Simon Willison Publishes Guide on How Coding Agents Work Under the Hood

Simon Willison

Mar 18, 2026 · Updated Jun 5, 2026

Simon Willison's new Agentic Engineering Patterns chapter breaks down how coding agents work — from LLM token mechanics and tool calling to system prompts and reasoning. A companion chapter covers subagents across seven major coding agents.

Simon Willison published a new chapter in his Agentic Engineering Patterns guide explaining how coding agents work. The guide defines a coding agent as an LLM wrapped in a harness — software that extends the model with a system prompt, callable tools, and a loop that replays conversation state. It covers token mechanics, chat templates, cached input tokens, tool calling, and how reasoning lets models spend more time on harder problems.

This fills a practical gap for anyone using Claude Code, Codex, or Cursor — understanding the underlying loop helps you make better decisions about prompt structure, cost management, and when to increase reasoning effort. A follow-up chapter covers subagents now shipping across seven major coding agents.

Read through the guide alongside your current coding agent workflow — the mental model of "LLM + system prompt + tools in a loop" reframes how you structure tasks and debug agent behavior.

View the full update on simonwillison.net

Simon Willison

@simonwMar 16

New chapter for Agentic Engineering Patterns: I tried to distill key details of how coding agents work under the hood that are most useful to understand in order to use them effectively https://t.co/14ai3UP79C

View on X

Every HeadsUpAI update is written based on its original source and reviewed before it's published. Read our editorial standards →

Keep reading

Simon Willison's Guide Argues Coding Agents Can Raise Code Quality

Shipping worse code with AI agents is a choice. Simon Willison's Agentic Engineering Patterns guide shows how teams can use agents to tackle refactoring debt — API redesigns, concept renames, module splits — that never felt worth the manual effort.

n8n Guide: Architect AI Agents for Production Reliability

n8nJun 5

n8n Guide: Architect AI Agents for Production Reliability

n8n has released a new guide on selecting the right AI agent architecture patterns, emphasizing that most agent failures stem from architectural issues rather than model performance. The guide details behavioral patterns, which define how an individual agent thinks, and topological patterns, which determine how multiple agents coordinate within a system.

OpenAI Updates Prompt Guide for Reliable GPT-5.4 Agent Patterns

OpenAIMar 6

OpenAI Updates Prompt Guide for Reliable GPT-5.4 Agent Patterns

OpenAI updated its prompting guide with GPT-5.4-specific patterns for building reliable AI agents. The guide covers tool use persistence, verification loops, and long-running workflow completeness, giving developers structured contracts for multi-step agent workflows that hold up in production.

Anthropic Publishes AI Agent Evaluation Framework from Production Deployments

AnthropicJan 9

Anthropic Publishes AI Agent Evaluation Framework from Production Deployments

Anthropic's engineering team published a guide to evaluating AI agents across coding, conversational, research, and computer use categories. The guide draws from Claude Code development and collaborations with Descript, Bolt, Stripe, and Shopify to provide a practical eval-building roadmap.