GitHub Copilot on Chris Reddington

An interactive agentic AI mental model

Thu, 16 Apr 2026 00:00:00 +0000

An interactive agentic AI mental model is an interactive guide to how an agentic AI system works. It brings together the moving parts that are easy to talk about separately, but harder to hold as one picture when you are building with agents.

The project walks through how instructions, capabilities, retrieved context, session state, memory, MCP servers, sandbox execution, tool results, and the Think-Act-Observe loop connect in practice.

Features

Interactive mental model: Explore the core components of an agentic AI system in one connected view
Context engineering focus: Understand how context windows, retrieved context, and session state shape agent behaviour
Operational building blocks: See where memory, tool use, MCP servers, and sandbox execution fit into the overall system
Practical framing: Use the Think-Act-Observe loop as a simple way to reason about how agents work in real workflows

Agentic memory: what agents should and shouldn't remember

Fri, 10 Apr 2026 00:00:00 +0000

While building some of my own AI-agent based projects, I’ve run into the same frustrating loop. An agent would uncover something useful in the work itself (a hidden dependency, an awkward repo rule, a dead end I’d already ruled out), and then forget it all in the next session. I’d steer it back on course, start fresh later, and watch it head straight for the same mistake again. All that earlier momentum had gone.

AGENTS.md and SKILL.md: building a reusable agent toolbox

Wed, 08 Apr 2026 00:00:00 +0000

I was working on a personal project and coming up with a Copilot CLI demo to show and tell at the GitHub Social Club in London yesterday. But as I started a fresh agent session, and typed the setup, I caught myself writing the same lines I’d written for some work a few days earlier.

It included a few lines around the process for writing out plans, how the agent should hand off between planning, what the implementation expectations were, and how to review the work when it was done. That repetition (me repeatedly hitting the up arrow to get to my earlier prompts) was a sign that the knowledge I was typing should be packaged as something reusable, not left as another throwaway prompt.

Context engineering: more context isn't better context

Sun, 05 Apr 2026 00:00:00 +0000

I was in a customer presentation recently where I asked the room whether they were familiar with the term prompt engineering. Almost everyone raised their hand. This wasn’t a surprise, given how it’s been used over the last 3 years to make sure that being specific, giving examples, and setting clear instructions are part of the conversation around AI tools.

But then I asked whether they were familiar with context engineering. Only a few people raised their hand, and even fewer were using it as a deliberate way to think about how they work with AI agents. I genuinely expected more people to have heard of it given how much the term has grown over the past year, even if they weren’t applying the principles just yet.

GitHub Copilot SDK demo: Creating "Flight School"

Thu, 05 Feb 2026 00:00:00 +0000

Chris Reddington demonstrates “Flight School,” a custom Next.js application built to personalize his learning journey using the GitHub Copilot SDK.

Key topics covered:

Agentic workflows — leveraging the Copilot SDK to generate daily coding challenges based on a GitHub profile
AI-powered evaluation — evaluating solutions against test cases with automated feedback
Project export — automatically exporting completed projects to new GitHub repositories
Personalized learning — habit tracking, dynamic learning topics, real-time skill customization, and integration with the GitHub MCP server for enhanced developer growth

Rubber Duck Thursdays - Let's build with GitHub Copilot SDK

Thu, 29 Jan 2026 00:00:00 +0000

Join us for Rubber Duck Thursdays! A lighthearted and informal stream where we live code on some projects. This week we explore how to bring the power of GitHub Copilot into your apps with the GitHub Copilot SDK, building hands-on examples and discussing patterns for integrating AI-powered coding assistance directly into developer tools and workflows.

Flight School

Mon, 26 Jan 2026 00:00:00 +0000

Flight School is an AI-powered coding practice platform built with the GitHub Copilot SDK. It delivers personalized challenges, real-time evaluation, and learning guidance based on your GitHub profile.

Features

Personalized Challenges: Generates coding exercises tailored to your skill level and GitHub activity
Real-time Evaluation: Instant feedback on your solutions powered by AI
Learning Guidance: Contextual hints and explanations to help you grow
GitHub Integration: Leverages your GitHub profile to understand your strengths and areas for improvement

Rubber Duck Thursdays - It's time to build!

Thu, 08 Jan 2026 00:00:00 +0000

Chris showcases Timestamp (gh.io/timestamp), an open-source countdown timer app that evolved from the 2025 holiday streams into a fully extensible project with multiple themes, comprehensive testing, and GitHub automation.

Timestamp — Open Source Countdown Timer

The app is built with vanilla TypeScript and Vite, featuring:

Multiple themes — contribution graph (GitHub-style squares that fill as midnight approaches), fireworks celebration (powered by fireworks.js), and a scaffoldable ring theme
World map wall clock — an interactive SVG map using Natural Earth public domain data with day/night visualization
Time zone support — countdown to midnight in any city worldwide with a drop-down and map selector
Light/dark mode — system-aware theme switching with per-theme styling
Accessibility — built-in reduced motion support, keyboard navigation, and WCAG considerations

Copilot Custom Instructions vs Agents vs Prompt Files

Chris shares key lessons learned from structuring his Copilot configuration:

Rubber Duck Thursdays - Let's build our way into 2026!

Thu, 18 Dec 2025 00:00:00 +0000

In the last European-timezone-friendly stream of 2025, Chris builds a New Year countdown app from scratch — and reveals a GitHub contribution graph-themed countdown he built earlier.

Building a Countdown App from Scratch

Chris scaffolds a new project using Vite with vanilla TypeScript and Tailwind CSS v4, using GitHub Copilot to generate the initial countdown logic, HTML structure, and styling. The app counts down to midnight on New Year’s with large digits and subtle animations.

Rubber Duck Thursdays - Let's build down tech debt

Thu, 11 Dec 2025 00:00:00 +0000

Chris reviews the latest GitHub changelog and explores the major VS Code December release, then continues building custom agents for a game MCP server project.

GitHub Changelog Highlights

CodeQL 2.23.6 adds Swift 6.2.1 and new C# security queries
GPT-5.1 Codex Max now in public preview for GitHub Copilot across VS Code, GitHub.com, and GitHub Mobile
Workflow dispatch inputs limit increased from 10 to 25
Copilot code generation metrics now available in the enterprise insights dashboard
Enterprise teams limits increased over 10x — up to 2,500 teams and 5,000 users per team
Dependabot-based dependency graphs for Go now provide more complete transitive dependency trees
npm classic tokens revoked — replaced with session-based and CLI token management
Repository custom properties now support GraphQL management and a URL type with built-in validation
GitHub MCP server adds tool-specific configuration, lockdown mode for untrusted contributors, and default content sanitization against prompt injection
GitHub Enterprise Server 3.19 GA with rule set history import/export, SSH/TLS cipher configuration, and OpenTelemetry metrics
Auto model selection GA in VS Code for all Copilot plans

VS Code December Release — Agent Features

Agent HQ for managing multiple coding agents — background, cloud, or local — working simultaneously
Background agents with git worktrees for isolated workspaces, enabling multiple agents to work in parallel without file conflicts
Custom agents for organizations — share agents at the org level via .github-private repositories
Sub-agents via run sub agent — delegate tasks to specialized sub-agents with their own context windows to avoid context bloat
Claude skills support — reuse existing Claude Code skills within VS Code agents
Session management improvements — integrated sessions view, compact and side-by-side layouts, and persistent local agent sessions

Live Coding — Custom Agents and Background Agents

Chris demonstrates the new VS Code agent features by continuing work on a tic-tac-toe game with an MCP server backend. He creates a testing specialist agent using a TDD workflow, experiments with background agents running in git worktrees, and explores sub-agent delegation for specialized tasks like code quality review.

