Build agents with tool use, memory, multi-agent orchestration, and evaluation frameworks.
AI agents can plan, use tools, and take action autonomously. Here's what they are, how they work under the hood, and what separates useful agents from overhyped demos.
Not every AI chatbot is an agent, and not every task needs one. Here's the real distinction between agents and chatbots, the spectrum between them, and when each makes sense.
Function calling lets LLMs interact with external systems by requesting structured tool executions. Here's how the loop works, how to define tools, and what to watch for across providers.
AI agents without memory forget everything between turns. Here's how to implement conversation buffers, sliding windows, summary memory, and vector-backed long-term recall.
Multi-agent systems use specialized AI agents working together on complex tasks. Here's how they work, the main architecture patterns, and when they're worth the complexity.
Evaluating AI agents requires different metrics than evaluating LLMs. Here's how to measure task completion, trajectory quality, tool-use accuracy, and regression across agent systems.
Up next
Ship AI to production with cost optimization, observability, streaming, and tool integration.
Get Insanely Good at AI
Chapter 6: Agents and Automationexplains how agents actually work under the hood: the observe-think-act loop, tool calls, orchestration, planning, and memory. Building agent workflows that are reliable, not just impressive.
Suggested
Guides
