"The workflow type is being developed by GitHub Next and Microsoft Research, and features sandboxed execution and a feature called secure output, which is intended to protect the agentic workflow from misuse. The service is part of the continuous AI concept, also presented at Universe. According to principal researcher Eddie Aftandilian, speaking at the event, "we coined the term continuous AI to describe an engineering paradigm that we see as the agentic evolution of continuous integration.""
"An agentic workflow is defined in a markdown file and compiled to GitHub Actions YAML with the GitHub CLI (command line interface). The workflow is triggered by events, with developers able to choose one or more from events including new issues, new issue comments, pull requests and their comments, and new discussions. The actions to be taken by the agent are determined by prompt instructions, such as asking the agent to analyze issues, add labels, review pull requests, and output a structured report. The agent used can be GitHub Copilot, Claude Code, or OpenAI Codex."
"According to the team, typical use cases for agentic workflows include triaging issues, updating documentation, identifying code improvements, monitoring test coverage and adding new tests, investigating continuous integration (CI) failures, and creating regular reports on repository health. GitHub states that agentic workflows make "entirely new categories of repository automation and software engineering possible," that could not be achieved without AI. The new agentic workflows are not intended to replace traditional CI/CD (continuous integration and delivery) workflows, but to be used alongside. The FAQ notes that CI/CD needs to be deterministic, whereas agentic workflows are not."
Agentic workflows run AI agents automatically within GitHub Actions and are now in technical preview. They include sandboxed execution and secure output to limit misuse. The continuous AI paradigm frames agentic evolution of continuous integration. Workflows are defined in markdown and compiled to Actions YAML with the GitHub CLI. Repository events such as new issues, comments, pull requests, and discussions trigger workflows. Prompt instructions determine agent actions, for example analyzing issues, adding labels, reviewing pull requests, and producing structured reports. Supported agents include GitHub Copilot, Claude Code, and OpenAI Codex. Typical uses include triaging issues, updating documentation, identifying code improvements, monitoring tests, investigating CI failures, and reporting repository health. Agentic workflows are designed to complement deterministic CI/CD.
Read at Theregister
Unable to calculate read time
Collection
[
|
...
]