Agentic AI Patterns: ReAct, Plan-and-Execute, and Multi-Agent

Descrizione del corso

Move beyond chatbots to building reliable autonomous agents. Covers the ReAct (Reason + Act) pattern, Plan-and-Execute agents, Reflexion and self-critique loops, agent memory architectures (working, episodic, semantic), tool selection strategies, multi-agent communication patterns (hierarchical, collaborative, adversarial), agent state machines with LangGraph, human-in-the-loop interruption points, agent debugging and tracing, and production reliability patterns for long-running agents.

Cosa imparerai

• Curated from public resources. Build production-grade AI agents with ReAct, Plan-and-Execute, and multi-agent patterns with reliability guarantees.

Programma del corso

1. ReAct: combining reasoning and acting in LLMs (32 min)
2. Plan-and-Execute: separating planning from execution (28 min)
3. Reflexion: self-critique and iterative improvement (30 min)
4. Agent memory architectures: working, episodic, semantic (35 min)
5. Agent state machines with LangGraph (40 min)
6. Human-in-the-loop: interruption and approval patterns (30 min)
7. Multi-agent communication: hierarchical and collaborative (38 min)
8. Agent reliability: retries, timeouts, and circuit breakers (32 min)
9. Debugging agents with LangSmith traces (28 min)

Struttura del corso

3 sezioni, 9 lezioni, 13h 0m di durata complessiva. Il corso si segue interamente online, al proprio ritmo.

Domande frequenti