Rubber Duck Thursdays - Let's build with custom agents (again!)

Thu, 04 Dec 2025 00:00:00 +0000

Chris continues building custom agents for the SDLC, exploring the awesome-copilot repository for inspiration and live-building a GitHub Actions workflow agent with plan mode.

Topics Covered

GitHub Changelog Roundup — Blocking repo admins from installing GitHub Apps now GA, Copilot Spaces with public spaces and code view support, secret scanning updates for November 2025, GitHub Enterprise Server 3.19 RC, assigning issues to Copilot via GraphQL and REST APIs, and Claude Opus 4.5 availability across more IDEs.
Agent Inspiration from awesome-copilot — Reviewing partner-built agents and the awesome-copilot repository for ideas including test writers, security reviewers, tech debt analyzers, documentation generators, PR review assistants, and onboarding guides.
Agent Consolidation — Discussing whether to keep agents separate or consolidate them based on shared tool access, output formats, and domain overlap.
Building a GitHub Actions Agent — Using plan mode to design a custom agent for authoring and updating GitHub Actions workflows, including monorepo build order awareness and minimal permissions guidance.
GitHub Actions Instructions File — Creating a companion instructions file with repository-specific CI/CD conventions, build order, environment variables, and recommended practices for workflow definitions.
Plan Mode Workflow — Demonstrating the iterative plan-then-implement workflow where Copilot asks clarifying questions before generating code, and switching between plan and agent modes.

Rubber Duck Thursdays - Let's build with custom agents

Thu, 27 Nov 2025 00:00:00 +0000

Chris explores Copilot custom agents and custom instructions, restructuring project context files and creating meta instruction files for a more effective AI-assisted development workflow.

Topics Covered

GitHub Changelog Roundup — Enterprise bring-your-own-key for Copilot, linter integration with Copilot code review (ESLint, PMD), GitHub Actions cache size exceeding 10 GB, Claude Opus 4.5 in public preview, and secret scanning updates.
Custom Instructions Deep Dive — Restructuring copilot-instructions.md to include monorepo tech stack details, build order, service boundaries, security guidelines, and testing conventions using recommended practices from the docs.
Meta Instruction Files — Creating instruction files that teach Copilot how to write better custom instructions and custom agents, pulling in recommended practices from the GitHub and VS Code documentation.
Plan Mode for Agent Design — Using Copilot’s plan mode to iterate on ideas before implementation, demonstrating how follow-up questions help refine requirements like rubber duck debugging.
Context Engineering — Discussion on supplying the right context to Copilot, balancing context window size, and the importance of being requirements-driven for high-quality code generation.
Community Q&A — Topics including sustainable engineering pace, avoiding burnout, handling merge conflicts, and the fundamentals of software quality.

Rubber Duck Thursdays - Let's build

Thu, 20 Nov 2025 00:00:00 +0000

Chris catches up on several weeks of GitHub releases and then returns to the turn-based game MCP server project to fix a dependency upgrade issue.

Topics Covered

GitHub Changelog Roundup — Managing Copilot coding agent tasks in VS Code, new OIDC token claims for GitHub Actions, GPT-5.1 and Codex models, configuring the coding agent as a bypass actor for rulesets, MCP registry and allowlist controls in VS Code Stable, plan mode and isolated sub-agents in public preview, Gemini 3 Pro, and CodeQL updates.
MCP Server for Games — Revisiting the tic-tac-toe MCP server project and demonstrating how tool calls allow natural language game interaction with a backend API.
Fixing Dependency Upgrades with Copilot — Using agent mode across multiple models (Codex, Gemini 3 Pro) to diagnose and resolve a type check failure caused by a Dependabot SDK version bump.

Rubber Duck Thursdays - Time to build!

Thu, 04 Sep 2025 00:00:00 +0000

Join us for Rubber Duck Thursdays! A lighthearted and informal stream where we live code on some projects.

In this stream, we explore adding a 3D visualization to the turn-based game MCP server using Three.js, built with help from Copilot coding agent. We demo switching between 2D and 3D views of tic-tac-toe games while playing against the MCP server, and discuss the iterative process of prompting Copilot — including the importance of specifying requirements like piece orientation and camera controls.

Rubber Duck Thursdays - Let's keep building!

Thu, 28 Aug 2025 00:00:00 +0000

Join us for Rubber Duck Thursdays! A lighthearted and informal stream where we live code on some projects.

In this stream, we recap the turn-based game MCP server and demo the elicitation feature for gathering user preferences, then shift gears into a deep dive on GitHub Actions. Starting from an empty repository, we build workflows from scratch — covering YAML structure, event triggers (issues, issue_comment, push, pull_request, workflow_dispatch), jobs running in parallel, job dependencies using the needs property, conditional steps with if, and matrix strategies for cross-platform builds across multiple OS and Node.js versions.

Rubber Duck Thursdays - Building a turn-based-game MCP server

Thu, 07 Aug 2025 00:00:00 +0000

Join us for Rubber Duck Thursdays! A lighthearted and informal stream where we live code on some projects.

In this stream, we continue building our turn-based game MCP server, focusing on implementing elicitation — a Model Context Protocol feature for gathering additional user input when creating games. We consolidate duplicate tool calls (create game, play game) into generic handlers, reducing code duplication and improving maintainability. The session also covers using Copilot coding agent to automate refactoring tasks like extracting shared constants and removing duplicated difficulty badge logic.

Rubber Duck Thursdays - Build for the love of code

Thu, 24 Jul 2025 00:00:00 +0000

In this episode, we recap the latest GitHub changelog including GitHub Spark entering public preview and coding agent support for instructions.md files. We introduce the Build for the love of code hackathon, prototype a rubber duck debugging app with GitHub Spark, and build an MCP server from scratch using TypeScript while exploring tools, prompts, and resources.

Topics covered

GitHub changelog recap — M2 Pro hosted runners, GitHub Issues quality-of-life updates, Azure endpoint deprecation for GitHub Models, PR files changed improvements, Copilot code review policy changes, GitHub Spark public preview for Copilot Pro Plus, coding agent support for instructions.md custom instructions, and base branch selection for coding agent tasks.
Build for the love of code hackathon — Introduced the gh.io/love-of-code hackathon running July 16 to September 22 with six categories: hardware projects, AI agents, terminal tools, games, web apps, and wildcard entries. Brainstormed duck-themed project ideas with Copilot.
GitHub Spark prototyping — Used GitHub Spark (now in public preview) to rapidly prototype a rubber duck debugging web app with animated duck companions and different debugging personalities.
Building an MCP server from scratch — Scaffolded a TypeScript MCP server project from an empty repository, covering server initialization with the MCP SDK, registering tools with Zod schema validation, defining prompts and resources, and setting up repository foundations including dev containers, Dependabot configuration, and GitHub Actions CI workflows.

Github-Informatiker verrät seine 4 besten KI-Prompts

Tue, 22 Jul 2025 00:00:00 +0000

Context

Featured in a Gründerszene profile where I shared my 4 best AI prompts that help me focus on higher-value tasks requiring human judgment and creativity. The article explores how I use AI tools daily in my role at GitHub to automate repetitive work.

Key Quotes

On using AI to enhance productivity:

KI hilft Github-Informatiker Reddington dabei, seine Rolle effizienter und effektiver zu erfüllen. „Ich habe immer noch die Kontrolle und treffe letztlich die Entscheidungen", sagt er.

