{"authors":[{"name":"Chris Reddington","url":"https://chrisreddington.com/about/"}],"description":"Chris Reddington is a Developer Relations expert sharing writing, talks and videos on AI tooling like GitHub Copilot, Claude Code and Codex, DevOps and cloud.","feed_url":"https://chrisreddington.com/feed.json","home_page_url":"https://chrisreddington.com/","items":[{"content_text":"ToolSmith proposes a plan before it builds anything, so the plan is where you catch mistakes. The fifth video in the Build EmployeeWorks plugins with ToolSmith series describes the booking cancellation task to ToolSmith, then reviews the plan it proposes, including how the plugin authenticates to PurpleSuite and whose bookings it finds.","date_published":"2026-11-06T00:00:00Z","id":"https://chrisreddington.com/video/describe-the-task-and-review-the-plan/","tags":["ServiceNow","EmployeeWorks","ToolSmith","Tool Studio","PurpleSuite","AI","Agentic AI","Developer Experience"],"title":"Describe the task and review the plan | Build EmployeeWorks plugins with ToolSmith (Part 5)","url":"https://chrisreddington.com/video/describe-the-task-and-review-the-plan/"},{"content_text":"You don't want to test a booking cancellation plugin against someone's real trip. The fourth video in the Build EmployeeWorks plugins with ToolSmith series introduces PurpleSuite, an enterprise app simulator, and shows how to create an instance, find the bookings and API operations in Purple Expense, and collect the credentials ToolSmith will need.","date_published":"2026-11-03T00:00:00Z","id":"https://chrisreddington.com/video/what-is-purplesuite/","tags":["ServiceNow","EmployeeWorks","ToolSmith","PurpleSuite","AI","Agentic AI","Developer Experience"],"title":"What is PurpleSuite? | Build EmployeeWorks plugins with ToolSmith (Part 4)","url":"https://chrisreddington.com/video/what-is-purplesuite/"},{"content_text":"Before ToolSmith builds a plugin for you, it helps to know how plugins are put together so you can review its plan. The third video in the Build EmployeeWorks plugins with ToolSmith series walks through a plugin's assets in Tool Studio (connector, HTTP actions, conversational process and the plugin itself), then follows an employee's request through all of them.","date_published":"2026-10-30T00:00:00Z","id":"https://chrisreddington.com/video/how-do-we-build-a-plugin-in-tool-studio/","tags":["ServiceNow","EmployeeWorks","ToolSmith","Tool Studio","AI","Agentic AI","Developer Experience"],"title":"How do we build a plugin in Tool Studio? | Build EmployeeWorks plugins with ToolSmith (Part 3)","url":"https://chrisreddington.com/video/how-do-we-build-a-plugin-in-tool-studio/"},{"content_text":"EmployeeWorks assistants can use Enterprise Search, MCP servers and plugins as tools. The second video in the Build EmployeeWorks plugins with ToolSmith series explains how tools and the agentic loop let a language model act, then when to reach for each option: Enterprise Search for company knowledge, MCP servers for an open standard set of tools, and plugins for tasks that have to run the same way every time.","date_published":"2026-10-27T00:00:00Z","id":"https://chrisreddington.com/video/plugins-mcp-servers-or-enterprise-search/","tags":["ServiceNow","EmployeeWorks","ToolSmith","MCP","AI","Agentic AI","Developer Experience"],"title":"Plugins, MCP servers or Enterprise Search? | Build EmployeeWorks plugins with ToolSmith (Part 2)","url":"https://chrisreddington.com/video/plugins-mcp-servers-or-enterprise-search/"},{"content_text":"An AI assistant is only as useful as the tools you give it. The first video in the Build EmployeeWorks plugins with ToolSmith series covers the groundwork: the problem employees face moving between systems to get something done, and how EmployeeWorks gives them one place to search company knowledge and take action across the systems they already use.","date_published":"2026-10-23T00:00:00Z","id":"https://chrisreddington.com/video/what-is-employeeworks/","tags":["ServiceNow","EmployeeWorks","ToolSmith","AI","Agentic AI","Developer Experience"],"title":"What is EmployeeWorks? | Build EmployeeWorks plugins with ToolSmith (Part 1)","url":"https://chrisreddington.com/video/what-is-employeeworks/"},{"content_text":"Employees shouldn't need to know which system handles