Agentic AI: Build a Multi-Agent Application with CrewAI
summary
Live demo builds a working multi agent app with CrewAI showing code, not slides, and four hands on assignments. It creates a two agent pipeline that takes a user prompt, one prompt-structure agent reformats it and a second agent optimizes it for a target LLM, uses pyantic to enforce outputs, demonstrates sequential and hierarchical processes, shows guardrails and a flow to detect hallucinations, optionally uses the serpev tool to browse the web, and publishes runnable solutions and a repo.
AI-written summary · about
chapters (11)
- 0:00Agentic AI introduction
- 1:12What is CrewAI
- 3:20Agents and LLM reasoning
- 8:43CrewAI components
- 13:43Sequential vs hierarchical
- 21:04Workshop setup
- 32:46First agent assignment
- 44:34First assignment solution
- 52:08Second assignment
- 56:28Solutions and Q&A
- 1:01:01Final Q&A
related talks
01h 53mAgentic AI: Build a Multi-Agent Application with CrewAI
29mDemystifying AI Agents with Python Code
41mGoing beyond copilot with AI Agents
01h 30mHow to build AI Agents: A step by step guide to creating AI agents
40mAI Agents in Practice
40mHow To Tame Your Agents?
32mBuilding Multi-Agent Systems: From Concepts to Collaboration
18mCollaborative AI Engineering: One Dev, Two Dozen Agents, Zero Alignment