Tools and function calling
How a model calls your functions: defining a tool, the tool use loop, tool results and errors, the raw JSON on the wire, the SDK's tool runner, and how to write good tools.
AI: tools and agents
AI series 3 of 5. How a model acts in the world. Tools, MCP, agents, workflow patterns, memory and multi-agent systems.
8 parts
- Part 1
- Part 2
MCP: the Model Context Protocol
What MCP is, why it exists, hosts, clients and servers, tools, resources and prompts, the two transports, and a small MCP server in Python.
- Part 3
Agents: a model with tools in a loop
What makes a system an agent, how it differs from a workflow, when an agent is worth it and when it is not, a minimal agent in Python, and the Claude Agent SDK.
- Part 4
Five workflow patterns
Prompt chaining, routing, parallelization, orchestrator-workers and evaluator-optimizer: the patterns that solve most LLM tasks without a full agent, with short Python for each.
- Part 5
Memory and context management
How agents keep working when a task outgrows the context window: context engineering, compaction, clearing tool results, notes and the memory tool, with safe file handling.
- Part 6
Multi-agent systems and subagents
When several agents beat one: the orchestrator-subagent design, what Anthropic measured in its research system, the token cost, and subagents in the Claude Agent SDK.
- Part 7
Computer use and Agent Skills
Agents that operate a desktop through screenshots, mouse and keyboard, and skills: folders of instructions and scripts that give an agent expertise only when it needs it.
- Part 8
WebMCP: web pages as tools for AI agents
What WebMCP is and how it relates to MCP: a page registers tools with document.modelContext, forms become tools with two attributes, annotations, iframes, testing in Chrome, and the security risks.