{"slug":"copilot-test-plan","title":"Ask Copilot for a test plan, then run it yourself","summary":"Copilot lists cases for a change you describe. You run them. The plan is not permission to skip the ones that are slow.","agent":"GitHub Copilot","agentSlug":"github-copilot","category":"Coding","categorySlug":"coding","roles":["Software engineer"],"roleSlugs":["software-engineer"],"industries":["Software"],"industrySlugs":["software"],"jobs":["code-review","shipping-code"],"topic":"Dev & Coding","topicSlug":"dev-and-coding","score":15,"difficulty":"easy","estCost":"GitHub Copilot subscription.","costTier":"low","timeSaved":"Remembering edge cases, not executing them.","prompt":"Here is the change. Write a test plan I can execute.\n\nInclude: the happy path, two boundary cases, one failure case, and one case that should stay unchanged.\n\nFor each case give the setup, the action, and the observable result. Prefer a command or a user step that exists today. Mark cases that need a staging account as manual.\n\nDo not claim you ran them. I will run them.\n\nCHANGE:","steps":[{"title":"Describe the change in behavior, not file names only","detail":"Copilot can see the IDE. Still write the user-visible change so the plan is about behavior."},{"title":"Generate the plan in Copilot chat","detail":"Use the IDE chat documented in GitHub's Copilot getting-started materials."},{"title":"Run the cases and check them off","detail":"Paste failures back if you want a fix. The plan itself is not the fix."},{"title":"Put the plan in the PR","detail":"A reviewer can see what you actually did versus what was listed."}],"sourceUrl":"https://docs.github.com/en/copilot/get-started/what-is-github-copilot","sourceNote":"Official documentation URL, checked when this seed was written. The prompt and steps are an original AI Playbook Gems playbook, not a quotation of a customer story, and have not been re-run.","date":"2026-10-02","verified":false,"status":"unverified","sponsorUrl":"","metrics":[{"label":"Hands-on time","value":"Execution time remains yours"},{"label":"You still approve","value":"Which cases you skip"},{"label":"Cost bucket","value":"Low"}],"faq":[{"question":"Has this GitHub Copilot playbook been re-run for the catalog?","answer":"No. Status is unverified. Paste the prompt, keep the version that worked, and do not treat the time or cost lines as measurements."},{"question":"Why not let a cloud agent run the plan?","answer":"GitHub documents cloud and IDE agents. This playbook stops at a plan you run, because an unrun plan is easier to audit than a claimed green check."}],"url":"https://aiplaybookgems.com/usecases/copilot-test-plan","jsonUrl":"https://aiplaybookgems.com/api/usecases/copilot-test-plan"}