10 - Introduction to AI Agents

An AI agent is a model that directs its own process: it reads its context, decides on an action (usually a tool call), observes the result, and repeats until the goal is met. This module builds that idea from first principles - the definition, the components, the loop, where agents work and how to evaluate one. The next modules add the building blocks (tools, memory, planning), protocols and agentic workflows.

Learning objectives 5-6 hours (notes + lab)

By the end of this module you will be able to:

Decide whether a task needs a single call, a workflow or an agent, and at what autonomy level
Name the parts of an agent - model, instructions, tools, memory, orchestration, guardrails, environment - and what each is responsible for
Write a correct tool-use loop against the Claude and OpenAI APIs and against any OpenAI-compatible server, with bounds and error handling
Evaluate an agent on environment state with pass^k over repeated trials

Prerequisites

Foundation Models - tokens, context windows, sampling
Prompt & Context Engineering - system prompts, structured outputs, context engineering
Optional, later in the course: RAG Systems - retrieval, which agents use as a tool

Where This Module Fits

flowchart LR
    W["01 What agents are"] --> AN["02 Anatomy"]
    AN --> L["03 The loop"]
    L --> PR["04 In practice"]
    PR --> E["05 Evaluation"]
    L -.-> LAB["🧪 Lab: loop from scratch"]
    E -.-> LAB
    E --> BB["🔧 Next: Agent Building Blocks"]

    style W fill:#e8e2d9,stroke:#ccc4b8
    style L fill:#e8e0d4,stroke:#c8b89a
    style E fill:#dde4dc,stroke:#b0c4b0
    style LAB fill:#d8dfe8,stroke:#b0bac8

Chapter Map

#	Chapter	You will learn	Time
1	What Are AI Agents	Agents vs workflows, the autonomy spectrum, why now, the decision test	40 min
2	Anatomy of an AI Agent	Model + harness: instructions, tools, memory, orchestration, guardrails, environment	35 min
3	The Agent Loop	Correct loops for Claude and OpenAI APIs, invariants, stop reasons, bounds, failures	60 min
4	Agents in Practice	Good use cases, personal vs enterprise, human-in-the-loop, build or buy	40 min
5	Agent Evaluation Basics	State-based grading, pass@k vs pass^k, first test sets, failure taxonomies	45 min

Tool use, memory and planning - the parts every agent is assembled from - are covered in depth in Agent Building Blocks.

Code Lab

Lab	What you build	Runs on
Agent Loop from Scratch	A tool-use loop with validation and bounds over a small retail environment, graded on database state with pass^k across prompt and tool-description variants	Any OpenAI-compatible endpoint: a local Qwen3 on a laptop (mlx-lm, Ollama, vLLM) or a hosted API

Mini-Project

Build and evaluate a single agent for a domain you know (an internal help desk, a lab-inventory assistant, a personal finance helper). Start it here and finish it after Agent Building Blocks:

An environment with 4-8 tools, at least two of them write tools with preconditions enforced in code, and a reset function.
A test set of 40 tasks across the six categories in Agent Evaluation Basics, each with an expected end state.
The loop from the lab (or a framework), with bounds, argument validation and informative errors.
Results: pass@1 with a confidence interval, pass^4, per-task counts, tokens and seconds per episode.
A failure taxonomy from the traces, one targeted fix, and before/after numbers.

Review

Q&A Review Bank - interview-style questions for this module
Module quiz - every Check Yourself question in this module, in course order

Summary & Key Terms

Summary & Key Terms - a quick recap of this module and its essential vocabulary.

Next Topic

Previous: 09 - Post-Training & Fine-Tuning · Next: 11 - Agent Building Blocks