The working reference
AI Coding Guides
Start with the job in front of you. Each guide gives you a workflow you can apply to your own codebase.
Prefer a reading sequence? Browse all chapters in order. For recent developments, read Updates.
01 / 3 guides
Choose models
Understand tradeoffs before choosing a model for your task.
02 / 5 guides
Ship features
Turn a requirement into a small, reviewable pull request.
- 04
Spec to PR
The full AI-assisted development loop, from spec file to merged pull request
- 09
How to Write Spec Files for AI Coding: Template and Worked Example
Keep requirements beside your code, reuse a Markdown template, and verify changes against a concrete component spec.
- 03
Prompting and Pitfalls
The mindset shift that makes AI coding actually work
- 07
Jira Ticket to Cursor to PR
Turning a Jira ticket into a structured Cursor task with Figma design context
- 10
Building Blocks First
Why starting from atoms changes how AI writes code
03 / 4 guides
Review and debug
Reproduce failures, inspect changes, and control agent scope.
- 05
AI-Assisted Debugging: From Bug Report to Tested Fix
Reproduce a pagination bug, write a failing test, make a minimal patch, and prove the fix with a runnable example.
- 08
AI-Powered Code Review
Using BugBot and Codex as PR reviewers - what they catch and what they miss
- 11
Diff Review Loops
Avoiding the looks-fine trap in AI-generated code
- 12
Agent Guardrails
Scope control and failure modes for autonomous coding agents
04 / 6 guides
Configure agents and design tools
Give agents reusable context and connect design to implementation.
- 14
Agents and Skills
How reusable skill files encode domain knowledge beyond a single session
- 19
What Is an AI Harness?
Raw model power is a runaway horse. A harness turns it into directed work.
- 15
Figma MCP to React: A Worked Design-to-Code Workflow
Map a Figma component to React with explicit token mappings, a copyable handoff prompt, and browser verification.
- 06
Design Token to Storybook
From Figma tokens to production component to documented Storybook stories
- 16
Code to Canvas
Pushing live rendered UI back into Figma as editable frames
- 17
Design to Code and Back
The full design and code feedback loop with Figma MCP