Rubber Duck Thursdays - Copilot agent mode, coding agent and MCP servers

Thu, 10 Jul 2025 00:00:00 +0000

In this episode, we review the latest GitHub changelog including remote MCP server support for coding agent and Copilot code review on mobile. We use the Playwright MCP server with Copilot agent mode to debug and fix UI issues in the Octo Arcade project, discuss the differences between ask, edit, and agent modes in VS Code, and explore MCP server concepts like tools, prompts, and resources.

Topics covered

GitHub changelog recap — Agents page for Copilot coding agent, CodeQL Rust support, improved repository creation experience, dependency auto-submission for Python, Copilot code review on GitHub Mobile, remote MCP server support for coding agent, and delegating tasks via the GitHub MCP server.
Playwright MCP server for UI debugging — Used Copilot agent mode with the Playwright MCP server to debug and fix game sizing issues in the Octo Arcade project, including viewport overflow, header overlap, and mobile responsiveness for pong, brick breaker, and matching games.
Ask vs Edit vs Agent mode — Walked through the practical differences between VS Code Copilot modes: ask for conversational code suggestions that must be manually applied, edit for targeted file changes, and agent mode for autonomous multi-step workflows that can run builds, tests, and use MCP tools.
MCP server concepts — Explored MCP server fundamentals including the three main primitives: tools (executable functions), prompts (predefined conversation templates), and resources (contextual data for the AI).

Rubber Duck Thursdays - Let's build

Thu, 03 Jul 2025 00:00:00 +0000

In this stream, Chris returns from vacation to catch up on weeks of GitHub updates and demonstrates adding internationalization to apps using Copilot coding agent, custom VS Code chat modes, and agent mode in Xcode.

Topics Covered

GitHub Changelog Review — Updates including model evaluations CLI for GitHub Models, remote GitHub MCP server in public preview, Copilot coding agent now available for business users, GitHub Models pay-as-you-go billing, Claude Sonnet 4 and Opus 4 GA, CodeQL updates for Go and Swift, Actions Runner Controller release, and Copilot code review with custom instructions support
Custom Chat Modes in VS Code — Creating a custom planning mode in VS Code Insiders to generate implementation plans and create GitHub issues, integrating the GitHub MCP server as a tool within the chat mode
Remote GitHub MCP Server — Setting up and authenticating with the new remote GitHub MCP server, eliminating the need for local Docker containers and personal access tokens via OAuth
Copilot Coding Agent for Internationalization — Assigning a GitHub issue to Copilot to add English, French, and Spanish language support to the Copilot Airways Next.js web app, reviewing the AI-generated pull request
Xcode Agent Mode — Demonstrating agent mode in Xcode to add internationalization to a Swift iOS version of the Copilot Airways app with a language selector
Issue Creation with Copilot — Using Copilot on github.com to draft well-structured GitHub issues from natural language descriptions

Rubber Duck Thursdays - Let's build with agents

Thu, 19 Jun 2025 00:00:00 +0000

In this episode, we recap the latest GitHub changelog updates including Copilot coding agent availability for pro users and the new Playwright MCP browser capability. We update Copilot custom instructions and setup steps for a GitHub Action project, use the Playwright MCP server to build interactive UI features on a trend radar app, and leverage Copilot coding agent to identify and fix technical debt.

Topics covered

GitHub changelog recap — Copilot coding agent for Copilot Pro users, GitHub Actions fine-grain permissions, upgraded Llama models, improved PR file experience, Dependabot minimum package age configuration, and Copilot coding agent Playwright MCP browser support.
Copilot custom instructions and setup steps — Updated custom instructions for a validate-file-exists GitHub Action project and created a Copilot setup steps YAML to configure the coding agent environment with Node.js and dependencies.
Playwright MCP server for UI development — Used the Playwright MCP server with Copilot coding agent to build drag-and-drop functionality and point editing on a trend radar web app, demonstrating how the agent can interact with a running application.
Technical debt with Copilot coding agent — Prompted Copilot to identify technical debt in the project, then created GitHub issues for package metadata fixes, documentation inconsistencies, and input validation improvements. Copilot coding agent autonomously submitted a PR addressing all three items with new tests.

Rubber Duck Thursdays - Copilot coding agent and Copilot agent mode

Thu, 05 Jun 2025 00:00:00 +0000

In this stream, Chris returns after Microsoft Build to dive deep into Copilot coding agent, demonstrating how to assign GitHub issues to Copilot and review the resulting pull requests.

Topics Covered

Microsoft Build Recap — Highlights from the event including Copilot coding agent announcements, agent mode availability in Eclipse, Xcode, and IntelliJ editors, and GitHub Models updates
GitHub Changelog Review — Three weeks of updates including Claude Sonnet 4 and Opus 4 in GitHub Copilot, Copilot Spaces, GPT-4o Copilot model update, coding agent on GitHub Mobile, secret scanning pattern expansions, and GitHub Enterprise Server 3.17
Copilot Coding Agent Deep Dive — Live demo with Copilot Airways app showing how to assign issues to Copilot, review AI-generated pull requests for refactoring and CI/CD deployment, and iterate through code review comments
MCP Integration with Notion — Demonstrating Model Context Protocol by connecting Copilot coding agent to a Notion MCP server to pull requirements from external tools and implement features automatically
Issue Scoping Best Practices — Structuring GitHub issues with overview, problem statement, acceptance criteria, implementation details, and file pointers for optimal Copilot coding agent results
Copilot Code Review — Using automated code review on pull requests with actionable suggestions for code quality

Extend GitHub Copilot coding agent with custom MCP tools

Sun, 01 Jun 2025 00:00:00 +0000

This video demonstrates an end-to-end MCP-powered workflow with the GitHub Copilot coding agent, using the ‘Copilot Airways’ travel guide as the demo application.

Key topics covered:

Creating a GitHub Issue from Copilot Chat on GitHub.com: asking Copilot to formulate a structured issue from a verbal description, including a link to the Notion document for traceability between the product team’s requirements and the engineering backlog
Assigning the issue to Copilot coding agent directly from the Copilot Chat interface—no need to navigate away to the Issues tab
How the Notion MCP server is configured to give Copilot access to external product documentation, bridging the gap between the product team’s tools and the engineering workflow
Inspecting the session view to see multiple MCP tool calls used to fetch information from Notion, which were then incorporated into Copilot’s implementation plan and code changes
How MCP servers and their associated tools are provisioned within GitHub Actions when Copilot is being set up for a coding agent task—visible in the workflow run logs
Navigating a large pull request using Copilot’s PR change summary to gain the right context before diving into a detailed code review

Assign issues to GitHub Copilot from the GitHub mobile app

Tue, 27 May 2025 00:00:00 +0000

The GitHub Copilot coding agent isn’t just a desktop experience—you can assign issues and track Copilot’s progress directly from the GitHub Mobile app or a mobile browser, making it useful during a commute or whenever you’re away from your laptop.

