11 - Agent Building Blocks

Every agent is assembled from the same parts. This module covers the three that decide whether an agent works: tools (how the model acts on the world, and how to design schemas and errors it uses reliably), memory (what the agent keeps in context, in task state and across sessions) and planning (how it decides what to do next, and when reflection helps). Agent Protocols: MCP & A2A then standardizes how tools and other agents are connected, and Agentic Workflows & Multi-Agent Systems composes these blocks into patterns.

Learning objectives 3-4 hours

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

Design tools, schemas and error messages a model uses reliably, and scale to large tool sets with tool search
Design working memory, task state and long-term memory (semantic, episodic, procedural), and name their risks
Choose a planning strategy - native reasoning, ReAct, plan-and-execute, ReWOO - and know when reflection helps

Prerequisites

The Agent Loop - the loop these blocks plug into
Structured Outputs and Context Engineering

Where This Module Fits

flowchart LR
    LOOP["🔁 The agent loop"] --> T["🔧 01 Tools"]
    LOOP --> M["💾 02 Memory"]
    LOOP --> P["📋 03 Planning"]
    T --> MCP["Next: MCP & A2A"]
    T & M & P --> WF["Then: Agentic Workflows"]

    style T fill:#e8e0d4,stroke:#c8b89a
    style M fill:#dde4dc,stroke:#b0c4b0
    style P fill:#d8dfe8,stroke:#b0bac8

Chapter Map

#	Chapter	You will learn	Time
1	Tool Use & Function Calling	Strict schemas, tool_choice, tool design, errors, idempotency, tool search	60 min
2	Agent Memory	One taxonomy; context management; checkpoints; Letta, Mem0, Zep, LangMem; poisoning	60 min
3	Planning & Reasoning	Reasoning models, ReAct, plan-and-execute, ReWOO, LLMCompiler, reflection, todo lists	50 min

Practice with the Agent Loop from Scratch lab: its tool descriptions and validation are the tool-design ideas of chapter 1 under measurement.

Review

Q&A Review Bank - interview-style questions on tools, memory and planning
Module quiz - every Check Yourself question in this module
Summary & Key Terms - a quick recap of this module and its essential vocabulary

Next Topic

Previous: 10 - Introduction to AI Agents · Next: 12 - Agent Protocols: MCP & A2A