Efficient DevSecOps workflows with a little help from AI
summary
Demonstrates concrete AI steps: use custom LLMs and RAG to answer up-to-date docs, run a local model (Olama) to debug Kubernetes via KS GPT, and auto-generate merge requests that patch scanned vulnerabilities and trigger CI. Shows code generation that builds a Kubernetes observability CLI, faster Rust learning, test and refactor generation, and pipeline root-cause summaries that identify bad image tags. Emphasizes guardrails, retention policies, metrics and local LLMs for sensitive data.
AI-written summary · about
chapters (18)
- 0:00Introduction and setup
- 0:45Defining inefficient DevSecOps tasks
- 2:11AI for development planning and code
- 5:02AI in code creation and learning
- 8:36Understanding and refactoring legacy code
- 10:43Generating unit tests with AI
- 12:07Improving code quality with AI
- 14:37AI for code reviews and merge requests
- 15:22AI for security and vulnerability mitigation
- 18:37AI in operations and root cause analysis
- 21:25Demo: Debugging Kubernetes with AI
- 25:05AI governance and security guardrails
- 27:34Performance and observability of AI models
- 28:59Measuring AI impact and effectiveness
- 30:02Retrieval augmented generation with AI
- 31:50AI agents and future workflows
- 32:12Summary and key takeaways
- 32:54Q&A session
related talks
45mDevSecOps at Warp Speed with AI
26mRunning Secure AI/ML Experiment in a Unified MLOPS-DevSecOps Pipeline
29mThe Future of DevOps: AI, Security, and Next-Gen Collaboration
51mBeyond Code Generation: Governing AI Agents Across the DevSecOps Lifecycle
40mSecure by Default: Building an AI-Augmented, OSS-Powered Reusable CI/CD Pipeline
34mDevOps at LLM Speed: Using an AI Copilot for Kubernetes and Jenkins
30mAI-Augmented DevOps with Platform Engineering
41mImproving DevOps workflows with GenAI