The video demonstrates the following mobile-first workflow using the ‘Copilot Airways’ demo repository:

Navigating the issues backlog and assigning a GitHub Pages deployment task to Copilot directly from the GitHub Mobile app
Copilot acknowledging the assignment with the 👀 emoji reaction and immediately creating a pull request
Switching to github.com in a mobile browser to open the pull request and tap ‘View session’
Reviewing how Copilot explored existing CI workflow files, formed a plan, updated configuration files, and modified the existing workflow to add the GitHub Pages deployment step
Copilot running linters, builds, and tests as quality checks during the agentic loop to ensure the CI pipeline remains healthy
Using the ‘Approve and Run’ button on mobile to authorize GitHub Actions execution against the AI-generated changes
Marking the pull request as ready for review and merging once checks pass—all without touching a laptop

Copilot Agent Mode is now available in GitHub Copilot for Xcode

Sat, 24 May 2025 00:00:00 +0000

GitHub Copilot for Xcode has added agent mode, bringing the same agentic capabilities available in Visual Studio Code to native Apple platform development. This video covers the key features and a practical demonstration.

Topics and demos include:

The new ask/agent mode toggle in the Copilot chat pane within Xcode—ask mode for back-and-forth conversation, agent mode for autonomous task execution that can invoke tools and run terminal commands
Configuring Model Context Protocol (MCP) via the Xcode settings page: navigating to the MCP tab, editing the configuration JSON, and reviewing available tools based on what’s already configured
Adding the GitHub MCP server to give Copilot access to GitHub repository data (issues, pull requests, etc.) directly from within Xcode
Using agent mode to look up open issues and summarize the state of work across the repository, helping prioritize what to tackle next
A hands-on fix: identifying that instant (on-first-keystroke) form validation creates a poor user experience in an iOS app, writing a clear instruction with explicit expectations for Copilot to follow, and watching it explore workspace files and apply the targeted change
Verifying the fix in the iOS simulator: confirming that input fields no longer show red validation errors on first load, and that error messages appear correctly when invalid data is entered

Assigning Copilot ad-hoc tasks through Copilot chat

Thu, 22 May 2025 00:00:00 +0000

The GitHub Copilot coding agent isn’t limited to work assigned from GitHub Issues—you can also delegate tasks directly from a Copilot Chat session in Visual Studio Code while actively working in the codebase.

The video walks through the following workflow on the ‘Copilot Airways’ demo app:

Opening Copilot Chat in ask mode in Visual Studio Code and invoking the @github chat participant
Describing naming inconsistencies found across the codebase and asking Copilot to raise a pull request that standardizes the naming conventions across all implementations
Reviewing Copilot’s proposed plan (including documentation improvements to make conventions explicit) and confirming before it proceeds
Copilot creating the pull request and returning a direct link within the chat session
Viewing the session log to see how Copilot mapped out the refactoring approach
Letting Copilot work asynchronously in the background—running lint and build steps to verify code quality—while continuing with other work
Returning to the pull request, using the ‘Approve and Run’ button to trigger GitHub Actions checks, and progressing to merge once all checks pass

How to get the most out of the Copilot coding agent

Wed, 21 May 2025 00:00:00 +0000

The GitHub Copilot coding agent works best when given rich context and a consistent environment. This video breaks down four concrete practices that help set Copilot up for success before a single line of code is written.

1. Write well-scoped GitHub Issues — Can the issue be resolved in a single pull request? Does it include a clear problem description, acceptance criteria, pointers to the relevant files, and a loose implementation plan to follow?

The GitHub Copilot coding agent NEW

Mon, 19 May 2025 00:00:00 +0000

GitHub Copilot coding agent lets you assign GitHub Issues to Copilot, which works asynchronously in the background while you continue with other tasks. This overview video uses the ‘Copilot Airways’ flight booking app to demonstrate the full workflow from issue assignment to merged pull request.

The video covers:

Assigning a GitHub Issue (adding form input validation) to Copilot with a single click
How Copilot acknowledges the assignment, creates a pull request, and keeps the PR description updated as it progresses
Viewing the Copilot session to understand how it explored the repository, formed a plan, and created a new GitHub Actions workflow file
How Copilot runs tools such as linters, builds, and tests to self-verify code quality during the agentic loop
The ‘Approve and Run’ safety gate, which requires explicit human approval before any GitHub Actions workflow executes against AI-generated code
Adding review comments to the PR (requesting a CI workflow) and watching Copilot acknowledge and act on the feedback
The final result: a form updated with real-time validation and an improved user experience, ready to merge

Rubber Duck Thursdays - Building from requirements with Agent Mode

Thu, 15 May 2025 00:00:00 +0000

In this stream, Chris walks through building a GitHub CLI extension in Go from scratch, taking a spec-driven and test-driven development approach powered by Copilot Agent Mode.

Topics Covered

GitHub Changelog Review — Model updates in GitHub Models (Mistral, Cohere, Llama), GPT-4.1 as the new default Copilot model, updated rate limits for unauthenticated requests, and the VS Code April release with MCP support and prompt files
Microsoft Build Preview — A look ahead at sessions and events for the following week
Building gh-demo from Scratch — Bootstrapping a new Go-based GitHub CLI extension using VS Code’s new workspace creation with Copilot, the Cobra library, and a spec-driven approach starting from a product requirements document
Test-Driven Development with Copilot — Writing tests first for a hydrate subcommand that reads JSON files to create GitHub issues, discussions, and pull requests, with content type filtering and label collection
GitHub Actions CI — Creating a build, test, and lint workflow for the new CLI extension
Custom Instructions — Setting up a copilot-instructions.md file to guide Copilot’s behavior around path handling and project conventions

Rubber Duck Thursdays - Agent mode and custom instructions

Thu, 08 May 2025 00:00:00 +0000

Chris continues exploring Copilot Agent Mode and custom instructions by building a memory sequence game for the GitHub CLI extension project in Go. The changelog segment covers GitHub CLI accessibility improvements, Copilot Code Review expanding to all languages, and the introduction of Copilot premium requests.

Changelog Highlights

GitHub CLI accessibility improvements — speech synthesis, screen reader support, enhanced prompting and progress indicators
Copilot Code Review now supports all languages with AI-powered suggestions and contextual feedback
Copilot Autofix updates for automated pull request suggestions
Copilot premium requests — announcement of upcoming premium model usage limits and visibility controls in VS Code and Visual Studio
GitHub CLI extension repo transferred to the github-samples organization

Live Coding — Memory Game with Agent Mode

Recapped custom instructions from the previous week and their impact on Copilot output quality
Built a memory sequence game (colors: red, yellow, green, blue) as a new subcommand in the Go-based GitHub CLI extension using Copilot Agent Mode
Used the Cobra command library and Bubble Tea for terminal UI interactions
Wrote detailed specs in chat — game mechanics, lives system, sequence display timing — and let Agent Mode scaffold the implementation and tests
Played live demos of coin toss, higher/lower, and word guess games from the CLI
Discussed potential future projects including VS Code extension development

Rubber Duck Thursdays - The one with custom instructions

Thu, 01 May 2025 00:00:00 +0000

This episode dives deep into Copilot custom instructions — what they are, how to write them, and why they matter for guiding AI-assisted development. Chris reviews the GitHub Changelog and then live codes a higher/lower game for a Go-based GitHub CLI extension using Agent Mode with detailed custom instructions.

