Agents

Stop hand-tuning kernels: How Neuron Agentic Development accelerates AWS Trainium optimizations

Today, we’re announcing the Neuron Agentic Development capabilities: a collection of AI agents and skills that make this possible for developers building on AWS…

Elevating the customer experience: IKEA’s agentic AI journey

The Swedish home-furnishing giant’s chief digital officer discusses the need to prioritize AI initiatives amid ‘the risk of doing everything but maybe nothing.’…

Evaluate AI agents systematically with Agent-EvalKit

Agent-EvalKit is an open-source toolkit (Apache 2.0) that makes this evaluation infrastructure available by integrating with AI coding assistants, including Cla…

Double click: Human takes on agentic AI

Introducing our MCP server: Bringing Figma into your workflow

Double click: What does MCP mean for agentic AI?

Design systems and AI: Why MCP servers are the unlock

Announcing Replicate's remote MCP server

Use our MCP to discover, compare, and run models from apps like Claude, Cursor, and VS Code.…

Connect your AI to 1,000+ models with the fal MCP Server

Today we're launching the fal MCP Server — a hosted endpoint that lets any AI assistant search, run, and chain 1,000+ generative AI models…

Agents, meet the Figma canvas

The TL;DR on MCP: Why context matters and how to put it to work

FigJam is now your coding agent’s whiteboard too

How to design agentic tools for work

Workflow lab: Expanding the canvas with Figma MCP

Fix with Copilot for failing Actions now in Pro, Pro+, and Max

When a GitHub Actions job fails, Copilot Pro, Pro+, and Max subscribers can now ask Copilot cloud agent to fix it in one click. Click the Fix with Copilot butto…

GPT-5.2 and GPT-5.2-Codex deprecated

As of today, June 5, 2026, we have deprecated the following models across most GitHub Copilot experiences (including Copilot Chat, inline edits, ask and agent m…

Security validation for third-party coding agents

Security validation for third-party coding agents is now generally available. GitHub supports third-party coding agents (including Claude and OpenAI Codex) that…

Claude Fable 5 is generally available for GitHub Copilot

Claude Fable 5 from Anthropic is now available in GitHub Copilot, the first model in Anthropic’s Mythos class, designed for long-horizon, autonomous codin…

Copilot Chat now sees your agent sessions

We’ve improved the handoff experience between Copilot Chat and Copilot cloud agent on the web. We’ve also enabled new functionality which allows you…

Agentic workflows no longer need a personal access token

You can now use GitHub Agentic Workflows with GitHub Actions’s built-in GITHUB_TOKEN. This means that you no longer need to create and store a personal ac…

GitHub Agentic Workflows is now in public preview

GitHub Agentic Workflows is now in public preview. With agentic workflows, you can automate reasoning-based tasks like issue triage, CI failure analysis, and do…

Sensible Agent: A framework for unobtrusive interaction with proactive AR agents

Human-Computer Interaction and Visualization…

Import AI 441: My agents are working. Are yours?

Plus: Corrupting AI systems with a poison fountain…

Import AI 443: Into the mist: Moltbook, agent ecologies, and the internet in transition

Plus, a story about agents corrupting other agents…

Import AI 447: The AGI economy; testing AIs with generated games; and agent ecologies

What might a superintelligence arcology be like?…

Import AI 448: AI R&D; Bytedance's CUDA-writing agent; on-device satellite AI

If Ukraine is the first major drone war, when will there be the first major AI war?…

GPT 5.4 is a big step for Codex

On evaluating and understanding the frontier of agents, and why I still turn to Claude.…

Import AI 453: Breaking AI agents; MirrorCode; and ten views on gradual disempowerment

Was fire equivalent to a singularity for people at the time?…

SocialReasoning-Bench: Measuring whether AI agents act in users’ best interests

Using SocialReasoning Bench, we observed a stable pattern across models—agents execute competently, but fail to consistently improve the user’s position, even w…

MagenticLite, MagenticBrain, Fara1.5: An agentic experience optimized for small models

MagenticLite is an agentic system for small models that works across the browser and local file system in a single workflow. It combines specialized models and …