GitHub Next

@githubnext
125 Followers
1 Following
18 Posts
We are a team of researchers and engineers at #GitHub who investigate the future of software development.
Webhttps://githubnext.com
GitHubhttps://github.com/githubnext
Discordhttps://gh.io/next-discord
Show threadGitHub NextFeb 14

Coda: You can get value out of this in five minutes, but getting maximum value requires a behavioral shift.

This tool can do many things. It's easy to use, but harder to realize/internalize that you can apply it to problems you wouldn't have before.

Much like Steve Yegge's 8 levels of AI adoption, the superusers of Agentic Workflows are not just doing the same work as before, they're moving the conventions around what is automatable.

It's wild to see this firsthand inside our team. ❤️

Show threadGitHub NextFeb 14

And we're particularly excited about using this to help open-source maintainers. When we showed this to @frenck (the maintainer of Home Assistant), he wrote a workflow that reads the traces for bugs and figures out if they originate in the HA codebase or not.

True noise elimination for OSS.

Show threadGitHub NextFeb 14

We're seeing teams at GitHub use it for building tooling and workflows for themselves.

We're seeing developer-adjacent personas at GitHub using agentic workflows to help them move information around.

Software is a team sport and this helps everyone on the team, not just the engineers.

Show threadGitHub NextFeb 14

You can check out a zillion examples in our docs site: https://gh.io/aw-tp-mastodon

It can be for easy things like "triage my issues" and it can be for hard things like "find ways to optimize my code".

If it's a task you'd express in English to an engineer, it might be a good agentic workflow!

GitHub Agentic Workflows

Automated repository agents running in GitHub Actions.

GitHub Agentic Workflows
Show threadGitHub NextFeb 14
Core to the behavior of Agentic Workflows is the notion of safe outputs. The body of a workflow is markdown, but the frontmatter is where you explicitly define what the agent can read and write, and those are enforced outside of the agentic run.
GitHub NextFeb 14

We're super jazzed to be launching GitHub Agentic Workflows into technical preview today!

"Generative AI" kind of fooled us into thinking that AI is synchronous, but async AI can have so much more value for us as developers.

Heuristics can only take you so far in automation. There's no linter in existence that can tell you if your code and documentation have drifted out of sync.

Agentic Workflows make it stupidly simple to express a task you want to delegate, forever.

https://github.blog/ai-and-ml/automate-repository-tasks-with-github-agentic-workflows/

Automate repository tasks with GitHub Agentic Workflows  

Build automations using coding agents in GitHub Actions to handle triage, documentation, code quality, and more.

The GitHub Blog
Show threadGitHub NextAug 15, 2025
6/ 💬 Join the conversation in the Continuous AI channel on the GitHub Next Discord: gh.io/next-discord
Show threadGitHub NextAug 15, 2025

5/ 🔍 This is a research demonstrator, not a product or even a prototype. We’re learning in the open. Help us figure out what works, what’s safe, and what’s reusable!

Examples: github.com/githubnext/agentics

Show threadGitHub NextAug 15, 2025
4/ ✨ Key ideas:
• GitHub-native, Actions-first
• Engine-neutral (swap LLMs without rewriting)
• Shareable workflow pieces
• Strong guardrails + auditable execution
Show threadGitHub NextAug 15, 2025

3/❓Why?

Some tasks are perfect for natural language:
• Continuous documentation updates
• Issue triage
• Accessibility reviews
• Test improvements
• Continuous QA

All repetitive, collaborative, and needing a bit of judgment.