Changelog Highlights

Copilot Code Review now supports C, C++, Kotlin, Swift, and more
CodeQL improves JavaScript and Ruby analysis in version 2.21.1
GitHub Models playground adds a prompt improvement feature to refine prompts with AI
Copilot Edits for JetBrains IDEs is now generally available
Credential revocation API for exposed tokens is now GA — supports bulk revocation via REST API
Task lists retirement on April 30th — code scanning alert references deprecated
Mistral Small 3.1 replaces Mistral Small in GitHub Models
Actions Runner Controller now supports running Dependabot on self-hosted Kubernetes runners

Live Coding — Custom Instructions Deep Dive

Explored how Copilot custom instructions provide repository context, coding standards, and structural guidance to every Copilot request
Demonstrated writing detailed instructions for a Go-based GitHub CLI extension — specifying test commands, linting rules, folder structure, and game design patterns using the Cobra library
Live coded a higher/lower guessing game using Copilot Agent Mode with Claude 3.7 Sonnet, showcasing how rich instructions lead to higher quality scaffolded code
Showed the Copilot Airways app built with Agent Mode from a screenshot, demonstrating vision capabilities and custom instruction-guided development

Rubber Duck Thursdays - Back to building GitHub CLI Extensions

Thu, 24 Apr 2025 00:00:00 +0000

In this episode, Chris reviews the GitHub Changelog covering organization-level Copilot custom instructions, CodeQL for Actions workflow security analysis, Copilot Code Review language expansion, secret scanning alert dismissals, and GitHub Mobile updates. The coding segment tackles theme switching for the Copilot Airways web app and a Tailwind CSS upgrade using GitHub Codespaces and Copilot Agent Mode.

Changelog Highlights

Organization custom instructions for Copilot enterprise customers
MAI-DSR1 — Microsoft AI-refined version of DeepSeek R1 available in GitHub Models
Copilot Code Review now supports C, C++, Kotlin, and Swift — covering over 90% of file types
CodeQL for GitHub Actions workflow security analysis is now generally available
Secret scanning alert dismissal requests with REST API support
Copilot for Xcode adds @workspace context, Claude 3.7 Sonnet, and GPT-4.5
GitHub Mobile updates including multi-model Copilot Chat and sub-issues
Dependabot scheduling with cron expressions

Live Coding

Fixed dark mode and light mode theme switching on the Copilot Airways web app
Attempted a Tailwind CSS upgrade in a fresh GitHub Codespace
Discussion of Copilot Agent Mode workflows and custom instructions for guiding AI-assisted development

Rubber Duck Thursdays - Building with Agent Mode and MCP

Thu, 17 Apr 2025 00:00:00 +0000

An especially announcement-heavy week focused on new AI model availability across GitHub Copilot and GitHub Models, plus hands-on experiments with those models in agent mode and GitHub Actions workflows.

The extensive changelog review covers GPT-4.1 rolling out to all Copilot plans, Gemini 2.5 Pro entering public preview, O3 and O4 mini availability, Meta Llama 4 Scout and Maverick models in GitHub Models, macOS 15 and Windows 2025 GA for Actions runners, Windows ARM64 hosted runners in preview, expanded vision support beyond GPT-4o to Claude and Gemini models, CodeQL 2.21.0 with TypeScript 5.8 support, Copilot Chat for Eclipse GA, secret scanning pattern expansions, and the new Codespaces agent mode button on pull requests.

Rubber Duck Thursdays - Building with Agent Mode and MCP

Thu, 10 Apr 2025 00:00:00 +0000

A big announcements week — this episode unpacks Copilot Agent Mode going stable in VS Code and the launch of the official GitHub MCP server, then puts both to work building a real app from scratch.

The GitHub Changelog segment covers the VS Code Copilot March release (agent mode GA, MCP support, next edit suggestions), the GitHub MCP server launch, Copilot Pro Plus tier, Copilot Code Review GA, security campaigns GA with automated issue creation, GitHub Issues and Projects improvements (sub-issues, issue types, 50K item limit), Helm support for Dependabot version updates, and more.

Rubber Duck Thursdays - Sshh, let's talk about secrets.

Thu, 03 Apr 2025 00:00:00 +0000

This episode focuses on why secrets should never exist in source code and how GitHub’s newly unbundled security products help prevent and detect secret leaks.

After the weekly GitHub Changelog review — covering the new GPT-4o Copilot completions model, repository ownership limits, GitHub Desktop updates, Copilot mobile multi-model support, and GitHub Issues dashboard improvements — Chris dives into the headline topic: GitHub Advanced Security splitting into two standalone products, Secret Protection ($19/month) and Code Security ($30/month), now available for GitHub Team plans without requiring Enterprise.

Rubber Duck Thursdays - Creating a brickbreaker walkthrough

Thu, 27 Mar 2025 00:00:00 +0000

Chris live-codes a GitHub-themed brick breaker game walkthrough using Copilot agent mode, demonstrating how prompt framing and context shape AI-generated code. The session covers bootstrapping project structure from an existing Game of Life template, Copilot custom instructions, and the latest GitHub changelog including enterprise rulesets, Copilot edits in JetBrains, and dependency label improvements.

In this episode, Chris sets out to build an educational walkthrough — similar to an existing Conway’s Game of Life sample — but for a brick breaker game styled with GitHub’s contribution graph colors. Using Copilot agent mode, he bootstraps the project structure by referencing the Game of Life walkthrough as context, then iterates on lesson pages focused on teaching prompt engineering for agent mode. The live coding demonstrates key concepts: how vague prompts produce incomplete results, how adding specific requirements (responsive containers, keyboard and mouse controls, bouncing physics) improves output, and how Copilot custom instructions (including a fun “talk like a pirate” experiment) modify agent behavior. Chris also briefly showcases the OctoSnap arcade concept and discusses ideas for making brick breaker use GitHub contribution data for brick colors and scoring. The changelog segment covers Mistral Small 3.1 in GitHub Models, upcoming GitHub Actions cache service changes, Copilot edits in JetBrains IDEs, enterprise custom properties and rulesets going GA, and Maven dependency labeling in the dependency graph.

Rubber Duck Thursdays - Exploring GitHub Models

Thu, 20 Mar 2025 00:00:00 +0000

Chris explores GitHub Models as an AI prototyping playground, demonstrates Copilot on the command line for learning Linux commands, and shows off a new leaderboard system for the OctoSnap card game. The session also covers two weeks of GitHub changelog updates including fine-grained personal access tokens going GA, enterprise-owned GitHub Apps, instant semantic code search indexing, and Copilot updates across VS Code, JetBrains, Xcode, and Eclipse.

Returning from a week off, Chris opens by demonstrating the GitHub CLI Copilot extension — using gh copilot suggest and gh copilot explain to translate natural language into shell commands, explain complex terminal commands, and learn Linux tooling interactively. He then showcases the OctoSnap leaderboard backed by Cosmos DB on Azure, and uses Copilot agent mode live to fix a bug where usernames with the @ symbol caused issues, including adding backend validation and tests. The second half focuses on GitHub Models, where Chris walks through the model catalog and playground, comparing models like GPT-4o and DeepSeek V3 for a computer science quiz scenario. He demonstrates system prompts, prompt presets, the prompt editor, quick actions for switching between cheaper and faster models, and how to generate integration code for JavaScript and Python. The changelog roundup covers Copilot custom instructions going GA, code referencing in JetBrains, enterprise-owned GitHub Apps, fine-grained PATs reaching general availability, actions performance metrics, and Copilot for Xcode chat becoming generally available.

Rubber Duck Thursdays - Building a scoring system

Thu, 06 Mar 2025 00:00:00 +0000

Chris walks through building “OctoSnap,” a GitHub-themed memory card matching game using Next.js and JavaScript. The session dives deep into designing a scoring model with GitHub Copilot — covering difficulty multipliers, time-based rewards, and penalty mechanics — and reviews the latest GitHub changelog including new AI models, GitHub Advanced Security pricing changes, secret scanning push protection APIs, and code scanning improvements for GitHub Actions workflows.

