Building AI Agents

Give LLMs tools, memory and the ability to act autonomously

Build real agents: tool calling, the ReAct loop, agent memory, planning, error recovery and production agent patterns. Move from single-shot completions to autonomous systems that act.

Skills you'll gain

Tool CallingAgent LoopsReActMemoryPlanningError Handling

Prerequisites

LLM APIsStructured OutputsFunction Calling

Chapters

Tool CallingAdvanced

Function calling, schemas, execution and the foundation of every agent.

32m

Agent LoopsAdvanced

The ReAct pattern: reason, act, observe, loop. With stopping conditions, budgets and safety.

38m

Agent Memory & PlanningAdvanced

Short-term, long-term and episodic memory; task decomposition and planning for complex agents.

36m

Labs in this series

Build a ReAct Agent Loop

Advanced

Implement run_agent(task, tools, max_iter) that loops reasoning + tool calling until final answer or max_iter.

70m4 skills