Advanced Technology Center AI Lead — Accenture
Sources: BLS Occupational Outlook Handbook, Software Developers (2023–2033 projection) · Anthropic & Google figures per Apr 2026 company statements / press reporting · Industry averages from 2025–26 developer surveys (GitHub, Stack Overflow, DORA).
A Question for the Room
Even a simple one — just a clickable mockup in Figma.
Spark hands the power of building to anyone with an idea — describe it in plain language and get a working prototype back, no team or backlog required.
The shift: when prototyping is nearly free, the bottleneck becomes ideas, not engineering bandwidth.
Clear prompts = better results from Copilot!
Copilot is powerful but can make mistakes — always validate before shipping.
Short answer To answer questions about your project, Copilot builds context from your code — including indexes that power features like @workspace and #codebase.
Practical tip: Use explicit scopes like #codebase, @github, or workspace context to limit what Copilot reads.
Live demos in VS Code — what could go wrong? :) The remaining slides are reference material to revisit later.
GitHub Copilot: Sign InCopilot is available on multiple GitHub plan tiers, and specific free/trial limits vary by account, org, and region.
| Action | macOS | Windows/Linux |
|---|---|---|
| Accept suggestion | Tab | Tab |
| Dismiss suggestion | Esc | Esc |
| Next suggestion | Option + ] | Alt + ] |
| Previous suggestion | Option + [ | Alt + [ |
| Trigger suggestion | Option + \ | Alt + \ |
| Open Chat view | Ctrl + Cmd + I | Ctrl + Alt + I |
| Inline Chat | Cmd + I | Ctrl + I |
Context Creep 🌊 Context Confusion 😵💫
How: Click "New Chat" or Ctrl/Cmd + L
pip install?Press the ↑ arrow in the chat input to quickly recall your previous chat messages.
Pro Tip: Iterate on questions without starting over.
After getting a response, you can:
Pro Tip: Hover over code blocks in chat to reveal action buttons.
@workspace — reason over your entire codebase@vscode — VS Code settings & features@terminal — command-line help@github — GitHub platform, web search & knowledge basesExamples: "Add a new component and wire it up" · "Migrate this feature and run the tests"
Create a plan for a user authentication system with:
- Email/password login
- Social OAuth integration
- Password reset
- JWT token management
- Database schema design
| Aspect | Plan Mode | Ask / Agent |
|---|---|---|
| Scope | Strategic planning | Immediate execution |
| Horizon | Days / weeks | Minutes / hours |
| Output | Detailed roadmap | Code implementation |
| Best For | Project planning | Code development |
GitHub Copilot offers distinct modes for different scenarios:
Quick in-place edits use Inline Chat (Cmd/Ctrl + I). Let's explore how they differ and when to use each…
| Feature | Ask Mode | Agent Mode |
|---|---|---|
| Purpose | Info & explanations | Autonomous multi-file changes |
| Access | Chat view (Ask) | Chat view (Agent dropdown) |
| Scope | Questions & learning | Entire workspace |
| Output | Text + examples | Code edits, commands, iterations |
| Best For | Learning, debugging | Features, refactors, migrations |
| Feature | Agent Mode | Plan Mode |
|---|---|---|
| Purpose | Autonomous multi-file work | Strategic planning |
| Access | Agent dropdown → Agent | Agent dropdown → Plan |
| Scope | Entire project/workspace | Full project lifecycle |
| Output | Workflows & changes | Implementation roadmap |
| Best For | Features, refactors | Large projects, migrations |
| Ask | Agent | Plan | |
|---|---|---|---|
| Complexity | Low | Med–High | High |
| Speed | Instant | Moderate | Planning |
| Interaction | Conversational | Autonomous | Strategic |
| Learning Curve | Easy | Moderate | Advanced |
Pro Tip: Ask to understand → Agent to build & refactor → Plan for big initiatives.
Create: .github/copilot-instructions.md (repo-wide, always applied)
- Use TypeScript for new files
- All functions include JSDoc comments
- Follow company naming conventions
- Always add error handling
- Write unit tests for new functions
AGENTS.md is also supported as an open, cross-tool standard~/Library/Application Support/Code/User/settings.json%APPDATA%\Code\User\settings.json~/.config/Code/User/settings.json.vscode/settings.jsonCreate: .github/prompts/<name>.prompt.md
Example: .github/prompts/test-generator.prompt.md
---
mode: agent
description: Generate comprehensive unit tests
---
Generate unit tests for the selected function:
- Happy path scenarios
- Edge cases and error conditions
- Mock external dependencies
- Use the Jest testing framework
Usage: type /test-generator in Copilot Chat
.github/prompts/code-review.prompt.md
# Code Review Assistant
Review the selected code for:
- Security vulnerabilities and best practices
- Performance optimizations
- Maintainability and readability
- Adherence to project coding standards
Usage: /code-review + select code
.github/prompts/arch-docs.prompt.md
# Architecture Documentation Generator
Update architecture documentation for:
- System design patterns used
- Component relationships and dependencies
- Data flow and API contracts
- Deployment and scaling considerations
Usage: /arch-docs + relevant files
Result: Copilot understands your architecture and suggests better code!
