The Self-Healing Pipeline: How Dagger + LLMs Are Making Traditional CI/CD Obsolete
summary
Claim: combining Dagger’s programmable container engine with LLMs produces a self-healing pipeline that diagnoses failing tests, edits code, reruns tests and opens a pull request automatically. Implementation uses the Dagger Python SDK, containerized workflows that run identically locally and in CI, vendor‑agnostic LLMs (OpenAI/Claude), and an agentic loop that reads failures, edits files, and retries. Demo fixes a broken Python REST API test, iterates until tests pass, and successfully creates the PR.
AI-written summary · about
chapters (8)
- 0:00Self-healing pipelines intro
- 2:27CI pipeline problems
- 6:02Agentic CI explained
- 8:08Dagger programmable CI
- 14:51Self-healing pipeline demo
- 24:57Q&A enterprise setups
- 33:52Dagger modules & resources
- 39:23Agent integration costs
related talks
42mCI/CD Reimagined: Building Portable, Composable Pipelines with Dagger
26mFuture-Proof Your Platform’s CI/CD Without Developers Noticing a Thing
30mDagger at Scale: How Not to Stab Yourself with Your Pipelines
27mWrite portable CI/CD pipelines using Python
31mNo More 'git commit -m "fix pipeline #42"' Thanks to Dagger
34mI Break Things, AI Fixes Them: Building a Self-Healing CI/CD Pipeline
40mSharpen up your CI/CD pipelines with Dagger
56mCutting-Edge Continuous Integration with Dagger