their request, jump between portals, or learn how every application works to get something done. This series introduces EmployeeWorks and shows how to plan, build, review, and test well-governed plugins with ToolSmith.","date_published":"2026-10-23T00:00:00Z","id":"https://www.servicenow.com/community/sn-employeeworks-blog/build-employeeworks-plugins-with-toolsmith/ba-p/3613461","tags":["ServiceNow","EmployeeWorks","ToolSmith","AI","Agentic AI","Developer Experience"],"title":"Build EmployeeWorks plugins with ToolSmith","url":"https://www.servicenow.com/community/sn-employeeworks-blog/build-employeeworks-plugins-with-toolsmith/ba-p/3613461"},{"content_text":"A static Astro website for a South Wales carpentry and construction business, built with no CMS, database, or client-side framework, and deployed to GitHub Pages on a custom domain.","date_published":"2026-07-31T00:00:00Z","id":"https://chrisreddington.com/project/haus/","tags":["Astro","Web Development","GitHub Pages","Static Site"],"title":"Haus Carpentry \u0026 Construction","url":"https://chrisreddington.com/project/haus/"},{"content_text":"One model reviewing its own plan tends to agree with itself. So I built a cleanup workflow shaped like a jury: separate critics from a deliberate mix of model families weigh the evidence, with a simple forcing function that keeps neighbouring reviewers off the same family. The orchestrator presides as judge, refuting rather than merging, votes promote shared findings, and a post-approval diff check can overrule a verdict that was unanimous and still wrong.","date_published":"2026-06-03T00:00:00Z","id":"https://chrisreddington.com/blog/mixture-of-critics/","tags":["AI","GitHub Copilot","Agentic AI","Context Engineering","Developer Experience"],"title":"The Jury Pattern: a mixture of critics for AI code review","url":"https://chrisreddington.com/blog/mixture-of-critics/"},{"content_text":"Building with one agent is familiar. Orchestrating a fleet of them in parallel across local, background, and cloud surfaces is where it gets real. This session covers the decisions that matter, how to decompose work across agents, when to fork vs. delegate, and how to verify quality when agents outnumber you — with patterns for multi-agent workflows you can apply to your own codebase.","date_published":"2026-06-03T00:00:00Z","id":"https://chrisreddington.com/talk/2026-06-03-vscode-live-build/","tags":["Visual Studio Code","GitHub Copilot","AI","Agentic AI"],"title":"Multi-agent patterns in VS Code you won't learn from docs","url":"https://chrisreddington.com/talk/2026-06-03-vscode-live-build/"},{"content_text":"An interactive mental model for agentic AI that explains how instructions, retrieved context, session state, memory, MCP servers, sandbox execution, tool results, and the Think-Act-Observe loop fit together.","date_published":"2026-04-16T00:00:00Z","id":"https://chrisreddington.com/project/agentic-ai/","tags":["AI","Context Engineering","GitHub Copilot","MCP"],"title":"An interactive agentic AI mental model","url":"https://chrisreddington.com/project/agentic-ai/"},{"content_text":"Conversation state and retrieved context lead naturally into memory, but only if we're clear about what memory is for. Rules, skills, and instruction files package what you already know. Memory should capture what the work itself teaches the system, and that means reflection, verification, and forgetting matter just as much as recall.","date_published":"2026-04-10T00:00:00Z","id":"https://chrisreddington.com/blog/agentic-memory-what-agents-should-remember/","tags":["AI","GitHub Copilot","Agentic AI","Context Engineering","Developer Experience"],"title":"Agentic memory: what agents should and shouldn't remember","url":"https://chrisreddington.com/blog/agentic-memory-what-agents-should-remember/"},{"content_text":"Start with minimal AGENTS.md and SKILL.md examples, then adapt the portable core alongside Copilot-specific concepts like custom instructions, agents and prompt files. This post explains what belongs where and how to check that the files improve a real agent task.","date_published":"2026-04-08T00:00:00Z","id":"https://chrisreddington.com/blog/building-your-agent-toolbox/","tags":["AI","GitHub Copilot","Agentic AI","Context Engineering","Developer Productivity"],"title":"AGENTS.md and SKILL.md examples: build a reusable agent toolbox","url":"https://chrisreddington.com/blog/building-your-agent-toolbox/"},{"content_text":"Better prompts help, but they're only part of the story. Context engineering is the craft of designing what an AI agent sees, when it sees it, and how that changes across the session. The goal isn't a bigger context window. It's a more effective one.","date_published":"2026-04-05T00:00:00Z","id":"https://chrisreddington.com/blog/context-engineering-more-isnt-better/","tags":["AI","GitHub Copilot","Agentic AI","Context Engineering","Prompt Engineering","Developer Experience"],"title":"Context engineering: more context isn't better context","url":"https://chrisreddington.com/blog/context-engineering-more-isnt-better/"},{"content_text":"There's a pattern I've seen play out across dozens of DevRel conversations, confirmed in my MBA dissertation research: teams without a clear golden thread from company strategy to daily activity get 'randomised' by whoever asks most urgently. Here's what the research says about why it happens and how to build your way out of it.","date_published":"2026-03-31T00:00:00Z","id":"https://chrisreddington.com/blog/devrel-randomisation-trap/","tags":["Developer Relations","DevRel","Strategy","Developer Experience","Measurement","Research"],"title":"The DevRel randomisation trap (and how to stop it)","url":"https://chrisreddington.com/blog/devrel-randomisation-trap/"},{"content_text":"DevRel is often framed as the voice of the developer. My research suggests a broader job: gathering representative feedback, reducing friction, and showing developers what changed.","date_published":"2026-03-22T00:00:00Z","id":"https://chrisreddington.com/blog/devrel-feedback-loop/","tags":["Developer Relations","DevRel","Strategy","Developer Experience","Community","Product Feedback","Measurement"],"title":"The feedback loop: how DevRel bridges community and product","url":"https://chrisreddington.com/blog/devrel-feedback-loop/"},{"content_text":"Of the 13 DevRel leaders I interviewed for my MBA dissertation, only two could clearly demonstrate a coherent link between tactical activity and organisational strategy. In this post, I talk through how focusing on the developer journey can help bridge that gap.","date_published":"2026-03-22T00:00:00Z","id":"https://chrisreddington.com/blog/devrel-tactics-to-strategy/","tags":["Developer Relations","DevRel","Strategy","Developer Experience","Measurement","Research"],"title":"From tactics to strategy: the DevRel measurement gap","url":"https://chrisreddington.com/blog/devrel-tactics-to-strategy/"},{"content_text":"Academic research on brand communities can help DevRel, but only up to a point. The bigger lesson is where the model breaks: developer communities run on trust in the technology, not loyalty to the brand.","date_published":"2026-03-21T00:00:00Z","id":"https://chrisreddington.com/blog/devrel-communities-not-brand-communities/","tags":["Developer Relations","DevRel","Strategy","Developer Experience","Community","Research"],"title":"Why developer communities are not brand communities","url":"https://chrisreddington.com/blog/devrel-communities-not-brand-communities/"},{"content_text":"Two companies can have similarly capable DevRel teams doing similar work and still get different results. In my research, company type, lifecycle stage, and technology cycles kept shaping what DevRel could realistically do.","date_published":"2026-03-19T00:00:00Z","id":"https://chrisreddington.com/blog/devrel-company-context-lifecycle/","tags":["Developer Relations","DevRel","Strategy","Developer Experience","Developer Communities"],"title":"Company context: the conditions that shape DevRel strategy","url":"https://chrisreddington.com/blog/devrel-company-context-lifecycle/"},{"content_text":"Education. Success. Marketing. Programs. These four pillars describe what Developer Relations teams do. But the more important question is what makes that work credible, useful, and trusted by developers.","date_published":"2026-03-16T00:00:00Z","id":"https://chrisreddington.com/blog/devrel-four-pillars-authentic-foundation/","tags":["Developer Relations","Developer Advocacy","Strategy","Developer Experience","Research"],"title":"The four pillars of DevRel (and the foundation they rest on)","url":"https://chrisreddington.com/blog/devrel-four-pillars-authentic-foundation/"},{"content_text":"Developer Experience isn't just central to DevRel strategy. It's both what your team depends on before it can succeed, and what it actively shapes through its work.","date_published":"2026-03-14T00:00:00Z","id":"https://chrisreddington.com/blog/devrel-developer-experience/","tags":["Developer Relations","DevRel","Strategy","Developer Experience","Developer Experience Audit","Product Adoption"],"title":"Developer experience: prerequisite and product of DevRel","url":"https://chrisreddington.com/blog/devrel-developer-experience/"},{"content_text":"Developer Relations is sometimes equated to marketing. Incorporating insights from 13 interviews, I explain why DevRel is better understood as value co-creation.","date_published":"2026-03-12T00:00:00Z","id":"https://chrisreddington.com/blog/devrel-value-co-creation-not-marketing/","tags":["Developer Relations","DevRel","Strategy","Developer Experience","Value Co-creation","Developer Advocacy","Community","Developer Marketing"],"title":"Developer Relations is more than marketing. It's co-creation.","url":"https://chrisreddington.com/blog/devrel-value-co-creation-not-marketing/"},{"content_text":"The question of how Developer Relations (DevRel) teams create value has been answered plenty of times (though rarely through systematic research). In 2024 I looked into it properly through 13 interviews with DevRel leaders, culminating in an MBA dissertation at Warwick Business School, unearthing a couple of surprises along the way. This series works through what I found.","date_published":"2026-03-11T00:00:00Z","id":"https://chrisreddington.com/blog/devrel-value-creation/","tags":["Developer Relations","DevRel","Strategy","Developer Experience","Research","Measurement","MBA"],"title":"How does Developer Relations (DevRel) create value? What 13 interviews revealed.","url":"https://chrisreddington.com/blog/devrel-value-creation/"},{"content_text":"Chris Reddington demonstrates \"Flight School,\" a custom Next.js application built to personalize his learning journey using the GitHub Copilot SDK. See how he leverages agentic workflows to generate daily coding challenges based on his GitHub profile, evaluate solutions against test cases, and automatically export projects to new repositories.","date_published":"2026-02-05T00:00:00Z","id":"https://chrisreddington.com/video/2026-02-05-copilot-sdk-flight-school/","tags":["GitHub","GitHub Copilot","GitHub Copilot SDK","AI","Agentic AI","Next.js","Developer Experience"],"title":"GitHub Copilot SDK demo: Creating \"Flight School\"","url":"https://chrisreddington.com/video/2026-02-05-copilot-sdk-flight-school/"},{"content_text":"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.","date_published":"2026-01-29T00:00:00Z","id":"https://chrisreddington.com/video/2026-01-29-rubber-duck-thursdays/","tags":["GitHub","GitHub Copilot","GitHub Copilot SDK","AI","Agentic AI","Developer Experience","Live Stream"],"title":"Rubber Duck Thursdays - Let's build with GitHub Copilot SDK","url":"https://chrisreddington.com/video/2026-01-29-rubber-duck-thursdays/"},{"content_text":"AI-powered coding practice platform built with the GitHub Copilot SDK. Personalized challenges, real-time evaluation, and learning guidance based on your GitHub profile.","date_published":"2026-01-26T00:00:00Z","id":"https://chrisreddington.com/project/flight-school/","tags":["AI","GitHub Copilot","TypeScript"],"title":"Flight School","url":"https://chrisreddington.com/project/flight-school/"},{"content_text":"Learn how I managed context to keep Copilot focused, used the Plan agent to sharpen vague requirements, and required Test Driven Development practices to catch bugs before users.","date_published":"2026-01-20T00:00:00Z","id":"https://github.blog/developer-skills/application-development/context-windows-plan-agent-and-tdd-what-i-learned-building-a-countdown-app-with-github-copilot/","tags":["AI","GitHub Copilot","Testing","TypeScript","Developer Experience"],"title":"Context windows, Plan agent, and TDD: What I learned building a countdown app with GitHub Copilot","url":"https://github.blog/developer-skills/application-development/context-windows-plan-agent-and-tdd-what-i-learned-building-a-countdown-app-with-github-copilot/"},{"content_text":"A countdown app where every countdown is a URL. Create custom countdowns, timers, and world clocks for any occasion with multiple visual themes and instant URL sharing.","date_published":"2026-01-08T00:00:00Z","id":"https://chrisreddington.com/project/timestamp/","tags":["TypeScript","Accessibility"],"title":"Timestamp","url":"https://chrisreddington.com/project/timestamp/"},{"content_text":"Chris showcases Timestamp, an open-source countdown timer app built with vanilla TypeScript featuring an extensible theme system, world map wall clock, and 2500+ unit tests with 300+ Playwright end-to-end tests. He deep-dives into structuring GitHub Copilot custom instructions vs agents vs prompt files, demonstrates manager-specialist agent patterns, and walks through GitHub Actions automation for issue forms and theme scaffolding.","date_published":"2026-01-08T00:00:00Z","id":"https://chrisreddington.com/video/2026-01-08-rubber-duck-thursdays/","tags":["GitHub","GitHub Copilot","AI","Agentic AI","TypeScript","GitHub Actions","Open Source","Testing","Developer Experience","Automation"],"title":"Rubber Duck Thursdays - It's time to build!","url":"https://chrisreddington.com/video/2026-01-08-rubber-duck-thursdays/"},{"content_text":"Chris builds a New Year countdown app from scratch using Vite, TypeScript, and Tailwind CSS, leveraging GitHub Copilot's Plan agent for iterative requirements and a custom UI Performance Specialist agent. The stream covers adding time zone support with a world map, a fireworks celebration theme using fireworks.js, and a test-driven development approach.","date_published":"2025-12-18T00:00:00Z","id":"https://chrisreddington.com/video/2025-12-18-rubber-duck-thursdays/","tags":["GitHub Copilot","AI","Agentic AI","TypeScript","JavaScript","Developer Experience","Open Source","Testing","GitHub"],"title":"Rubber Duck Thursdays - Let's build our way into 2026!","url":"https://chrisreddington.com/video/2025-12-18-rubber-duck-thursdays/"},{"content_text":"Chris reviews the latest GitHub changelog including CodeQL updates, GPT-5.1 Codex Max preview, GitHub MCP server tool-specific configuration, and Enterprise Server 3.19 GA. He then explores the major VS Code December release featuring Agent HQ, background agents with git worktrees, sub-agents, and custom agents for organizations, while continuing to build custom agents for a game MCP server project.","date_published":"2025-12-11T00:00:00Z","id":"https://chrisreddington.com/video/2025-12-11-rubber-duck-thursdays/","tags":["GitHub","GitHub Copilot","Agentic AI","AI","Visual Studio Code","Model Context Protocol","GitHub Advanced Security","Enterprise","Security","Developer Experience"],"title":"Rubber Duck Thursdays - Let's build down tech debt","url":"https://chrisreddington.com/video/2025-12-11-rubber-duck-thursdays/"},{"content_text":"Chris continues building custom agents for the software development life cycle. After reviewing the changelog including Copilot Spaces updates and assigning issues to Copilot via API, he explores the awesome-copilot repository for agent inspiration, brainstorms SDLC agent ideas like test writers and security reviewers, and live-builds a GitHub Actions workflow agent with a companion instructions file.","date_published":"2025-12-04T00:00:00Z","id":"https://chrisreddington.com/video/2025-12-04-rubber-duck-thursdays/","tags":["GitHub Copilot","Agentic AI","GitHub Actions","Context Engineering","CI/CD","Visual Studio Code","Developer Experience","DevOps","Automation"],"title":"Rubber Duck Thursdays - Let's build with custom agents (again!)","url":"https://chrisreddington.com/video/2025-12-04-rubber-duck-thursdays/"},{"content_text":"Chris dives into Copilot custom agents and custom instructions for the turn-based game MCP server project. After reviewing the changelog including enterprise bring-your-own-key support and Claude Opus 4.5, he restructures copilot-instructions.md, creates meta instruction files for writing instructions and agents, and explores plan mode for iterating on agent designs.","date_published":"2025-11-27T00:00:00Z","id":"https://chrisreddington.com/video/2025-11-27-rubber-duck-thursdays/","tags":["GitHub Copilot","Agentic AI","Context Engineering","Model Context Protocol","Visual Studio Code","Developer Experience","TypeScript","Prompt Engineering"],"title":"Rubber Duck Thursdays - Let's build with custom agents","url":"https://chrisreddington.com/video/2025-11-27-rubber-duck-thursdays/"},{"content_text":"Chris catches up on several weeks of GitHub releases, including new models including GPT-5.1, GPT-5.1 Codex, and GPT-5.1 Codex Mini, MCP registry controls, and isolated sub-agents. He then returns to the turn-based game MCP server project, using Copilot's agent mode to diagnose and fix a dependency upgrade failure.","date_published":"2025-11-20T00:00:00Z","id":"https://chrisreddington.com/video/2025-11-20-rubber-duck-thursdays/","tags":["GitHub Copilot","GitHub Actions","Model Context Protocol","Context Engineering","Developer Experience","Visual Studio Code","Agentic AI","DevOps","TypeScript"],"title":"Rubber Duck Thursdays - Let's build","url":"https://chrisreddington.com/video/2025-11-20-rubber-duck-thursdays/"},{"content_text":"I've been exploring ways to bring social engagement into my blog posts. Taking inspiration from Ashley Willis' implementation, I've integrated Bluesky comments and likes into my Hugo site using the AT Protocol's public API.","date_published":"2025-11-18T00:00:00Z","id":"https://chrisreddington.com/blog/bluesky-comments-integration/","tags":["Hugo","Static Sites"],"title":"Adding Bluesky Comments to My Hugo Site","url":"https://chrisreddington.com/blog/bluesky-comments-integration/"},{"content_text":"In this live stream, we explore building a 3D tic-tac-toe visualization using Three.js and Copilot coding agent, demo MCP elicitation for gathering game preferences, and discuss the importance of context engineering when working with AI tools. We also cover GitHub changelog highlights including path-scoped custom instructions for Copilot code review and agents.md support.","date_published":"2025-09-04T00:00:00Z","id":"https://chrisreddington.com/video/2025-09-04-rubber-duck-thursdays/","tags":["GitHub Copilot","Model Context Protocol","Agentic AI","AI","Context Engineering","GitHub Actions","JavaScript","Developer Experience","Open Source","Community"],"title":"Rubber Duck Thursdays - Time to build!","url":"https://chrisreddington.com/video/2025-09-04-rubber-duck-thursdays/"},{"content_text":"Explore how MCP elicitation transforms AI tool interactions by gathering missing information upfront.","date_published":"2025-09-04T00:00:00Z","id":"https://github.blog/ai-and-ml/github-copilot/building-smarter-interactions-with-mcp-elicitation-from-clunky-tool-calls-to-seamless-user-experiences/","tags":["AI","GitHub Copilot","Model Context Protocol","TypeScript"],"title":"Building smarter interactions with MCP elicitation: From clunky tool calls to seamless user experiences","url":"https://github.blog/ai-and-ml/github-copilot/building-smarter-interactions-with-mcp-elicitation-from-clunky-tool-calls-to-seamless-user-experiences/"},{"content_text":"In this live stream, we recap the MCP server elicitation feature and then dive into GitHub Actions fundamentals — building workflows from scratch, covering triggers, jobs, dependencies with needs, matrix builds for cross-platform testing, and workflow_dispatch for manual runs. We also walk through a packed GitHub changelog covering ARM64 runners, GPT-5 in GitHub Models, immutable releases, and GitHub MCP server secret scanning.","date_published":"2025-08-28T00:00:00Z","id":"https://chrisreddington.com/video/2025-08-28-rubber-duck-thursdays/","tags":["GitHub Actions","CI/CD","DevOps","GitHub Copilot","Model Context Protocol","AI","GitHub","Developer Experience","Open Source","Community"],"title":"Rubber Duck Thursdays - Let's keep building!","url":"https://chrisreddington.com/video/2025-08-28-rubber-duck-thursdays/"},{"content_text":"Learn Model Context Protocol by building a turn-based game server that shows how to extend GitHub Copilot with custom tools, resources, and prompts.","date_published":"2025-08-22T00:00:00Z","id":"https://github.blog/ai-and-ml/github-copilot/building-your-first-mcp-server-how-to-extend-ai-tools-with-custom-capabilities/","tags":["AI","GitHub Copilot","Model Context Protocol","TypeScript","Developer Experience"],"title":"Building your first MCP server: How to extend AI tools with custom capabilities","url":"https://github.blog/ai-and-ml/github-copilot/building-your-first-mcp-server-how-to-extend-ai-tools-with-custom-capabilities/"},{"content_text":"In this live stream, we continue building a turn-based game MCP server, implementing MCP elicitation to gather user preferences and consolidating duplicate tool calls into cleaner abstractions. We also recap the latest GitHub changelog including npm trusted publishing with OIDC, Claude Opus 4.1, and Copilot coding agent updates.","date_published":"2025-08-07T00:00:00Z","id":"https://chrisreddington.com/video/2025-08-07-rubber-duck-thursdays/","tags":["Model Context Protocol","GitHub Copilot","Agentic AI","AI","GitHub Actions","TypeScript","Open Source","DevOps","GitHub","Community"],"title":"Rubber Duck Thursdays - Building a turn-based-game MCP server","url":"https://chrisreddington.com/video/2025-08-07-rubber-duck-thursdays/"},{"content_text":"GitHub Copilot coding agent can help burn down your backlog, kickstart new projects, and refactor legacy codebases. This video walks through the major upgrades shipped in June: Copilot Business and Copilot Pro access to the agent, viewing recent coding agent sessions from the agents page, Playwright MCP by default for validating and screenshotting UI changes, and support for remote MCP servers.","date_published":"2025-07-25T00:00:00Z","id":"https://chrisreddington.com/video/2025-07-25-copilot-coding-agent-updates/","tags":["GitHub Copilot","Agentic AI","GitHub","Model Context Protocol","Developer Experience"],"title":"What's new with the GitHub Copilot coding agent: A look at the updates","url":"https://chrisreddington.com/video/2025-07-25-copilot-coding-agent-updates/"},{"content_text":"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.","date_published":"2025-07-24T00:00:00Z","id":"https://chrisreddington.com/video/2025-07-24-rubber-duck-thursdays/","tags":["GitHub Copilot","Agentic AI","Model Context Protocol","TypeScript","Developer Experience","GitHub Actions","Open Source","Community","Context Engineering"],"title":"Rubber Duck Thursdays - Build for the love of code","url":"https://chrisreddington.com/video/2025-07-24-rubber-duck-thursdays/"},{"content_text":"Explore how I use agentic tools like GitHub Copilot agent mode and the Playwright MCP server to accelerate troubleshooting and debugging of UI issues, while revisiting the importance of clear requirements.","date_published":"2025-07-22T00:00:00Z","id":"https://github.blog/ai-and-ml/github-copilot/debugging-ui-with-ai-github-copilot-agent-mode-meets-mcp-servers/","tags":["Agentic AI","GitHub Copilot","Model Context Protocol"],"title":"Debugging UI with AI: GitHub Copilot agent mode meets MCP servers","url":"https://github.blog/ai-and-ml/github-copilot/debugging-ui-with-ai-github-copilot-agent-mode-meets-mcp-servers/"},{"content_text":"Explore how you can set Copilot coding agent up for success with custom instruction and Copilot setup steps.","date_published":"2025-07-15T00:00:00Z","id":"https://github.blog/ai-and-ml/github-copilot/from-chaos-to-clarity-using-github-copilot-agents-to-improve-developer-workflows/","tags":["Agentic AI","GitHub Copilot","GitHub","Context Engineering"],"title":"From chaos to clarity: Using GitHub Copilot agents to improve developer workflows","url":"https://github.blog/ai-and-ml/github-copilot/from-chaos-to-clarity-using-github-copilot-agents-to-improve-developer-workflows/"},{"content_text":"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.","date_published":"2025-07-10T00:00:00Z","id":"https://chrisreddington.com/video/2025-07-10-rubber-duck-thursdays/","tags":["GitHub Copilot","Agentic AI","Model Context Protocol","Visual Studio Code","Developer Experience","Testing","GitHub Actions","JavaScript"],"title":"Rubber Duck Thursdays - Copilot agent mode, coding agent and MCP servers","url":"https://chrisreddington.com/video/2025-07-10-rubber-duck-thursdays/"},{"content_text":"In this stream, Chris catches up on several weeks of GitHub updates including the remote MCP server preview and Copilot coding agent for business users. The live coding session demonstrates adding internationalization to the Copilot Airways app using Copilot coding agent, custom VS Code chat modes for planning, and agent mode in Xcode for iOS development.","date_published":"2025-07-03T00:00:00Z","id":"https://chrisreddington.com/video/2025-07-03-rubber-duck-thursdays/","tags":["GitHub Copilot","Agentic AI","AI","Model Context Protocol","Visual Studio Code","GitHub Actions","Context Engineering","DevSecOps","Developer Experience","Open Source"],"title":"Rubber Duck Thursdays - Let's build","url":"https://chrisreddington.com/video/2025-07-03-rubber-duck-thursdays/"},{"content_text":"A practical guide to GitHub Copilot’s agentic coding agent, chat modes, and remote MCP server so you turn issues into tested PRs with clear steps (and no hype).","date_published":"2025-07-01T00:00:00Z","id":"https://github.blog/ai-and-ml/github-copilot/from-idea-to-pr-a-guide-to-github-copilots-agentic-workflows/","tags":["GitHub","GitHub Copilot","AI","Agentic AI","Model Context Protocol"],"title":"From idea to PR: A guide to GitHub Copilot’s agentic workflows","url":"https://github.blog/ai-and-ml/github-copilot/from-idea-to-pr-a-guide-to-github-copilots-agentic-workflows/"},{"content_text":"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.","date_published":"2025-06-19T00:00:00Z","id":"https://chrisreddington.com/video/2025-06-19-rubber-duck-thursdays/","tags":["GitHub Copilot","Agentic AI","GitHub Actions","Model Context Protocol","Context Engineering","Developer Experience","Testing","Open Source"],"title":"Rubber Duck Thursdays - Let's build with agents","url":"https://chrisreddington.com/video/2025-06-19-rubber-duck-thursdays/"},{"content_text":"In this stream, Chris recaps announcements from Microsoft Build, reviews three weeks of GitHub changelog updates, and does a deep dive into Copilot coding agent using the Copilot Airways demo app. Topics include assigning issues to Copilot, reviewing AI-generated pull requests, MCP integration with Notion, and best practices for writing well-scoped GitHub issues.","date_published":"2025-06-05T00:00:00Z","id":"https://chrisreddington.com/video/2025-06-05-rubber-duck-thursdays/","tags":["GitHub Copilot","Agentic AI","AI","Model Context Protocol","GitHub Actions","Visual Studio Code","Developer Experience","Community"],"title":"Rubber Duck Thursdays - Copilot coding agent and Copilot agent mode","url":"https://chrisreddington.com/video/2025-06-05-rubber-duck-thursdays/"},{"content_text":"This video shows how to create a GitHub Issue directly from Copilot Chat on GitHub.com and immediately assign it to the Copilot coding agent. The core focus is Model Context Protocol (MCP): how the Notion MCP server is configured to give Copilot access to a product requirements document stored in Notion, enabling it to implement a user reviews feature for the 'Copilot Airways' travel guide with full traceability back to the source document. The video also covers how MCP servers are provisioned inside GitHub Actions and how to use Copilot's PR change summary to navigate large code reviews.","date_published":"2025-06-01T00:00:00Z","id":"https://chrisreddington.com/video/2025-06-01-copilot-coding-agent-mcp/","tags":["GitHub Copilot","Agentic AI","Model Context Protocol","GitHub","GitHub Actions","Integration","Developer Experience"],"title":"Extend GitHub Copilot coding agent with custom MCP tools","url":"https://chrisreddington.com/video/2025-06-01-copilot-coding-agent-mcp/"},{"content_text":"The GitHub Copilot coding agent works from anywhere—including your phone. This video demonstrates assigning a GitHub Issue to Copilot directly from the GitHub Mobile app, targeting a GitHub Pages deployment task for the 'Copilot Airways' CI workflow. It then shows how to monitor Copilot's progress, view the session log, and review and approve the resulting pull request entirely from a mobile browser, including the 'Approve and Run' gate that protects GitHub Actions execution.","date_published":"2025-05-27T00:00:00Z","id":"https://chrisreddington.com/video/2025-05-27-copilot-coding-agent-mobile/","tags":["GitHub Copilot","Agentic AI","GitHub","GitHub Actions","CI/CD","DevOps","Developer Experience"],"title":"Assign issues to GitHub Copilot from the GitHub mobile app","url":"https://chrisreddington.com/video/2025-05-27-copilot-coding-agent-mobile/"}],"language":"en-GB","title":"Chris Reddington","version":"https://jsonfeed.org/version/1.1"}