Agentic AI: What It Is and Why It Matters
summary
Agentic AI augments LLMs with explicit reasoning, planning, memory and programmatic tool calls so models can book flights, run CI, write tests, and act—claiming up to 120 hours saved on an HR hiring process. Workable connectors already exist as MCB servers on GitHub (Google Maps, GitHub, Airbnb, AWS, local file access), plus emerging A2A state‑sharing and agent orchestration protocols that let multiple domain agents coordinate and actually execute tasks end to end.
AI-written summary · about
chapters (12)
- 0:00Agentic AI introduction
- 1:04AI agents and components
- 3:13AI agents use cases
- 9:19AI agents vs LLMs
- 11:10Core AI agent components
- 13:20AI agent in action
- 16:36AI agents today
- 18:45Multi-agent systems
- 20:35Model Context Protocol
- 23:09MCP servers and tools
- 25:46Building MCP servers
- 26:08AI agent future
related talks
40mAgentic AI: The Next Evolution of Automation
19mAgentic AI — From Hype to Reality
28mAgentic Enterprise - What your CEO must know about AI
27mAgentic Engineering: Working With AI, Not Just Using It
42mAgentic AI and the Future of AI
28mAgentic AI
21mAgentic AI & Blockchain: Autonomous Systems
20mReimagining InnerSource for the Agentic AI Era