Topic
GitHub
8 episodes
-
Better tools made Copilot code review worse. Here's how we actually improved it.
Pippa and Tyler dig into GitHub’s post on why giving Copilot code review better tools actually regressed its performance—and how rewriting tool instructions for a reviewer’s workflow flipped the regression into a 20% cost win without losing review quality.
-
Q1 2026 Innovation Graph update: Open source collaboration is accelerating worldwide
Vince and Ava dig into GitHub's Q1 2026 Innovation Graph update, arguing that the real story isn't just open source growth but cross-border collaboration speeding up fast enough to change maintainer burden and platform product choices.
-
How we built an internal data analytics agent
Qubot, GitHub's internal Copilot-powered analytics agent, lets any employee query the data warehouse in plain language. Cody digs into the architecture (federated context layer, MCP servers for Kusto and Trino, offline eval framework) and lands on the real bottleneck: curation—keeping documentation current so the agent doesn't hallucinate. Justy sees the workflow win (Slack iteration vs. Jira wait) but flags the caveat: this only works for exploratory questions, not high-stakes decisions. Both agree the eval loop is what separates a demo from a production system.
-
Figma Make's new two way GitHub integration turns designs into live, production code — with built In governance
Justy and Cody dig into Figma Make’s new two-way GitHub integration and the bigger claim behind it: not that designers replace engineers, but that visual editing can finally sit inside a real software workflow without breaking governance. They unpack what the article actually shows, where the technical case is solid, and who this is genuinely useful for.
-
One Developer, Two Dozen Agents, Zero Alignment
Ace is a GitHub Next prototype that treats coding with agents as a shared workspace instead of a solo tool. The skepticism is whether teams really want another surface for coordination, even if the architecture is clever.
-
Agent Skills vs MCP
The discussion centers on the relationship between Skills and MCP (Multi-Channel Protocol) in AI development, emphasizing how they complement rather than replace each other. Host A and Host B explore the implications of this synergy, the role of institution knowledge, and how this understanding can improve AI functionality in real-world applications.
-
GitHub Pguso/rag From scratch: Demystify RAG by building it from scratch. Local LLMs, no black boxes Real understanding of embeddings, vector search, retrieval, and context Augmented generation.
RAG from Scratch Demystify Retrieval-Augmented Generation (RAG) by building it yourself - step by step. No black boxes.
-
Configure MCP server access for your organization or enterprise GitHub Docs
GitHub Copilot / How-tos / Administer Copilot / Manage MCP usage / Configure MCP server access Configure MCP server access for your organization or enterprise You can configure an MCP registry URL and access control policy to determine which MCP servers developers can discover and use in supported IDEs with GitHub Copilot. Who can use this feature?