Source URL: https://simonwillison.net/2025/Jun/27/continuous-ai/#atom-everything
Source: Simon Willison’s Weblog
Title: Continuous AI
Feedly Summary: Continuous AI
GitHub Next have coined the term “Continuous AI" to describe "all uses of automated AI to support software collaboration on any platform". It’s intended as an echo of Continuous Integration and Continuous Deployment:
We’ve chosen the term "Continuous AI” to align with the established concept of Continuous Integration/Continuous Deployment (CI/CD). Just as CI/CD transformed software development by automating integration and deployment, Continuous AI covers the ways in which AI can be used to automate and enhance collaboration workflows.
“Continuous AI” is not a term GitHub owns, nor a technology GitHub builds: it’s a term we use to focus our minds, and which we’re introducing to the industry. This means Continuous AI is an open-ended set of activities, workloads, examples, recipes, technologies and capabilities; a category, rather than any single tool.
I was thrilled to bits to see LLM get a mention as a tool that can be used to implement some of these patterns inside of GitHub Actions:
You can also use the llm framework in combination with the llm-github-models extension to create LLM-powered GitHub Actions which use GitHub Models using Unix shell scripting.
The GitHub Next team have started maintaining an Awesome Continuous AI list with links to projects that fit under this new umbrella term.
I’m particularly interested in the idea of having CI jobs (I guess CAI jobs?) that check proposed changes to see if there’s documentation that needs to be updated and that might have been missed – a much more powerful variant of my documentation unit tests pattern.
Tags: continuous-integration, github, ai, github-actions, generative-ai, llms, llm
AI Summary and Description: Yes
Summary: The text introduces the concept of “Continuous AI,” a term coined by GitHub Next to describe the integration of AI in software collaboration, similar to Continuous Integration and Continuous Deployment (CI/CD). It emphasizes the versatility of AI in enhancing workflows, particularly through the use of Large Language Models (LLMs) in GitHub Actions.
Detailed Description: The text elaborates on the newly introduced term “Continuous AI,” which serves to encapsulate various uses of automated AI within software collaboration contexts. Key points include:
– **Alignment with CI/CD**: The term is inspired by Continuous Integration and Continuous Deployment, signifying a similar transformative role for AI in automating processes.
– **Open-Ended Category**: Continuous AI is described as a broad set of activities rather than a specific technology or tool, suggesting its potential for expansive applications.
– **Integration of LLMs**: It highlights the possibility of using Large Language Models (LLMs) within GitHub Actions, specifically through the llm framework and the llm-github-models extension. This indicates an innovative way to enhance automation by leveraging AI capabilities.
– **Documentation Improvement**: A noteworthy application discussed is the idea of CI jobs (or CAI jobs) that can identify documentation updates needed when changes are proposed, which improves the quality control of project documentation.
– **Community Resources**: The GitHub Next team maintains an “Awesome Continuous AI” list, which curates projects related to this new concept, facilitating further exploration and adoption by practitioners.
This concept is particularly relevant for professionals in software development and DevSecOps, showcasing how AI can be effectively integrated into existing workflows to enhance productivity and accuracy.