Course Building Agentic AI Systems Chapter 3 Difficulty advanced Estimated Time 600 min

Chapter 3: Agent Taxonomy

Agent Taxonomy in Building Agentic AI Systems.

14% complete

Learning Objectives

By the end of this chapter, you will be able to:

  • Explain the agentic AI concept behind Agent Taxonomy.
  • Apply Agent Taxonomy to design reliable, production-grade agent systems.
  • Recognize operational trade-offs in tool use, orchestration, safety, and cost.

Chapter 3: Agent Taxonomy

Eight architecture types — and a decision matrix for choosing between them

Picking the Right Architecture

Most engineering mistakes in agentic AI come from applying a complex architecture to a problem that did not need it — or a simple one to a task that demanded more. This chapter gives you the vocabulary and the criteria to match architecture to problem.

The eight types below are not mutually exclusive. A production system often combines a planner that coordinates a team of tool-using workers, each of which uses reflection to verify its output.

Reactive

Direct stimulus → action, no planning

Tool-Using

Single-step function calls

ReAct

Reason + Act loop

Planning

Decompose then execute

Reflection

Self-critique + revise

Critic

Separate judge model

Computer-Use

Vision + mouse/keyboard

Code-Execution

Write & run code

Architecture Types in Depth

1. Reactive Agent

No memory, no planning. Maps the current observation directly to an action using a lookup or a single LLM call. Fast and cheap. Use for narrow, well-defined, stateless tasks — e.g., classifying an incoming support ticket.

📥
Input
Action
📤
Output

2. Tool-Using Agent (Single-Step)

Adds a tool call layer. The LLM decides which tool to invoke based on the user request, executes once, and returns the result. Still single-turn from the user's perspective. Example: a flight search that calls one API.

3. ReAct Agent (Reason + Act)

Interleaves reasoning (Thought) with tool calls (Action) and reads back results (Observation). Loops until the goal is met. This is the most common architecture for general-purpose agents. Introduced by Yao et al. (2022).

💭
Thought

Reason about next step

🔧
Action

Call tool

👁
Observation

Tool result

↺ repeat

4. Planning Agent

Before any tool call, generates a full plan. The plan is then executed step by step by an executor. Better for long-horizon tasks where upfront decomposition reduces errors. The planner can also replan if an execution step fails unexpectedly.

🗺
Planner

Decompose goal

📋
Plan

Ordered subtasks

⚙️
Executor

Run each step

Result

5. Reflection Agent

After producing an output, the same LLM (or a second call) critiques it and decides whether to revise. Key insight: a model is better at evaluating an output than generating it correctly on the first attempt. Self-consistency and Best-of-N sampling are simpler variants of reflection.

6. Critic Agent

A separate model (judge) evaluates the primary agent's output and provides structured feedback. The primary agent uses that feedback to revise. More expensive than self-reflection but higher quality — the critic can be prompted to focus on specific failure modes.

🤖
Generator
👩‍⚖️
Critic

Score + feedback

🔄
Revise
↺ until score ≥ threshold

7. Computer-Use Agent

Takes screenshots as observations, decides on keyboard/mouse actions, and interacts with any application without a dedicated API. Required when no programmatic interface exists. Claude's "computer use" capability is the canonical example. Slow, costly, and harder to debug — use only when necessary.

8. Code-Execution Agent

Writes Python (or another language) to solve problems, runs it in a sandboxed interpreter, reads stdout/stderr as observations, and iterates until the output is correct. Extremely powerful for data analysis, mathematical computation, and automated testing. Always run code in an isolated environment (e.g., E2B, Modal, Docker).

Decision Matrix

Use this table to select a starting architecture for a new task. Start with the simplest option that satisfies the requirements and complexity column.

Architecture Task Horizon Needs Memory? External Tools? Verification? Cost/Step
ReactiveSingle turnNoNoNoLowest
Tool-UsingSingle turnNoYes (1 call)NoLow
ReActMulti-stepShort-termYes (multi)ImplicitMedium
PlanningLong-horizonYesYesAt plan levelMedium
ReflectionAnyOptionalOptionalSelf-critiqueMedium+
CriticHigh-quality outputOptionalOptionalSeparate judgeHigh
Computer-UseMulti-stepYesAny app (visual)Screenshot diffVery High
Code-ExecutionMulti-stepSession stateVia codestdout/testHigh

Practical guidance

Start with ReAct for 80% of general-purpose agent tasks. Add a separate Planner when you observe the agent making poor mid-task decisions. Add a Critic when output quality is the bottleneck, not task completion. Use Code-Execution when the task is computation-heavy. Computer-Use is the last resort.

Chapter 3 Quiz

1. A ReAct agent interleaves Thought, Action, and Observation. What is the purpose of the "Thought" step?

2. When should you prefer a Critic Agent over self-reflection?

3. A Computer-Use Agent's "observation" is: