.webp)
.svg)
Program overview
Online
On-site
Hybrid
Agentic Development with GitHub Copilot
Copilot is no longer autocomplete. Learn to work with agent mode inside the IDE, delegate whole issues to the cloud coding agent, drive the Copilot CLI, and extend all three with persistent instructions and MCP servers connected to your own systems.
Duration:
3 Days
Level:
Intermediate
.avif)
1500+ users onboarded
Who will Benefit from this Training?
Training Objectives
Build a high-performing, job-ready tech team.
Personalise your team’s upskilling roadmap and design a befitting, hands-on training program with Uptut
Key training modules
Comprehensive, hands-on modules designed to take you from basics to advanced concepts
Download Curriculum
- The Copilot Surface in 2026
- Completions, chat, agent mode, the cloud coding agent and the CLI compared
- Choosing the right surface for a given piece of work
- Multi-model selection and how model choice changes results
- Premium requests: what consumes quota and how to monitor it
- Where Copilot sits against other agentic coding tools
- Agent Mode in the IDE
- How the agent plans a task, edits across files and runs terminal commands
- Self-correction loops, iteration limits and when it stalls
- Approving, interrupting and steering a run in progress
- Agent mode across VS Code and JetBrains
- Hands-on: deliver a multi-file feature end to end in agent mode
- Writing Delegations That Work
- Intent, scope and explicit stop conditions in a delegation
- Defining success criteria the agent can verify for itself
- Decomposing large tasks into agent-sized units
- Diagnosing why a run produced unusable output, and correcting it
- Hands-on: rewrite a failed delegation until it succeeds
- Persistent Context: Instructions, AGENTS.md and Spaces
- copilot-instructions.md for always-on project context
- AGENTS.md for agent-specific workflow rules and definitions of done
- Nesting instruction files across a monorepo
- Copilot Spaces for curated grounding across files, issues, PRs and docs
- Hands-on: author instruction files and measure the change in output
- The Cloud Coding Agent
- Assigning a GitHub issue and receiving a pull request back
- How the agent executes in the background and what it has access to
- Writing issues the coding agent can actually complete unattended
- Reviewing agent-authored pull requests without rubber-stamping them
- Hands-on: take an issue from assignment through to a merged PR
- Copilot CLI
- Installing and authenticating the CLI alongside your IDE setup
- Plan mode for scoping work before execution
- Autopilot mode and the guardrails worth setting first
- Parallel specialised subagents for explore, task, review and plan work
- Repository memory, hooks and plugins
- Hands-on: drive a complete task from the terminal
- Extending Copilot with MCP
- Model Context Protocol fundamentals and the built-in GitHub MCP server
- Connecting internal APIs, databases and documentation sources
- Scoping access, handling credentials and applying least privilege
- Copilot Extensions and how they differ from MCP connectors
- Hands-on: connect an MCP server and complete a task through it
- Working at Scale and Knowing When to Stop
- Running multiple agents in parallel without collisions
- Review load as the real constraint on agentic throughput
- Recognising when delegation costs more than doing the work yourself
- Team conventions for labelling and reviewing agent-generated code
- Measuring whether the workflow is genuinely faster, not just busier
Hands-on Experience with Tools
Training Delivery Format
Flexible, comprehensive training designed to fit your schedule and learning preferences
Opt-in Certifications
AWS, Scrum.org, DASA & more
.avif)
100% Live
on-site/online training
.avif)
Hands-on
Labs and capstone projects
.avif)
Lifetime Access
to training material and sessions
Skill-Gap Assessment
Analysing skill gap and assessing business requirements to craft a unique program
1
Personalisation
Customising curriculum and projects to prepare your team for challenges within your industry
2
Implementation
Supplementing training with consulting support to ensure implementation in real projects
3
Why this course
- Delegate whole tasks: Move from line-level suggestions to issues that come back as reviewable pull requests.
- Know when not to delegate: Judgement on where the agent loop pays off and where it costs you time.
- Persistent project context: Encode your standards once so every agent run follows them.
- Extend to your systems: Connect internal tools and data through MCP rather than copy-pasting context.
Training objectives
- Distinguish agent mode, the cloud coding agent and the Copilot CLI, and choose between them
- Write delegations with clear intent, scope and stop conditions
- Operate the agent loop across multi-file edits, terminal commands and self-correction
- Assign issues to the coding agent and review the resulting pull requests critically
- Use the Copilot CLI plan mode, autopilot and parallel subagents
- Encode persistent context using custom instructions, AGENTS.md and Copilot Spaces
- Extend Copilot with MCP servers connected to internal tools and data
- Select models per task and manage premium request consumption
Who will benefit
- Software developers and engineers
- Tech leads and engineering managers
- Platform and DevOps engineers
- Architects evaluating agentic development workflows
.avif)
Lead the Digital Landscape with Cutting-Edge Tech and In-House " Techsperts "
Discover the power of digital transformation with train-to-deliver programs from Uptut's experts. Backed by 70,000+ professionals across the world's leading tech innovators.
.svg)
.svg)
.svg)
.svg)
.svg)
Recommended Training
Continue your learning journey with these hand-picked courses and bundles
Frequently Asked Questions
2. Will my team get any practical experience with this training?
.svg)
With our focus on experiential learning, we have made the training as hands-on as possible with assignments, quizzes and capstone projects, and a lab where trainees will learn by doing tasks live.
3. What is your mode of delivery - online or on-site?
We conduct both online and on-site training sessions. You can choose any according to the convenience of your team.
4. Will trainees get certified?
Yes, all trainees will get certificates issued by Uptut under the guidance of industry experts.
5. What do we do if we need further support after the training?
We have an incredible team of mentors that are available for consultations in case your team needs further assistance. Our experienced team of mentors is ready to guide your team and resolve their queries to utilize the training in the best possible way. Just book a consultation to get support.