In this session, we’ll explore how Large Language Models (LLMs) can be systematically integrated into GitHub Actions to enhance code quality and security in Apache projects, story behind the real-world example of apache/brpc#2911. Is ideal for developers and maintainers seeking actionable, low-overhead strategies to design, implements and deploy AI agent for code quality assurance. We’ll incentivize audience thinking on: Human-AI Collaboration: Contrast the traditional “copilot” model (human-driven, synchronous) with asynchronous AI agent workflows in pipelines, highlighting efficiency gains and trade-offs. We’ll bridge theory and practice, as Practical LLM Integration: Learn how to leverage LLMs for targeted tasks like code robustness scanning and CVE detection — without relying on RAG, fine-tuning, or MCP —while working within resource constraints.

Speakers:

CNCF kepler project maintainer, major focus on project’s pipeline.