Agents in Action: Advancing Open Source AI Missions
summary
Defines agents as LLMs that plan, call tools and act; demonstrates a working agent built on LlamaStack + Granite 8B that reads OpenShift logs via an OpenShift MCP tool, summarizes an error and posts a formatted alert to Slack using an MCP Slack tool. Compares frameworks (LangChain, Haystack, CrewAI), highlights MCP as a USB‑like protocol for tool/model integration, and shows memory, planning and tool access are required components — the demo executes end‑to‑end successfully.
AI-written summary · about
chapters (12)
- 0:00Generative AI and agents
- 2:33Traditional vs generative AI
- 6:25How LLMs work
- 9:36From search to automation
- 12:03AI agents and capabilities
- 13:53Agent system components
- 17:05Open-source agent frameworks
- 19:54Model Context Protocol
- 22:23AI agents use case
- 24:48Live agent demo
- 32:19Agentic AI conclusions
- 35:06Q&A on memory
related talks
36mPutting AI Agents to Work: A New Era of Open Source Connectivity with MCP
01h 28mAI Coding Agents and how to code them
34mAI Agents: Transforming Autonomous Decision-Making
01h 03mAI Coding Agents and how to code them
19mBuilding Agents at Cloud Scale
38mBuilding AI Agents and Assistants for DevOps Workflows
49mAI Agents: Collaboration in Real-Life Applications
08magentctl: A CLI for Managing AI Agents & MCP Servers Like Infra