Interesting update from GitHub! Now that Copilot code review user counts are aggregated in the usage metrics API, dev managers will have a much clearer picture of its adoption for reviews. This is great for understanding real-world impact beyond general usage. More data, more insights! 📊 #GitHubCopilot #DevTools

🎬 GitHub Copilot CLI Multi-AI Integration: Second Opinion Feature Explained GitHub Copilot CLI introduces multi-AI model integration, allowing developers to get diverse code suggestions from different AI families for more robust development workflows. ▶️ Watch the full breakdown: https://is.gd/EyIr5K

For the last few months I have been developing a spec-driven framework to build with AI coding agents using Github Copilot for the whole SDLC. One of the resources I suggest, if you are starting to explore this approach, is the "Scale institutional knowledge using Copilot Spaces". I just completed this GitHub Skills hands-on exercise. Highly recommended. https://lnkd.in/gsjWY9S5 #GitHubSkills #OpenSource #GitHubLearn

Want tips on using GitHub Copilot CLI ? I built a "Tip of the Day" for GitHub Copilot CLI — powered by /chronicle, it learns from how I actually use it 🚀 I use Copilot CLI daily for team investigations, GitHub searches, and workplace lookups. But I kept forgetting about features that would save me time. So I automated it. Now every morning, a personalized tip appears in my terminal — generated by Copilot's /chronicle command, based on my real session history. Here's how it works: - 🔍 /chronicle analyzes my past Copilot sessions — what tools I used, what I asked, what patterns I follow - 🎯 It generates a tip tailored to my workflow — features I haven't tried, better ways to do things I already do - 🔄 A zsh precmd hook displays the tip the first time I interact with any terminal each day — even ones left open overnight - ⏰ A macOS LaunchAgent pre-generates the tip at 7am so it's instant The whole setup is just two files: 1. daily-tip.sh — the zsh hook that calls /chronicle and caches the result 2. A LaunchAgent plist for pre-generation (optional) Add one line to your ~/.zshrc: [[ -f "$HOME/.copilot/daily-tip.sh" ]] && source "$HOME/.copilot/daily-tip.sh" That's it. No Python scripts, no static tip lists, no maintenance. /chronicle does the heavy lifting — it knows your history and gets smarter as your usage evolves. Grab the code: https://lnkd.in/e7CM4Wjz I built all of this using Copilot CLI itself. 😎 #GitHubCopilot #CopilotCLI #DeveloperProductivity #AI #DevTools

One prompt → a whole analyst team (inside Copilot CLI) One prompt. Three clarifying questions. A full multi-agent market analysis workflow. This breakdown shows how “AnalystCouncil” was created inside GitHub Copilot CLI—without hand-writing orchestration code, deploying APIs, or authoring YAML. What’s worth clicking for: 🤖 How a natural-language requirements doc turned into structured agent configs (as markdown instruction files) 🧩 What the generated “platform” actually included: specialized agents, workflows, conventions, personality definitions, orchestration spec ⚠️ The reality check: “working” still needed human edits + token burn adds up 📝 The exact initial prompt that shaped the entire system (and why prompt quality became the main lever) If building agentic workflows feels fuzzy, this is a concrete, step-by-step example of going from idea → runnable skeleton in a real tool. What would be most valuable in an “agent council” for product launches: competitor intel, positioning, pricing, or messaging? Thank you Bogdan Crivat https://lnkd.in/dNzSvmJb #GitHubCopilot #AIagents #PromptEngineering #MarketResearch #ProductStrategy

Been using GitHub Copilot (agent mode) for automation - feature files, step defs, page objects… all of it. And wow… this thing has confidence. 😂 Give it a vague BRD? It will happily invent logic like it’s part of the requirements. Generic prompt? You’ll get generic nonsense back. Lesson learned real quick: You don’t “use” Copilot - you manage it. That said… Debugging is ridiculously fast now. And yes, it sometimes generates code so complex I just stare at it… but hey, it works 🤷♀️ Big takeaway: Copilot is basically that overconfident teammate who moves fast, breaks things, but somehow still gets the job done - if you guide it well. Anyone else seeing this? Or is it just me fighting my AI coworker daily? #AIinQA #GitHubCopilot #SoftwareTesting #AutomationTesting #AIinTech #ShiftLeft #FutureOfWork

