GitHub Agentic Workflows is generally available: automations written in plain Markdown

On 28 October 2026 GitHub made Agentic Workflows generally available: AI agents that triage issues, analyse CI failures and update docs, defined in Markdown and run inside GitHub Actions with read-only defaults.

On 28 October 2026 GitHub Next announced that GitHub Agentic Workflows is generally available, after a public preview we covered in September. It lets teams automate reasoning-heavy chores such as issue triage, CI failure analysis, documentation updates and test writing with coding agents running inside GitHub Actions.

How it works

Automations are written as natural-language Markdown files and compiled into standard Actions YAML. They run on your existing runners and policies, powered by GitHub Copilot or your own coding agent. The project is open source.

The safeguards GitHub lists

Agents run read-only by default, inside a sandboxed container behind a firewall. Outputs pass a “safe outputs” check, and a separate threat-detection job scans proposed changes before they are applied. Since preview, GitHub added support for self-hosted runners, stronger isolation for cross-repository work, per-workflow model choice, model routing by task difficulty, and a gh aw forecast command that estimates AI credit spend.

Availability

It is generally available on github.com for Free, Team and Enterprise. The default engine needs a Copilot licence.

What it means

The unit of AI development is moving from a developer’s chat window to background automation on the repository. That is where the productivity gain is, and also where an unreviewed agent can do the most damage, which is why the safeguards are the story as much as the feature.

So what

Before agents touch your codebase, decide what they may read, write and merge, and who signs off. Our AI-assisted development service sets those boundaries from day one. If you want it applied to your product, start a project.

← All research

More research.

GitHub secret scanning cuts false alarms for AWS, Google and Alibaba cloud keys and adds a SpaceX detector

GitHub's 5 November 2026 secret scanning update tightens detectors for AWS, Google Cloud and Alibaba keys, relevant to teams building software with AI coding tools that can paste credentials into code.

Read ›

GitHub's Copilot code review can now be managed by API, with review effort levels and AI credit costs shown

GitHub's 6 November 2026 update lets organisations manage Copilot code review by API and see the review effort and AI credits each AI code review used, a sign AI-assisted development is becoming auditable.

Read ›

GitHub's Copilot impact dashboard now counts chat and VS Code agent use, and drops the 'passive users' label

On 6 November 2026 GitHub added Copilot Chat and the VS Code Agents window to its Copilot impact dashboard, bringing it to nine tracked experiences, and renamed 'Passive users' to 'Chat-first users'.

Read ›

Claude Code 2.1.319: a setting that denies permission prompts so AI agent runs don't stall

Claude Code 2.1.319 (6 November 2026) adds a permissions.denyInsteadOfPrompting setting and moves long MCP tool calls to the background, a sign AI-assisted development is being built for unattended runs.

Read ›

GitHub now reports how often developers act on Copilot code review comments

On 5 November 2026 GitHub added code review metrics, including an addressed rate, to the Copilot usage metrics API. For AI software development buyers, it is the first first-party number for how much AI review feedback is acted on.

Read ›

Dependabot can now keep AI agent skills and prompts up to date

GitHub's Dependabot gained Agent Package Manager (APM) support on 3 November 2026, treating AI agent skills, prompts and instructions as dependencies that need updating like any other software.

Read ›

Start a project

Building with AI? Let's talk.

Tell us what you are building. We'll give you an honest view of the right approach.

Start a projectSee our work