Building AI Agents and Assistants for DevOps Workflows
summary
Shows an actual assistant integrated into continue.dev with Ollama, runs local models (Mistral, Granite), installs LangChain and edits files automatically, writes tests and README updates, and demonstrates agents chaining via LangChain, Bee, LlamaIndex with RAGs. Claims swarm behavior — dozens to thousands of agents hitting APIs risks uptime and costs, one demo generates ~28 BDD features and another prompt produces 18,000 file changes, and agents both create and modify code and tests on disk in real time.
AI-written summary · about
chapters (9)
- 0:00AI in DevOps intro
- 3:59Platform engineering shifts
- 8:12Standard workflow challenges
- 15:39Agents vs assistants
- 17:25Demo of AI tools
- 23:11Live coding with AI
- 30:18Model Context Protocol
- 33:11Redefining workflows
- 35:43Future of AI dev
related talks
40mAgents in Action: Advancing Open Source AI Missions
19mBuilding Agents at Cloud Scale
25mDirecting a Swarm of Agents for Fun and Profit
24mAI Agent Swarms Are Amazing
41mGoing beyond copilot with AI Agents
52mCut the Hype and Build Your Own AI Agents
32mBuild your own Autonomous Agent powered by LLMs using Kubernetes
27mAI Demystified Unveiling the Intelligence Behind the Machine