In this episode, Chris steps away from the Go-based CLI game extension built in previous weeks and introduces OctoSnap, a browser-based card matching game featuring artwork from the GitHub Octodex. He demonstrates the game across easy, medium, and hard difficulty modes, showing how image transformations like rotation and color filters increase challenge. The core focus is on iterating with Copilot to build a nuanced scoring system that balances mode difficulty multipliers, time duration bonuses, perfect play ratios, and random click penalties. Chris shares how he broke the problem into granular prompts for Copilot and visualized the scoring curves to ensure fair overlap between difficulty tiers. The changelog segment covers new models in GitHub Copilot and GitHub Models, GitHub Advanced Security being split into Secret Protection and Code Security standalone products, delegated alert dismissal, expanded CodeQL support for GitHub Actions and Go 1.24, and GitHub Mobile updates including Copilot chat and sub-issues.

Rubber Duck Thursdays - Lizard, Spock

Thu, 27 Feb 2025 00:00:00 +0000

In this episode, the team extends the Rock Paper Scissors game to include Lizard and Spock using GitHub Copilot Vision — feeding an image of the game’s relationship diagram directly into Copilot, which interprets it and generates the extended game logic without explicitly naming the game. The stream also adds a hidden flag for the extended mode, demonstrating prompt engineering with Copilot’s multimodal capabilities.

The GitHub changelog review covers Copilot autofix expansion for CodeQL alerts, Claude 3.7 Sonnet availability in Copilot, Docker Compose support in Dependabot, Copilot code review in public preview, and Copilot in Windows Terminal Canary. The latter portion demonstrates Dependabot version updates configured for Go modules and GitHub Actions ecosystems, with a live review of a dependency update pull request. A GitHub Codespaces session is used to verify the gh-skyline CLI extension still works after a dependency bump, and repository settings for auto-deleting branches and auto-merging pull requests are configured.

Rubber Duck Thursdays - Rock, Paper, Scissors

Thu, 20 Feb 2025 00:00:00 +0000

In this episode, I add a Rock Paper Scissors game to the gh-game GitHub CLI extension. The stream begins with a comprehensive GitHub changelog review covering the new GPT-4o Copilot code completion model, Copilot availability in Eclipse and Xcode, repository ruleset enhancements, secret scanning improvements, Copilot Workspace updates, and GitHub Issues and Projects feature updates.

The coding session uses GitHub Copilot Agent Mode to build the Rock Paper Scissors game in Go, taking advantage of Next Edit Suggestions and the new GPT-4o code completion model. A significant portion of the stream focuses on improving test coverage using Copilot’s inline chat in the terminal, progressing from 42.6% to 100% statement coverage by generating targeted test cases for uncovered functions. The episode also covers merging the Tic Tac Toe pull request from the previous week and shipping a new release of the CLI extension.

Rubber Duck Thursdays - Tic, Tac, Toe

Thu, 13 Feb 2025 00:00:00 +0000

In this episode, the team continues building the gh-game GitHub CLI extension by adding a Tic Tac Toe game written in Go. The stream kicks off with a demo of GitHub Spark, a GitHub Next experiment for creating micro apps from natural language prompts, followed by a walkthrough of the latest GitHub changelog updates including Gemini 2.0 Flash availability, Copilot Vision, and Agent Mode in VS Code Insiders.

The main coding session uses GitHub Copilot Agent Mode, Copilot Chat, and Copilot Edits to scaffold and iterate on the Tic Tac Toe implementation. Along the way, CodeQL code scanning is enabled on the repository, catching issues with missing workflow permissions and unpinned GitHub Actions versions. The episode also covers the CI/CD pipeline setup with build and test steps in GitHub Actions, and improving code readability through Copilot-assisted refactoring.

Rubber Duck Thursdays - Actions, Codespaces and Coin Toss

Thu, 06 Feb 2025 00:00:00 +0000

Continuing the gh-game CLI extension project, this episode covers setting up a complete development workflow. Chris creates a GitHub Codespace with a dev container configuration, installs Go and the GitHub CLI as features, and demonstrates how Codespaces provide a consistent environment for contributors.

The stream then covers creating a CI workflow using GitHub Actions with build and test steps, followed by writing Go tests for the coin toss game. A key segment focuses on refactoring the coin toss input from manual text entry to interactive selection menus using the go-gh prompter package, demonstrating how context and accurate prompting is essential when working with GitHub Copilot. Chris uses multiple Copilot models including Gemini 2.0 Flash and O3 Mini throughout the session.

Rubber Duck Thursdays - Creating gh-game CLI extension

Thu, 30 Jan 2025 00:00:00 +0000

This episode dives into GitHub Actions, starting with a walkthrough of the build, linter, and release workflows configured for the GitHub Skyline CLI extension. Chris explains workflow triggers, permissions, and demonstrates cutting a live release using semantic versioning and the cli/gh-extension-precompile action to generate cross-platform binaries.

The second half focuses on creating a brand new GitHub CLI extension from scratch. Using gh extension create, Chris bootstraps the gh-game project and builds a coin toss game in Go with the Cobra package. GitHub Copilot assists with scaffolding the command structure, applying code changes, and generating commit messages. The stream also covers publishing the repository using gh repo create.

Rubber Duck Thursdays - GitHub Skyline

Thu, 23 Jan 2025 00:00:00 +0000

In this inaugural Rubber Duck Thursdays episode, Chris introduces GitHub Skyline — a GitHub CLI extension written in Go that generates 3D STL models and ASCII art visualizations of your GitHub contribution history. The stream demonstrates the gh skyline command, including the --full flag for rendering your entire contribution history across all years as a single 3D model suitable for 3D printing.

The main coding activity focuses on refactoring the Skyline Go codebase using GitHub Copilot. Chris uses Copilot Chat for rubber ducking on code structure, then leverages Copilot Edits to split a monolithic main.go into modular components — separating the root command, browser interface, GitHub client, and skyline generation logic into individual files. The stream also covers GitHub Codespaces and dev containers for setting up a consistent development environment, and discusses community files like CODE_OF_CONDUCT, CONTRIBUTING, and LICENSE for open source projects.

Game of Life Walkthrough

Wed, 18 Dec 2024 00:00:00 +0000

This is a companion walkthrough for the hero Game of Life video that was published on the GitHub YouTube channel. It provides a step-by-step guide to the concepts covered in the video, including:

GitHub Actions
GitHub Codespaces
GitHub Copilot
GitHub Copilot Chat
GitHub Copilot Edits
GitHub Copilot Instructions
GitHub Copilot Extensions
GitHub Pages

Build Conway's Game of Life with GitHub Copilot Free

Mon, 16 Dec 2024 00:00:00 +0000

This is a demo video showing GitHub Copilot in an end-to-end scenario, by building Conway’s Game of Life. The video covers the following specific topics:

Selecting the Claude Sonnet 3.5 model in the GitHub Copilot Chat model picker in Visual Studio Code
Writing specific, clear prompts: requesting a single-file implementation with a responsive layout and configurable cell size
Tips on effective prompt engineering: keeping prompts simple and specific to reduce ambiguous output
Reviewing generated code before inserting it, then customising the colour scheme to match the GitHub contribution graph
Using the “Apply in Editor” button with speculative decoding to apply targeted diffs across an existing file
Refactoring from a single HTML/CSS/JS file to separate files using Copilot Edits for multi-file changes
Reviewing multi-file diffs in the Copilot Edits view and accepting changes per file
Using drag-and-drop to add files as context to Copilot Chat and Copilot Edits sessions
Improving readability with Copilot Edits: grouping variables, adding a new class, and nesting methods
Using a Copilot instructions file to enforce team coding standards (HTML5 meta tags, JSDoc comments) in subsequent edits
Inline chat slash commands: /doc to generate documentation for a function and /explain to learn about an unfamiliar concept (torus topology)
Using Copilot Extensions to integrate Copilot’s natural language interface with external tools and services
Generating a project README with Copilot Edits, summarising the app, implementation, and contribution guidelines
Writing a GitHub Actions deployment workflow to publish the static site to GitHub Pages
Using Copilot to suggest a commit message, committing, pushing, and verifying the live GitHub Pages deployment

Use GitHub Spark to create a podcast timer apps

Mon, 04 Nov 2024 00:00:00 +0000

This is a demo video showcasing GitHub Spark. The video covers the following specific topics:

GitHub Spark’s mobile-first design philosophy: building apps on the go using natural language
Creating a podcast session timer app from a plain-language description
Iteratively adding controls via natural language: start, pause, and reset for each timer segment
Adding a reverse progress bar to give hosts a visual sense of remaining time
Implementing a color-coded time indicator: green (>50% remaining), amber (25–50%), red (<25%)
Triggering a red flashing alert when a timer reaches zero
Using Spark’s built-in LLM integration to allow users to create timer segments from a natural language description (e.g. “two 5-minute stanzas and a 3-minute outro”)
Using the Spark sidebar to view and edit managed state (timer data) directly and see updates reflected in the app
Renaming and starring the app to keep it accessible from the dashboard
Sharing the finished app via a read-only or write-access link for collaboration

How GitHub Next took Copilot Workspace from concept to code

Thu, 31 Oct 2024 00:00:00 +0000

Whether you’re addressing an issue, iterating on a pull request, or bootstrapping a project, GitHub Copilot Workspace helps jumpstart your tasks by describing what you want in natural language. You remain in control as you move between tasks, specs, plans, and code. Join GitHub’s Chris Reddington, senior program manager of DevRel, and Cole Bemis, research engineer on GitHub Next, for an introduction to Copilot Workspace, a Copilot-native dev environment launched in April 2024 by GitHub Next. Learn how Copilot Workspace works, how we got here, and what we’ve learned so far from the technical preview.

Hands on with Anthropic Claude 3.5 Sonnet in GitHub Copilot

Wed, 30 Oct 2024 00:00:00 +0000

Come to this session to be the first in the world to get a deep-dive demo of the exciting Claude 3.5 Sonnet model from Anthropic built right into GitHub Copilot. Learn what this powerful new model will help you achieve and why you should use it for your development teams.

Use GitHub Spark to create a travel log app

Tue, 29 Oct 2024 00:00:00 +0000

This is a demo video showcasing GitHub Spark. The video covers the following specific topics:

GitHub Spark’s positioning as an AI-native micro-app platform from GitHub Next: build, use, and share apps through natural language without managing deployments
Building a city travel log app by describing it in plain language and receiving an immediately interactive app (no code shown)
Using the built-in theme editor to switch light/dark mode and customise accent colours and border radii
Iterating on the app via natural language: adding latitude/longitude capture for each city entry
Using the data tab to view and manage stored state without any database or connection string configuration
Extending the app to support editing and deleting entries, and plotting city ratings on an interactive map
Adding AI-powered city suggestions: using Spark’s built-in LLM integration to recommend three destinations based on existing ratings
Using the variant generator when a prompt is ambiguous (“make it more sunny and fun”), producing multiple distinct UI options to choose from
Navigating the revision history sidebar to review, revert, or branch off prior states
Renaming and starring the app for quick dashboard access

GitHub Copilot Chat and o1-preview: Building a maze generator!

Thu, 03 Oct 2024 00:00:00 +0000

This is a demo video showcasing GitHub Copilot and o1-preview. The video covers the following specific topics:

Accessing the model picker in GitHub Copilot Chat within Visual Studio Code (GPT-4o, o1 mini, o1 preview)
Writing a specific, multi-requirement prompt for o1-preview: a JavaScript maze generator with keyboard navigation, variable maze sizing, and a maze-solve button
Understanding o1-preview’s extended internal reasoning, which produces longer response times but handles complex requirements more reliably
Reviewing the generated code and copying it into the VS Code editor; initial iteration produces a working maze with BFS and DFS visualisation
Iterating with a follow-up prompt to enhance the solution path display (black dot trail, no-path notification)
Testing edge cases with a 50×50 maze and a distant starting position to observe depth-first search behaviour visually
Comparing o1-preview output quality against the expectation for GPT-4o on the same multi-constraint task

Beyond Code With Github the AI Revolution in Software Development

Wed, 04 Sep 2024 00:00:00 +0000

As AI continues to reshape the way businesses innovate, the conversation shifts beyond the mere integration of new technology. Chris emphasizes that adopting AI-powered software development is a significant cultural shift, requiring more than just technical tools. It demands a top-down approach, where leadership support and change management are critical to fostering a progressive culture within development teams.

GitHub Galaxy 2024 Amsterdam

Wed, 12 Jun 2024 00:00:00 +0000

Ready to explore our blueprint for AI-powered development? Join us to network with local tech leaders and learn the key to addressing tech debt, modernizing the software development lifecycle, and transforming your enterprise.

GitHub Galaxy 2024 Paris

Wed, 29 May 2024 00:00:00 +0000

GitHub Galaxy 2024 Stockholm

Wed, 22 May 2024 00:00:00 +0000

Code from your phone with Github Copilot Workspace

Fri, 03 May 2024 00:00:00 +0000

This is a demo video for the technical preview of GitHub Copilot Workspace. The video covers the following specific topics:

Accessing GitHub Copilot Workspace from the GitHub mobile app on a phone or tablet
Entering a task using typed text or the device’s built-in voice dictation
Reviewing, editing, and approving the AI-generated specification (current state and proposed state)
Progressing from specification to plan and reviewing the proposed file changes on mobile
Inspecting code diffs and making edits directly on the mobile interface
Running unit tests from the built-in terminal to verify the implementation before raising a PR
Creating a pull request with an AI-generated description from within the mobile workflow

How to use Copilot Workspace for inspiration

Wed, 01 May 2024 00:00:00 +0000

This is a demo video for the technical preview of GitHub Copilot Workspace. The video covers the following specific topics:

Starting Copilot Workspace from a GitHub template repository as a creative springboard
Generating a specification that outlines the current state (template) and proposed state (customised to-do app)
Progressing from specification to a step-by-step implementation plan
Using the live app preview pane alongside the plan and code for in-flow iteration
Streaming code changes into the environment and installing new npm dependencies via the integrated terminal
Using undo/redo to navigate through Copilot Workspace change history while the live preview updates in sync
Switching to GitHub Codespaces to make direct code edits (layout, styling, form) that sync back into Copilot Workspace
Sharing the in-progress workspace with collaborators via the share button
Creating the repository from Copilot Workspace, which triggers a GitHub Actions build and deployment to production automatically

Transform issues into plans with GitHub Copilot Workspace

Mon, 29 Apr 2024 00:00:00 +0000

This is a demo video for the technical preview of GitHub Copilot Workspace. Chris was responsible for:

Writing the script
Creating a demo environment
Recording the demo
Recording the voiceover
Production and Editing

GitHub Galaxy 2024 London

Thu, 25 Apr 2024 00:00:00 +0000

GitHub Galaxy 2024 Berlin

Tue, 16 Apr 2024 00:00:00 +0000

Beyond version control: Using GitHub throughout your development lifecycle

Sat, 02 Mar 2024 00:00:00 +0000

GitHub is well-known for version control, and its work with the open source community. But did you know you can use GitHub throughout your development lifecycle?

