What if AI-driven software development could be made more deterministic and reliable?
"Coro" explores an interesting approach to building AI-powered development workflows with a deterministic harness.
https://t.co/e0ray5ecgA
#AI#SoftwareEngineering#AIEngineering
We’ve received notice that the Department of Commerce has lifted export controls on Claude Fable 5 and Mythos 5.
We'll begin restoring access tomorrow, and will share an update soon.
We’re grateful to our users for their patience, and to everyone who worked with us on redeploying the models.
The 2026 Agentic Coding Trends Report: https://t.co/xKywhrlZiT
🔹 From coders to orchestrators
🔹 The human element is irreplaceable
🔹 Single agents are becoming teams
🔹 Coding is expanding to everyone
#SoftwareEngineering#AI#GenerativeAI#TechTrends
Stop building RAG pipelines from scratch. Foundry IQ is the agent-native knowledge layer behind your Foundry agents. Every source in one knowledge base - Work IQ, Fabric IQ, and now Web IQ. Serverless grounding, zero friction.
Available today. https://t.co/W4mwlWLvsZ
New course: Spec-Driven Development with Coding Agents, built in partnership with @jetbrains, and taught by @paulweveritt.
Vibe coding is fast, but often produces code that doesn't match what you asked for. This short course teaches you spec-driven development: write a detailed spec defining what to build, and work with your coding agent to implement it. Many of the best developers already build this way.
A spec lets you control large code changes with a few words, preserve context across agent sessions, and stay in control as your project grows in complexity.
Skills you'll gain:
- Write a detailed specification to define your mission, tech stack, and roadmap, giving your agent the context it needs from the start
- Plan, implement, and validate features in iterative loops using a spec as your agent's guide
- Apply the same repeatable workflow to both new and legacy codebases
- Package your workflow into a portable agent skill that works across agents and IDEs
Join and write specs that keep your coding agent on track!
https://t.co/hI4GwuvhtN
I believe it's important to hire engineers who closely follow academic articles and can transfer knowledge from academia to software industry practices.
Academia also needs to learn from industry practices to stay relevant.
The #EvoDev approach allows us to build large-scale, functional applications by using LLM agents to systematically map feature dependencies and iteratively propagate context.
#SoftwareEngineering#AI
https://t.co/kJRuTKh1KW
We just released 𝚛𝚎𝚊𝚌𝚝-𝚋𝚎𝚜𝚝-𝚙𝚛𝚊𝚌𝚝𝚒𝚌𝚎𝚜, a repo for coding agents.
React performance rules and evals to catch regressions, like accidental waterfalls and growing client bundles.
How we collected them and how to install the skill ↓
https://t.co/kfLSbKl15X
We hacked the AWS JavaScript SDK, a core library powering the entire @AWScloud ecosystem - including the AWS Console itself 🤯
How did we do it? Just two missing characters was all it took.
This is the story of #CodeBreach 🧵👇
Today we're open sourcing a technical preview of the GitHub Copilot CLI SDK. Build agents with custom tools in Go, Python, TypeScript, and C#.
Built on the same agent loop that powers the Copilot CLI and GitHub Coding Agent. Supports BYOK, and any model.
Here is the Copilot CLI driving Excel:
I wonder how AI will learn best practices for new tools, since people no longer share their experiences and insights on platforms such as Stack Overflow.