RESEARCH PROTOTYPE
GitHub Agentic Workflows
Write natural language workflows (AI-powered automation that can make decisions) that understand context, make decisions, and take meaningful actions across your repositories.
Key Features
Section titled “Key Features”Natural Language Workflows
Write automation in markdown instead of complex YAML
AI-Powered Decision Making
Workflows that understand context and adapt to situations
GitHub Integration
Deep integration with Actions, issues, PRs, discussions, and repository management
Safety First
Sandboxed execution with minimal permissions and safe output processing
Multiple AI Engines
Support for Claude, Codex, and custom AI processors
Continuous AI
Systematic, automated application of AI to software collaboration
Part of the Continuous AI Initiative
Learn more about systematic, automated application of AI to software collaboration in the GitHub Next Agentic Workflows blog post.
Workflow Examples
Section titled “Workflow Examples”ChatOps
commandInteractive automation triggered by slash commands like /review and /deploy
IssueOps
automatedAuto-triage and respond to issues as they’re created
LabelOps
automatedWorkflows triggered by label changes on issues and PRs
DailyOps
scheduledSmall daily improvements that compound over time
Research & Planning
scheduledWeekly research reports and automated team status updates
Triage & Analysis
automatedIntelligent issue triage and CI failure investigation
Coding & Development
automatedPR assistance and automated dependency updates
Quality & Testing
automatedTest coverage improvements and performance optimization