# DynaCI: Generating GitHub Actions Workflows via Dynamic Analysis

DevFeed: [DynaCI: Generating GitHub Actions Workflows via Dynamic Analysis](<https://devfeed.tech/articles/dynaci-generating-github-actions-workflows-via-dynamic-analysis-94647.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2610.29890>)

Author: Javid Ditty, Rahul Ghanshyam Chavan, Nimmi Weeraddana, Foyzul Hassan

Published: 2026-10-22T04:00:00Z

Content type: article

Language: en

Sources: [arXiv: Software Engineering](<https://devfeed.tech/sources/arxiv-software-engineering.md>)

Topics: [CI/CD](<https://devfeed.tech/topics/cicd.md>), [GitHub Actions](<https://devfeed.tech/topics/github-actions.md>), [Retrieval Augmented Generation (RAG)](<https://devfeed.tech/topics/retrieval-augmented-generation-rag.md>)

Tags: [analysis](<https://devfeed.tech/tags/analysis.md>), [ci](<https://devfeed.tech/tags/ci.md>), [cs-se](<https://devfeed.tech/tags/cs-se.md>), [devops](<https://devfeed.tech/tags/devops.md>), [github](<https://devfeed.tech/tags/github.md>), [github-actions](<https://devfeed.tech/tags/github-actions.md>), [llm](<https://devfeed.tech/tags/llm.md>), [python](<https://devfeed.tech/tags/python.md>), [rag](<https://devfeed.tech/tags/rag.md>), [runtime](<https://devfeed.tech/tags/runtime.md>), [workflows](<https://devfeed.tech/tags/workflows.md>)

## AI overview

DynaCI generates GitHub Actions workflows from runtime information collected by tracing developers' local environments. It builds an initial workflow using runtime-informed heuristics, then iteratively refines it with LLM-based retrieval-augmented generation (RAG). In an evaluation on 50 popular Python projects, DynaCI exceeded GH-WCOM and LLM4GW by more than 21.13% in average BLEU score and 20.96% in average F1 score. It produced workflows without missing functionality in 56% of cases and required fewer manual repairs for exceptions. The evidence is an abstract, so it does not detail the tracing setup or evaluation procedure.

## Source excerpt

arXiv:2610.29890v1 Announce Type: new Abstract: Continuous Integration (CI) is an essential practice that automatically validates code changes through builds and tests. However, configuring CI workflows remains challenging, as modern software often features complex architectures, numerous dependencies, and support for diverse execution environments. Most CI platforms also require workflows to be written in their particular domain-specific languages. As a result, CI workflows are often error-prone and hard to maintain, especially for those unfamiliar with CI semantics. Prior work on automated CI workflow generation require developers to create specifications that describe their intended workflows using natural language, partial workflows, etc. However, in practice, developers may struggle to articulate requirements and may be unaware of available CI features. To address these limitations, we propose DynaCI, a novel approach that uses runtime information from developers' local environments to generate CI workflows. DynaCI (i) traces the developers' local environment to collect runtime information, (ii) constructs an initial workflow by applying runtime-informed heuristics, and (iii) iteratively refines the workflow via LLM-based Retrieval Augmented Generation (RAG). We evaluate DynaCI on 50 popular Python projects that use GitHub Actions, a popular CI platform, and compare it against the state-of-the-art CI workflow generation approaches: GH-WCOM and LLM4GW. DynaCI outperforms these existing approaches by more than 21.13% in BLEU score and 20.96% in F1 score on average. It also generates workflows without missing functionality in 56% of cases, while requiring fewer manual modifications to repair such exceptions. These results demonstrate that leveraging runtime information substantially improves LLM-based CI workflow generation, and offer a promising direction for broader DevOps configuration automation.