop the lab.

Session materials

Resource Purpose
trainer-content/README.md Minute-mapped teaching and demo plan
slides.md Trainer-facing teaching deck
lab/README.md Two-hour issue-to-review lab
lab/starter/ Issue, setup, sample project, and review guide
lab/solution/ Completed issue journey and runnable solution

Current product references

Product notes were checked against official GitHub documentation on October 5, 2026. Trainers must recheck access and policy before delivery: