// Content

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.

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.

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.

Explore how MCP elicitation transforms AI tool interactions by gathering missing information upfront.

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.

Learn Model Context Protocol by building a turn-based game server that shows how to extend GitHub Copilot with custom tools, resources, and prompts.

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.

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.

Featured in Gründerszene/Business Insider Germany discussing my daily use of AI tools for productivity, focusing on the prompts I use to automate repetitive tasks.

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.