Create: .github/instructions/<name>.instructions.md
---
applyTo: "src/**/*.ts"
---
# TypeScript Code Style
- Use camelCase for variables and functions
- Add explicit types for all parameters
- Include JSDoc comments for public functions
- Keep components under 200 lines
The applyTo glob scopes these rules to matching files automatically.
Create: .github/agents/<name>.agent.md (formerly "custom chat modes")
---
description: Expert code reviewer
tools: ['codebase', 'search']
---
You are an expert code reviewer. Focus on:
- Security vulnerabilities
- Performance optimizations
- Maintainability & best practices
Always provide specific suggestions with examples.
Usage: select your agent from the Chat view Agent dropdown
Sparkles are the ✨ icons in VS Code that signal:
.vscode/settings.json{
"github.copilot.chat.commitMessageGeneration.instructions": [
{ "text": "Use conventional commit format" }
],
"github.copilot.chat.codeGeneration.instructions": [
{ "text": "Always add TypeScript types" }
]
}
{
"github.copilot.chat.commitMessageGeneration.instructions": [
{
"text": "For Slides changes, describe the change in
content — not the technical implementation."
}
]
}
your-project/
├── .vscode/
│ └── settings.json
├── .github/
│ ├── copilot-instructions.md
│ ├── instructions/
│ ├── prompts/
│ └── agents/
└── other-files...
Three ways to enhance your interactions:
# context · @ participants · / commands
#file:README.md — include a specific file#<symbol> — reference a function, class, or variable#selection — current code selection#codebase — search the whole project for context#terminalLastCommand — last terminal command & outputMore precise context → more accurate, relevant suggestions.
@workspace, @vscode, @terminal, @githubType @ in chat to see every participant available in your install.
/explain — explain selected code/fix — fix issues in code/tests — generate test cases/doc — generate documentation/new — scaffold new files/projectsYour custom prompt files also show up here as /<name>.
Fix issues in a specific file:
/fix #file:src/components/Button.js
Generate tests for the selection:
/tests #selection
Explain with full codebase context:
@workspace /explain #codebase
The Model Context Protocol (MCP) lets Copilot connect to external tools & data sources.
.vscode/mcp.json or through the MCP tooling UI in your editorTooling and one-click installs vary by editor version and extension capabilities.
"Create a bug ticket for the login timeout issue"
"Show me open issues in the frontend repo"
"Update ticket DEV-456 status to In Progress"
#getJiraIssue
#editJiraIssue
Create a high-priority Jira bug for the login
timeout in the authentication module
Show open issues assigned to me in the frontend repo
List my current sprint tasks with status "To Do"
Set AUTH-123 to "In Progress" and comment
"Started investigating timeout configuration"
These settings help you shape Copilot from a general assistant into a tool that fits your work style, team practices, and project context.
Plugins expand Copilot's capabilities by adding new tools, integrations, or features that the agent can use during a task.
Think of them as add-ons: more power, but only when relevant.
Model Context Protocol (MCP) servers let Copilot connect to external systems in a standard, reusable way.
Benefit: the agent can work with live tools instead of only reading local code.
Skills are reusable capabilities that teach the agent how to perform a certain kind of work well.
Goal: consistent expertise, not random guesswork.
Instructions are the long-term guardrails for Copilot.
- Use TypeScript for new files
- Add JSDoc for public APIs
- Always validate with tests
- Follow team naming conventions
Result: less drift and more predictable output.
Agents are specialized assistant profiles built for a specific job or team workflow.
Best use: repeatable, specialized work rather than open-ended brainstorming.
Hooks trigger automation when events happen in your workflow.
Example: validate code quality or generate notes immediately after a file is updated.
Tools are the actions Copilot is allowed to take. They define what the agent can read, edit, run, and verify.
Rule: the more precise the tool access, the more controlled and reliable the automation.
Takeaway: Copilot becomes much more useful when you give it the right context, constraints, and tools.
# Install the standalone CLI (example)
npm install -g @github/copilot
# Start an interactive session
copilot
copilot
# Chat, iterate, and steer. Use the agent selector for planning workflows.
# Common features may include /model, /mcp, /context, and /compact
copilot -p "Show this week's commits and summarize them" \
--allow-tool='shell(git)'
# Run in an isolated cloud sandbox
copilot --cloud
# Local code changes
"Change the background-color of H1 headings to dark blue"
# Work an assigned issue end-to-end
"I've been assigned issue #1234 — start it in a new branch"
# Make changes and open a PR
"Add a user-info.js script and open a pull request"
# Git help
"Revert the last commit, leaving the changes unstaged"
Auto-compaction keeps long sessions going; /sandbox enable restricts local access.
James Gress · AI Lead @ Accenture
jmgress.github.io/githubcopilot
| → Space PgDn | Next slide |
| ← PgUp | Previous slide |
| Home / End | First / last slide |
| S | Toggle speaker notes |
| F | Toggle fullscreen |
| ? | Toggle this help |
Press any key to close.