Announced Oct 28, Foundry Agent Service can now run your agent on the same managed loop and sandbox as GitHub's Copilot products, with skills, MCP tools and 20+ models; you pick it at agent creation and can't switch later. Runtime is free until Dec 1, then $0.0994 per vCPU-hour plus model costs, and the GitHub Copilot SDK is being renamed Microsoft Copilot SDK (changelog).
Announced at Universe on Oct 28, you describe tasks like issue triage, CI failure analysis or test writing in a Markdown file, and gh aw compiles it to standard Actions YAML powered by Copilot or your own coding agent, running read only by default in a sandboxed container with a threat detection job checking proposed changes. GA adds self hosted ARC runners, per workflow model choice and routing, micro VM isolation, and gh aw forecast for estimating AI credit spend…
Announced at Universe on Oct 28, Fusion replaces Auto in the model picker and decides per prompt whether one model answers, a cheap model drafts and escalates, or one model critiques another; Fusion Max scored within two points of Claude Code on Opus 5.5 Max on Artificial Analysis's coding index at about half the cost per task. It's on all plans in VS Code, the Copilot app, CLI and JetBrains, billed per model used, with 30% off for a limited time…
Announced at Universe on Oct 28, Memory now carries your preferences and repo conventions across the Copilot app, CLI, VS Code, cloud agent and code review. Dreaming, in public preview and billed in AI credits, reflects on past sessions to update memories and opens pull requests to improve checked in skills and instruction files…
Announced at Universe on Oct 28, Copilot Projects let you give the app a goal plus context like repos, Figma mocks or Slack threads, and it runs as many background agents as needed, returning PRs for review. Computer use, in public preview on macOS and Windows, lets Copilot click and type in desktop apps with no API after you approve it (Settings Computer Use)…
In beta since Oct 27, your agent runs on Akamai Functions via the Spin SDK, and the JavaScript or Python it writes runs in a second, tighter Wasm sandbox with limits on compute, memory and network; the tech preview suits short steps of about a minute. Akamai also opened a beta of Akamai Inference, OpenAI compatible serverless or dedicated hosting for 12 open weight models including gpt oss 120b and Gemma 4…
Spotted something we missed? Start a thread.