GitHub Spec Kit integrates with Copilot CLI for developer workflows

Unlocking a new level of productivity... or extreme context switching 😅. In my role, I wear many hats: managing GitHub, Atlassian to name a few, keeping up with our Cloud and FinOps, and driving AI initiatives. Today, I’m experimenting with Agentic Coding, not just to test tools, but to build an AI flow, hopefully for our teams. This is how it works... I describe a task to an AI agent, then jump to helping someone set up GitHub Copilot in VSCode, or checking AWS EC2 attestation updates, jump back to review the code and repeat. Is this ideal? Probably not. But is it possible? Absolutely!! Tasks that would normally demand prolonged focus, I can now make progress. Context switching usually kills focus—but maybe, just maybe, AI can change this. #Productivity #AI #AIAssistedCoding #CloudTech #FinOps #GitHub #Automation #TechExperimentation #ContextSwitching

👨💻 Anthropic's Claude Code: Coding in the Cloud 🔧 Tried Claude Code for a quick prototyping session and the cloud-based workflow is surprisingly smooth. Real-time progress tracking and secure sandboxes make it feel like pair programming with an AI that actually understands context. The mobile access is a game-changer for quick fixes. This could fundamentally change how we approach development environments. Who else has tested it? #ClaudeCode #CloudDevelopment

Seqera MCP is live. Debugging the pipelines that run on your cloud with your preferred agent is finally a reality. We support Claude, Claude Code, Cursor, and VS Code Copilot at launch! This means you can now: - Debug your Nextflow pipelines directly from your favorite AI coding assistant - Access Seqera Platform data without leaving your IDE - Have AI analyze failed runs with full compute environment context - Let your preferred agent understand your entire pipeline infrastructure The Model Control Protocol (MCP) brings Seqera's pipeline intelligence to where you already work. Your workflows. Your tools. Now connected. Connect here: https://seqera.io/mcp/ Read about it here: https://lnkd.in/e8-Mr4xx

Serverless MCP Agent with LangChain.js v1 — Burgers, Tools, and Traces 🍔. AI agents that can actually do stuff (not just chat) are the fun part nowadays, but wiring them cleanly into real APIs, keeping things observable, and shipping them to the cloud can get... messy. So we built a fresh end‑to‑end sample to show how to do it right with the brand new LangChain.js v1 and Model Context Protocol (MCP). In case you missed it, MCP is a recent open standard that makes it easy for LLM agents to consume tools and APIs, and LangChain.js, a great framework for building GenAI apps and agents, has first-class support for it. This new sample gives you: A LangChain.js v1 agent that streams its result, along reasoning + tool steps An MCP server exposing real tools (burger menu + ordering) from a business API A web interface with authentication, sessions history, and a debug panel (for developers) A production-ready multi-service... #techcommunity #azure #microsoft https://lnkd.in/gQJ6kw_f

Serverless MCP Agent with LangChain.js v1 — Burgers, Tools, and Traces 🍔 AI agents that can actually do stuff (not just chat) are the fun part nowadays, but wiring them cleanly into real APIs, keeping things observable, and shipping them to the cloud can get... messy. So we built a fresh end‑to‑end sample to show how to do it right with the brand new LangChain.js v1 and Model Context Protocol (MCP). In case you missed it, MCP is a recent open standard that makes it easy for LLM agents to consume tools and APIs, and LangChain.js, a great framework for building GenAI apps and agents, has first-class support for it. This new sample gives you: A LangChain.js v1 agent that streams its result, along reasoning + tool steps An MCP server exposing real tools (burger menu + ordering) from a business API A web interface with authentication, sessions history, and a debug panel (for developers) A production-ready multi-service architecture Serverless deployment on Azure in one command (azd up) Yes, it’s a burger ordering system. Who doesn't like burgers? Grab your favo https://lnkd.in/ggjfSCUd

Serverless MCP Agent with LangChain.js v1 — Burgers, Tools, and Traces 🍔 AI agents that can actually do stuff (not just chat) are the fun part nowadays, but wiring them cleanly into real APIs, keeping things observable, and shipping them to the cloud can get... messy. So we built a fresh end‑to‑end sample to show how to do it right with the brand new LangChain.js v1 and Model Context Protocol (MCP). In case you missed it, MCP is a recent open standard that makes it easy for LLM agents to consume tools and APIs, and LangChain.js, a great framework for building GenAI apps and agents, has first-class support for it. This new sample gives you: A LangChain.js v1 agent that streams its result, along reasoning + tool steps An MCP server exposing real tools (burger menu + ordering) from a business API A web interface with authentication, sessions history, and a debug panel (for developers) A production-ready multi-service architecture Serverless deployment on Azure in one command (azd up) Yes, it’s a burger ordering system. Who doesn't like burgers? Grab your favo https://lnkd.in/ggjfSCUd

🚀 GitHub named a Leader in the Gartner® Magic Quadrant™ for AI Code Assistants - for the second year in a row! As AI transforms software development, GitHub continues to lead the way by embedding Copilot into everyday workflows, enabling Agent Mode, and centralizing development on GitHub Enterprise Cloud. 📊 Gartner predicts that by 2028, 90% of enterprise software engineers will use AI code assistants - up from just 14% in early 2024. GitHub’s strategy is helping teams move faster, stay secure, and scale AI adoption with confidence. This recognition reflects the strength of that vision. 🔗 Read more here : https://lnkd.in/etmwAzNR #AI #GitHubCopilot #SoftwareDevelopment #GartnerMQ #AIEngineering #GitHub #TechLeadership #Innovation

Three months ago, we launched Leap and since then, you've built 50,000+ apps and saved over $100M in development costs. Every line of code, every piece of infrastructure—yours. Today we're launching Leap 2.0. Most AI coding tools work fine for small demos. But as your project grows, they break down. More mistakes, slower, way more expensive. Leap 2.0 handles projects 10X bigger than before. 90% cheaper at scale. It's powered by Claude 4.5, browses the web, reads docs, auto-builds and fixes errors, generates images, and deploys to your own AWS/GCP. Other AI builders lock you into their platforms, costs explode as you grow and you lose control. With Leap, you deploy to your own cloud. You own everything. Production-ready. This is day 1 of Launch Week. 4 more launches coming.

AI and "vibe" programming promise to eliminate the drudgery and grunt work from your usual coding routines. But what if you had a language where you could get your work done without drudgery and grunt work in the first place?? Don't treat symptoms, treat problems. Unison Computing

concept pages dropped → https://lnkd.in/dJUFe8EQ git solved collaboration for code. ai still runs on hope and undo. what if every ai action was a commit? (versioned, explainable, reversible) we built legit -> git for ai collaboration. today we’re dropping the concept pages: 01 - git as the missing control layer 02 - a filesystem as a universal API 03 - dogfood example (chat app) 04 - flipping the model (browser sync, no cloud) #git #ai #localfirst #buildinpublic