{"appId":"copilot-app","version":6,"selectedAngularVersion":20,"item":{"id":"copilot-lesson-012","conceptKey":"copilot-topic-04-copilot-architecture","subjectId":"copilot-topic-04-copilot-architecture","title":"Copilot Architecture","summary":"Understand how a request moves from the editor through context collection, prompt construction, model and tool selection, and response generation.","baseContent":"<h2>Copilot Architecture</h2><p>Understand how a request moves from the editor through context collection, prompt construction, model and tool selection, and response generation.</p><h3>Learning objectives</h3><ul><li>Explain Copilot Architecture in clear language.</li><li>Recognize when it helps and when it does not.</li><li>Apply it in a small, reviewable development workflow.</li><li>Validate AI-generated output before accepting it.</li></ul><h3>Practical developer workflow</h3><ol><li>State the desired outcome and acceptance criteria.</li><li>Provide only the relevant repository context.</li><li>Ask Copilot for a plan or a small change.</li><li>Review every suggestion and generated file.</li><li>Run tests, linting, builds, and security checks appropriate to the change.</li></ol><h3>Easy example</h3><p>Begin with a narrow request that explains one concept or proposes one small change.</p><pre><code>Explain this concept in plain language, give one realistic developer example, and list two limitations or risks.</code></pre><h3>Easy-example verification</h3><ul><li>Check that the response addresses the exact request.</li><li>Compare technical claims with the repository or trusted documentation.</li><li>Do not apply a suggestion until you understand it.</li></ul><h3>Advanced example</h3><p>Use Copilot Architecture in a production task with explicit scope, constraints, review gates, and recovery requirements.</p><pre><code>Plan and implement a production use of Copilot Architecture.\nLimit changes to the named files and preserve public behavior.\nInclude normal, edge, and failure tests.\nRun the relevant lint, test, build, and security checks.\nReport assumptions, evidence, tradeoffs, and rollback steps.</code></pre><h3>Real-world example</h3><p>A development team uses Copilot Architecture while working on a customer-facing application. The team supplies repository rules and acceptance criteria, keeps changes small, reviews the generated diff, and verifies behavior with automated checks and manual inspection.</p><h3>Common mistakes</h3><ul><li>Using a vague request without constraints or success criteria.</li><li>Providing too much irrelevant context or omitting the files that define behavior.</li><li>Accepting generated code, commands, or claims without verification.</li><li>Including secrets, personal data, or restricted source material in prompts.</li><li>Allowing a large change to proceed without checkpoints and rollback.</li></ul><h3>Production perspective</h3><p>Verify the response against source code or trusted documentation; AI output is a proposal, not evidence.</p><h3>Review checklist</h3><ul><li>Is the intended outcome explicit?</li><li>Is the supplied context relevant and safe?</li><li>Does the result follow repository architecture and standards?</li><li>Were edge cases, security, and accessibility considered?</li><li>Is there test evidence and a safe recovery path?</li></ul>","detailId":"copilot-lesson-012-detail","versions":[],"isActive":true,"detailIsActive":true,"lessonVersions":[],"selectedVersion":20,"content":"","updatedAt":"2026-08-01T10:13:48.230Z","details":[{"id":"copilot-lesson-012","conceptKey":"copilot-topic-04-copilot-architecture","subjectId":"copilot-topic-04-copilot-architecture","title":"Copilot Architecture","summary":"Understand how a request moves from the editor through context collection, prompt construction, model and tool selection, and response generation.","baseContent":"<h2>Copilot Architecture</h2><p>Understand how a request moves from the editor through context collection, prompt construction, model and tool selection, and response generation.</p><h3>Learning objectives</h3><ul><li>Explain Copilot Architecture in clear language.</li><li>Recognize when it helps and when it does not.</li><li>Apply it in a small, reviewable development workflow.</li><li>Validate AI-generated output before accepting it.</li></ul><h3>Practical developer workflow</h3><ol><li>State the desired outcome and acceptance criteria.</li><li>Provide only the relevant repository context.</li><li>Ask Copilot for a plan or a small change.</li><li>Review every suggestion and generated file.</li><li>Run tests, linting, builds, and security checks appropriate to the change.</li></ol><h3>Easy example</h3><p>Begin with a narrow request that explains one concept or proposes one small change.</p><pre><code>Explain this concept in plain language, give one realistic developer example, and list two limitations or risks.</code></pre><h3>Easy-example verification</h3><ul><li>Check that the response addresses the exact request.</li><li>Compare technical claims with the repository or trusted documentation.</li><li>Do not apply a suggestion until you understand it.</li></ul><h3>Advanced example</h3><p>Use Copilot Architecture in a production task with explicit scope, constraints, review gates, and recovery requirements.</p><pre><code>Plan and implement a production use of Copilot Architecture.\nLimit changes to the named files and preserve public behavior.\nInclude normal, edge, and failure tests.\nRun the relevant lint, test, build, and security checks.\nReport assumptions, evidence, tradeoffs, and rollback steps.</code></pre><h3>Real-world example</h3><p>A development team uses Copilot Architecture while working on a customer-facing application. The team supplies repository rules and acceptance criteria, keeps changes small, reviews the generated diff, and verifies behavior with automated checks and manual inspection.</p><h3>Common mistakes</h3><ul><li>Using a vague request without constraints or success criteria.</li><li>Providing too much irrelevant context or omitting the files that define behavior.</li><li>Accepting generated code, commands, or claims without verification.</li><li>Including secrets, personal data, or restricted source material in prompts.</li><li>Allowing a large change to proceed without checkpoints and rollback.</li></ul><h3>Production perspective</h3><p>Verify the response against source code or trusted documentation; AI output is a proposal, not evidence.</p><h3>Review checklist</h3><ul><li>Is the intended outcome explicit?</li><li>Is the supplied context relevant and safe?</li><li>Does the result follow repository architecture and standards?</li><li>Were edge cases, security, and accessibility considered?</li><li>Is there test evidence and a safe recovery path?</li></ul>","detailId":"copilot-lesson-012-detail","versions":[],"isActive":true,"detailIsActive":true,"lessonVersions":[],"selectedVersion":20,"content":"","updatedAt":"2026-08-01T10:13:48.230Z"}]}}