Tu recorrido

Nivel 1
Course map: plans, AI Credits, setting up Visual Studio 2026 and VS Code, the ENGAGE repository~1 h · A · Foundations
Nivel 2 · ~1,5 h · A · Foundations · según el diseño del autor, después de «Course map: plans, AI Credits, setting up Visual Studio 2026 and VS Code, the ENGAGE repository»dentro de un nivel, el orden lo eliges tú
How Copilot works: prompt building, context, proxy filtering, post-processing, suggestion lifecycle
Responsible use: risks, hallucinated APIs, insecure patterns, output ownership, verification discipline
Nivel 3
Context engineering and prompting: #-references, participants, zero/few-shot, chat history, fresh sessions~1,5 h · A · Foundations · según el diseño del autor, después de «How Copilot works: prompt building, context, proxy filtering, post-processing, suggestion lifecycle»
Governance: organisation policies, content exclusion and its gaps, public code filter, audit log, REST API for seats, AI Credit budgets~2 h · E · Governance & exam · según el diseño del autor, después de «Responsible use: risks, hallucinated APIs, insecure patterns, output ownership, verification discipline»
Nivel 4
Visual Studio 2026 basics: inline suggestions, Next Edit Suggestions, Chat, Copilot Actions, commit messages~1 h · B · Visual Studio 2026 · según el diseño del autor, después de «Context engineering and prompting: #-references, participants, zero/few-shot, chat history, fresh sessions»
VS Code: Chat, Plan, agent sessions, the Agents window, model choice and its price~1,5 h · C · VS Code & team customisation · según el diseño del autor, después de «Context engineering and prompting: #-references, participants, zero/few-shot, chat history, fresh sessions»
Aldervane case: the February confidentiality incident — root causes across the whole course~1,5 h · E · Governance & exam · según el diseño del autor, después de «Governance: organisation policies, content exclusion and its gaps, public code filter, audit log, REST API for seats, AI Credit budgets»
Copilot CLI essentials: install, interactive sessions, plan and autopilot, permissions, key commands, scripts and files~1 h · E · Governance & exam · según el diseño del autor, después de «Context engineering and prompting: #-references, participants, zero/few-shot, chat history, fresh sessions»
Measuring impact and rolling Copilot out to a team: metrics, adoption, avoiding vendor numbers~1 h · Optional · Beyond the exam · según el diseño del autor, después de «Governance: organisation policies, content exclusion and its gaps, public code filter, audit log, REST API for seats, AI Credit budgets»
Nivel 5
Agent mode in Visual Studio: tools, approvals, the build/test loop, Plan agent → Implement plan~1,5 h · B · Visual Studio 2026 · según el diseño del autor, después de «Visual Studio 2026 basics: inline suggestions, Next Edit Suggestions, Chat, Copilot Actions, commit messages»
Team rules: copilot-instructions.md, *.instructions.md with applyTo, prompt files, organisation instructions — and what VS and the CLI see~1,5 h · C · VS Code & team customisation · según el diseño del autor, después de «VS Code: Chat, Plan, agent sessions, the Agents window, model choice and its price»
Exam rehearsal: GH-300 formats, traps by domain, time management~1,5 h · E · Governance & exam · según el diseño del autor, después de «Aldervane case: the February confidentiality incident — root causes across the whole course», «Copilot CLI essentials: install, interactive sessions, plan and autopilot, permissions, key commands, scripts and files»
Copilot CLI at work: sessions, delegation to the cloud agent, plugins and custom agents~1 h · Optional · Beyond the exam · según el diseño del autor, después de «Copilot CLI essentials: install, interactive sessions, plan and autopilot, permissions, key commands, scripts and files»
Models, BYOK and cost engineering under AI Credits~1 h · Optional · Beyond the exam · según el diseño del autor, después de «VS Code: Chat, Plan, agent sessions, the Agents window, model choice and its price»
Nivel 6
Built-in agents in Visual Studio: @debugger, @profiler, @test, @git review~1,5 h · B · Visual Studio 2026 · según el diseño del autor, después de «Agent mode in Visual Studio: tools, approvals, the build/test loop, Plan agent → Implement plan»
Custom agents and agent skills: team roles and procedures in the repository~2 h · C · VS Code & team customisation · según el diseño del autor, después de «Team rules: copilot-instructions.md, *.instructions.md with applyTo, prompt files, organisation instructions — and what VS and the CLI see»
Testing with Copilot: unit and integration tests, edge cases, assertions — and why an agent's green tests prove little~1,5 h · D · Quality & teamwork · según el diseño del autor, después de cualquiera de estas: «Agent mode in Visual Studio: tools, approvals, the build/test loop, Plan agent → Implement plan», «VS Code: Chat, Plan, agent sessions, the Agents window, model choice and its price»
Copilot CLI in automation: non-interactive runs, preToolUse hooks, scripts and CI~1 h · Optional · Beyond the exam · según el diseño del autor, después de «Copilot CLI at work: sessions, delegation to the cloud agent, plugins and custom agents»
Nivel 7
Lab: modernising Engage.Legacy.Import with @modernize (.NET Framework 4.8 → .NET 10)~2 h · B · Visual Studio 2026 · según el diseño del autor, después de «Built-in agents in Visual Studio: @debugger, @profiler, @test, @git review»
MCP: connecting servers, trust, allowlists and registry policy, data leakage and prompt injection through tools~1,5 h · C · VS Code & team customisation · según el diseño del autor, después de «Custom agents and agent skills: team roles and procedures in the repository»
Security and performance review: Review Selection, Copilot code review on pull requests, and judging AI findings~1,5 h · D · Quality & teamwork · según el diseño del autor, después de «Testing with Copilot: unit and integration tests, edge cases, assertions — and why an agent's green tests prove little»
Hooks and guardrails in VS Code: agent hooks, scoped hooks in custom agents, failure semantics~1 h · Optional · Beyond the exam · según el diseño del autor, después de «Custom agents and agent skills: team roles and procedures in the repository»
Nivel 8
The cloud agent: from issue to pull request, reviewing an agent's PR, and when delegation pays off~1,5 h · D · Quality & teamwork · según el diseño del autor, después de «Security and performance review: Review Selection, Copilot code review on pull requests, and judging AI findings»
Nivel 9
Spaces, PR summaries and review standards in instruction files (and Spark, briefly)~1 h · D · Quality & teamwork · según el diseño del autor, después de «The cloud agent: from issue to pull request, reviewing an agent's PR, and when delegation pays off»
Examenfinal · en el navegador, sin el asistentecerrada · inscríbete en el curso

0 de 25 unidades hechas · ~29,5 h sin las unidades opcionales, ~34,5 h con ellas

Security and performance review: Review Selection, Copilot code review on pull requests, and judging AI findings

Qué enseña la unidad

Choose the right review surface: Review Selection, @git and Review changes with Copilot in Visual Studio, Generate Code > Review and Uncommitted Changes in VS Code, /review in the CLI, and Copilot code review on pull requests
Explain Copilot code review defaults: Comment reviews, one review per pull request, skipped files, no model switching, content exclusion respected
Configure automatic reviews and effort levels, and explain the announced Lite-to-Balanced default change and its cost
Describe preview approvals and their controls (enterprise, organisation, repository, file paths, dismissal on new commits)
Separate a correct security finding from an incorrect suggested fix and verify performance claims with measurement
Distinguish Copilot code review from Copilot Autofix and CodeQL code scanning

Esta unidad está abierta para los inscritos

La inscripción es gratuita: es lo que permite al servidor recordar tu progreso entre sesiones.

Iniciar sesión e inscribirse Volver a la página del curso