Join Chris Reddington from GitHub’s Developer Relations team as he explores how you can use GitHub to plan, code, build, and deploy your work. Learn how the platform comes together in GitHub Issues, Projects, Codespaces, Actions, Copilot and Advanced Security!

London Reactor Meetup | DevOps meets AI

Tue, 16 Jan 2024 00:00:00 +0000

DevOps is inherently a cultural shift with a mass of technologies involved at many stages of the lifecycle. Over the past year we have seen a huge change in the AI sector and these developers, entrepreneurs and businesses are all starting to adopt this technology and make it a part of their everyday development. With this being the case, the DevOps lifecycle is going to pivot and change for everyone in one way or another, so let’s dive into how this is happening!

End-to-end InnerSourcing and Secure Development with GitHub

Thu, 13 Oct 2022 00:00:00 +0000

From 'It works on my machine' to 'It was written by a machine' - GitHub Codespaces & Copilot

Mon, 10 Oct 2022 00:00:00 +0000

From 'It works on my machine' to 'It was written by a machine' - GitHub Codespaces & Copilot

Fri, 23 Sep 2022 00:00:00 +0000

ToolUp Days #12

Tue, 06 Sep 2022 00:00:00 +0000

With the game’s microservices architecture designed and a clear definition of done in hand, Chris and Matt turn their attention to getting the World Events Engine working end-to-end. The session opens with an unexpected obstacle: Chris had inadvertently broken all the GitHub Actions builds in the run-up to the stream.

Diagnosing the GitHub Actions deployment bug

Two workflows were triggered simultaneously, both defaulting to the same container name (derived from the workflow filename). Deploying two Azure Container App revisions with identical names into the same resource group created a race condition — one deployment could not start because the other was already in progress under the same name.

ToolUp Days #11

Tue, 23 Aug 2022 00:00:00 +0000

This episode marks the official rebrand from ToolUp Tuesday to ToolUp Days — giving Chris and Matt the scheduling flexibility they need to maintain a consistent cadence. After recapping progress (multiple microservices built, GitHub Actions CI/CD in place, container images published, and Infrastructure as Code deployed), the pair set a concrete goal: reach a point where two players can independently make a decision, a “tick” happens, and there is a winner and a loser.

ToolUp Tuesday #2

Tue, 22 Feb 2022 00:00:00 +0000

Chris and Matt move from planning to coding, creating the Player State API as a .NET Web API project. They define data models representing player state for the SpaceBar management sim, debating how deep and detailed the models should go. The episode covers practical .NET development decisions, including the trade-offs between minimal API patterns and traditional controller-based approaches, with a preference for controllers for better logical grouping.

The pair also set up their first GitHub Actions CI workflow, walking through YAML syntax for building the .NET project on push to main. They troubleshoot the workflow live — discovering they forgot the checkout step — and iterate until the build succeeds. GitHub Copilot makes a brief appearance as a code suggestion tool during API scaffolding.

V027 - Weekly Technology Vlog #27

Sun, 04 Jul 2021 00:00:00 +0000

Vlog #27 was the first dedicated tech episode under the new alternating format (gaming one week, tech deep-dives the next). No Sea of Thieves this time — the full runtime went to GitHub Copilot, CNCF, Kubernetes, Azure Arc, and more.

GitHub Copilot Technical Preview

Chris walked through a live GitHub Copilot demo across two languages, showing how the AI pair programmer synthesises code from natural language comments and surrounding context.

GitHub Copilot on Chris Reddington

An interactive agentic AI mental model

Features

Agentic memory: what agents should and shouldn't remember

AGENTS.md and SKILL.md: building a reusable agent toolbox

Context engineering: more context isn't better context

GitHub Copilot SDK demo: Creating "Flight School"

Rubber Duck Thursdays - Let's build with GitHub Copilot SDK

Flight School

Features

Rubber Duck Thursdays - It's time to build!

Timestamp — Open Source Countdown Timer

Copilot Custom Instructions vs Agents vs Prompt Files

Rubber Duck Thursdays - Let's build our way into 2026!

Building a Countdown App from Scratch

Rubber Duck Thursdays - Let's build down tech debt

GitHub Changelog Highlights

VS Code December Release — Agent Features

Live Coding — Custom Agents and Background Agents

Rubber Duck Thursdays - Let's build with custom agents (again!)

Topics Covered

Rubber Duck Thursdays - Let's build with custom agents

Topics Covered

Rubber Duck Thursdays - Let's build

Topics Covered

Rubber Duck Thursdays - Time to build!

Rubber Duck Thursdays - Let's keep building!

Rubber Duck Thursdays - Building a turn-based-game MCP server

Rubber Duck Thursdays - Build for the love of code

Topics covered

Github-Informatiker verrät seine 4 besten KI-Prompts

Context

Key Quotes

Rubber Duck Thursdays - Copilot agent mode, coding agent and MCP servers

Topics covered

Rubber Duck Thursdays - Let's build

Topics Covered

Rubber Duck Thursdays - Let's build with agents

Topics covered

Rubber Duck Thursdays - Copilot coding agent and Copilot agent mode

Topics Covered

Extend GitHub Copilot coding agent with custom MCP tools

Assign issues to GitHub Copilot from the GitHub mobile app

Copilot Agent Mode is now available in GitHub Copilot for Xcode

Assigning Copilot ad-hoc tasks through Copilot chat

How to get the most out of the Copilot coding agent

The GitHub Copilot coding agent *NEW*

Rubber Duck Thursdays - Building from requirements with Agent Mode

Topics Covered

Rubber Duck Thursdays - Agent mode and custom instructions

Changelog Highlights

Live Coding — Memory Game with Agent Mode

Rubber Duck Thursdays - The one with custom instructions

Changelog Highlights

Live Coding — Custom Instructions Deep Dive

Rubber Duck Thursdays - Back to building GitHub CLI Extensions

Changelog Highlights

Live Coding

Rubber Duck Thursdays - Building with Agent Mode and MCP

Rubber Duck Thursdays - Building with Agent Mode and MCP

Rubber Duck Thursdays - Sshh, let's talk about secrets.

Rubber Duck Thursdays - Creating a brickbreaker walkthrough

Rubber Duck Thursdays - Exploring GitHub Models

Rubber Duck Thursdays - Building a scoring system

Rubber Duck Thursdays - Lizard, Spock

Rubber Duck Thursdays - Rock, Paper, Scissors

Rubber Duck Thursdays - Tic, Tac, Toe

Rubber Duck Thursdays - Actions, Codespaces and Coin Toss

Rubber Duck Thursdays - Creating gh-game CLI extension

Rubber Duck Thursdays - GitHub Skyline

Game of Life Walkthrough

Build Conway's Game of Life with GitHub Copilot Free

Use GitHub Spark to create a podcast timer apps

How GitHub Next took Copilot Workspace from concept to code

Hands on with Anthropic Claude 3.5 Sonnet in GitHub Copilot

Use GitHub Spark to create a travel log app

GitHub Copilot Chat and o1-preview: Building a maze generator!

Beyond Code With Github the AI Revolution in Software Development

GitHub Galaxy 2024 Amsterdam

GitHub Galaxy 2024 Paris

The GitHub Copilot coding agent NEW