5 months ago I sat down with Scott Durow🌈 and Rami Mounla after Power Platform Community Conference to record where coding agents were heading. Rewatched it this week. Holds up better than most of what we were all saying back then. Governance muscle from the low-code years carries over. Who gets access. Which tools they can call. AuthZ/AuthN. How it gets reviewed when it goes to prod. One citizen dev with a coding agent just creates a lot more code in one run. The AI harnesses matured. Most of the practical progress went into instrumentation around the context window. Auto-compaction, handling context rot, steering through progressive tool descriptions. Copilot CLI made big jumps on that front. Primitives underneath are becoming standards - agent definitions, skills, hooks, MCP tools. What changed is how well the harness manages the window around all of that. My own opinion shifted too. In autumn the results were mostly there but I wasn't confident about it yet and I was saying so. Now it's not a question for me whether we go this way. Only who, how fast and how well. Coding agents run end-to-end through #UDPP26 next week. Scott opens with GitHub Copilot CLI tips for people who haven't started yet. We'll walk through the new CLI tools and skills Microsoft just released and where they fit with Power Platform. Then the full build lifecycle with agents. 🦸Diana Birkelbach on frontend. Jonas Rapp on backend. Matěj Samler on whole Power Platform solutions end-to-end. Raphael POTHIN on securing what those agents produce. Julie Koťátková on agents running UI tests against the result. Rami Mounla closes with the authoring and review workflow that keeps control of what actually ships. Governance track runs in parallel. Jan Hajek and Sabin Nair on Entra Agent ID and MCP in the tenant. Jukka Niiranen on inventory and cost. Marcel Ferreira and Casey Burke on ALM. 📅 April 27-28, Livestream + Q&A + recordings on demand + on-site if you're close #PowerApps #PowerPlatform #GitHubCopilot #GitHubCopilotCLI #CopilotStudio #Governance #ProDev #Dataverse

Summarize 0.13 Adds Local Video Slide Support and Expands Model Backend Integration 📌 Summarize 0.13 transforms media handling with local video slide support, letting developers process files directly-no uploads needed. It now powers through GitHub Copilot and OpenClaw models via intuitive flags, turning summarization into a unified, flexible workflow. Perfect for teams needing fast, reliable media analysis without friction. 🔗 Read more: https://lnkd.in/d6-4BPSy #Summarizecli #Githubcopilot #Openclaw #Videoslide #Modelbackend

Copilot usage metrics just got more honest (CLI included) 🚨 Copilot dashboards been undercounting usage? GitHub just integrated Copilot CLI activity into the main Copilot usage metrics—so top-level totals and feature breakdowns finally reflect IDE + CLI combined. ✅ What changes: • Top-level totals now include CLI (activity counts + LOC added/deleted) • CLI shows up in breakdowns as feature=copilot_cli • totals_by_ide stays IDE-only • Existing totals_by_cli section still remains 🎯 Why click: If reporting, thresholds, or adoption dashboards rely on “IDE-only” assumptions, numbers will jump—this update explains exactly what to adjust (and where CLI now appears). 📌 Admins: this makes it easier to compare CLI vs other Copilot capabilities—without manual stitching. https://lnkd.in/ePRUnmj5 #GitHub #Copilot #DevOps #Analytics #CLITools

One of my favorite things about GitHub Copilot right now: you can switch models mid-session. Claude Opus 4.7 just went GA in Copilot. I've been using it for a few days and the thing that stands out isn't the benchmark numbers (87.6% on SWE-bench, sure, impressive). It's that it checks its own work before telling you it's done. I had it refactor a multi-file MAUI handler last week. With the previous model, I'd get the refactor but then find one file was left inconsistent. Opus 4.7 caught that itself and fixed it before presenting the result. The multi-step reliability is where this shines. For single-file edits, you probably won't notice a huge difference. But for agentic workflows where the model needs to plan, execute across files, and verify? Night and day. Some practical things worth knowing: → Available in VS Code, VS, Copilot CLI, and GitHub.com → Each request counts as 7.5x premium (promotional rate until April 30) → Pro+ and Business/Enterprise only (removed from Pro as of April 20) My workflow now: Sonnet for quick edits and exploration, Opus when the task is complex or touches multiple files. You burn through fewer tokens on the routine stuff and save the heavy model for where it actually matters. What's your model switching strategy? Do you stick with one or mix them based on the task? #GitHubCopilot #AI