Ihr Weg

Stufe 1
Course map: plans, AI Credits, setting up Visual Studio 2026 and VS Code, the ENGAGE repository~1 Std. · A · Foundations
Stufe 2 · ~1,5 Std. · A · Foundations · laut Plan des Autors nach „Course map: plans, AI Credits, setting up Visual Studio 2026 and VS Code, the ENGAGE repository“innerhalb einer Stufe ist die Reihenfolge frei
How Copilot works: prompt building, context, proxy filtering, post-processing, suggestion lifecycle
Responsible use: risks, hallucinated APIs, insecure patterns, output ownership, verification discipline
Stufe 3
Context engineering and prompting: #-references, participants, zero/few-shot, chat history, fresh sessions~1,5 Std. · A · Foundations · laut Plan des Autors nach „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 Std. · E · Governance & exam · laut Plan des Autors nach „Responsible use: risks, hallucinated APIs, insecure patterns, output ownership, verification discipline“
Stufe 4
Visual Studio 2026 basics: inline suggestions, Next Edit Suggestions, Chat, Copilot Actions, commit messages~1 Std. · B · Visual Studio 2026 · laut Plan des Autors nach „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 Std. · C · VS Code & team customisation · laut Plan des Autors nach „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 Std. · E · Governance & exam · laut Plan des Autors nach „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 Std. · E · Governance & exam · laut Plan des Autors nach „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 Std. · Optional · Beyond the exam · laut Plan des Autors nach „Governance: organisation policies, content exclusion and its gaps, public code filter, audit log, REST API for seats, AI Credit budgets“
Stufe 5
Agent mode in Visual Studio: tools, approvals, the build/test loop, Plan agent → Implement plan~1,5 Std. · B · Visual Studio 2026 · laut Plan des Autors nach „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 Std. · C · VS Code & team customisation · laut Plan des Autors nach „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 Std. · E · Governance & exam · laut Plan des Autors nach „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 Std. · Optional · Beyond the exam · laut Plan des Autors nach „Copilot CLI essentials: install, interactive sessions, plan and autopilot, permissions, key commands, scripts and files“
Models, BYOK and cost engineering under AI Credits~1 Std. · Optional · Beyond the exam · laut Plan des Autors nach „VS Code: Chat, Plan, agent sessions, the Agents window, model choice and its price“
Stufe 6
Built-in agents in Visual Studio: @debugger, @profiler, @test, @git review~1,5 Std. · B · Visual Studio 2026 · laut Plan des Autors nach „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 Std. · C · VS Code & team customisation · laut Plan des Autors nach „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 Std. · D · Quality & teamwork · laut Plan des Autors nach einer beliebigen davon: „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 Std. · Optional · Beyond the exam · laut Plan des Autors nach „Copilot CLI at work: sessions, delegation to the cloud agent, plugins and custom agents“
Stufe 7
Lab: modernising Engage.Legacy.Import with @modernize (.NET Framework 4.8 → .NET 10)~2 Std. · B · Visual Studio 2026 · laut Plan des Autors nach „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 Std. · C · VS Code & team customisation · laut Plan des Autors nach „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 Std. · D · Quality & teamwork · laut Plan des Autors nach „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 Std. · Optional · Beyond the exam · laut Plan des Autors nach „Custom agents and agent skills: team roles and procedures in the repository“
Stufe 8
The cloud agent: from issue to pull request, reviewing an agent's PR, and when delegation pays off~1,5 Std. · D · Quality & teamwork · laut Plan des Autors nach „Security and performance review: Review Selection, Copilot code review on pull requests, and judging AI findings“
Stufe 9
Spaces, PR summaries and review standards in instruction files (and Spark, briefly)~1 Std. · D · Quality & teamwork · laut Plan des Autors nach „The cloud agent: from issue to pull request, reviewing an agent's PR, and when delegation pays off“
PrüfungAbschluss · im Browser, ohne den Assistentengesperrt · in den Kurs einschreiben

0 von 25 Einheiten abgeschlossen · ~29,5 Std. ohne die optionalen Einheiten, ~34,5 Std. mit ihnen

The cloud agent: from issue to pull request, reviewing an agent's PR, and when delegation pays off

Was die Einheit vermittelt

Explain how the cloud agent works and its limits: GitHub Actions environment, one repository, one branch, one pull request, 59 minutes
Start cloud agent tasks from issues, pull request comments, the agents page, VS Code, Visual Studio and the CLI, and iterate correctly via PR comments
Write a delegable issue with a file boundary, checkable acceptance criteria and a test command, and prepare the environment with copilot-setup-steps.yml
Describe the built-in guardrails and their gaps, including workflow approval, requester approval, the public code filter and content exclusion
Review an agent's pull request from the session log and diff, catching changes that compile and pass but miss the goal
Decide when delegation pays off by comparing review cost with implementation cost

Diese Einheit ist für Eingeschriebene zugänglich

Die Einschreibung ist kostenlos — dadurch kann sich der Server Ihren Fortschritt zwischen den Sitzungen merken.

Anmelden und einschreiben Zurück zur Kursseite