← All paths
Coding agents for engineering teams
From how a coding agent thinks to Claude Code in CI/CD: the tool landscape, Claude Code and Cursor, verifiable specs, MCP integrations, testing, code review, legacy refactors, parallel agents and the security of AI-written code. Closes with both Claude certification study guides.
- Route
- 17 guides · 866 lessons
- Level
- Beginner to advanced
How Coding Agents WorkUnderstand how coding agents think, act, and fail so you can direct them with judgment in any tool, and build a small one to see how it works inside.Start →
The AI Coding Tools LandscapePlace any AI coding tool on the map, test it on your own tasks, and pick your team's tools with criteria that last.Open →
Claude Code FoundationsInstall and direct Claude Code on a real project: give it memory with CLAUDE.md, explore and plan before you code, and delegate tasks to subagents.Open →
Cursor EssentialsDirect Cursor with judgment on a real project: choose the right way to ask for each change and review what it does before you accept it.Open →
Working with Coding AgentsDirect coding agents as a craft: write verifiable specs, set up your repo so the agent can check its own work, and review what it delivers before you accept it.Open →
Prompt Engineering with Claude CodeGet consistent results from Claude Code by writing instructions with the right structure, specifying before you code, and building your own prompt library.Open →
Claude Code and MCP: Building Custom IntegrationsConnect Claude Code to your own APIs, databases, and services by building MCP servers in TypeScript or Python that you can test and share with your team.Open →
Testing with Claude CodeWrite the tests first as the spec and let Claude Code implement, so AI-generated code does exactly what you asked for.Open →
Debugging and Code Review with Claude CodeReview and debug AI-generated code with calibrated trust: catch what it makes up, find the usual mistakes, and decide when to regenerate and when to edit.Open →
Refactoring and Legacy Code with Claude CodeUse Claude Code to quickly understand code you didn't write, refactor across many files with tests as your safety net, and migrate a real legacy project.Open →
Advanced Claude Code WorkflowsGo from using Claude Code on your own to coordinating several agents that work in parallel, with memory, team rules, and automations that run without you.Open →
Claude Code in Parallel and in the CloudRun several Claude Code sessions at once, on your machine and in the cloud, without them stepping on each other, while you decide what gets merged.Open →
Parallel Coding Agents with OrcaWork with several coding agents at once without them stepping on each other: have them compete on a task, hand work between them, and coordinate them like a team.Open →
Claude Code in CI/CD PipelinesPut Claude Code to work on every pull request in your pipeline, reviewing, fixing, and preparing releases with nobody at the keyboard, under tight limits on permissions and spend.Open →
Security for AI-Generated CodeFind and fix the vulnerabilities AI leaves in the code it writes, and protect your coding agent from malicious instructions and made-up dependencies.Open →
CCAO-F Exam Study GuidePrepare for the Claude Certified Associate: Foundations certification and build the judgment to tell whether Claude's output is right, complete, and ready to send. Independent guide with its own cases, exercises and practice questions, written from Anthropic's public documentation. Not affiliated with Anthropic and with no exam material.Open →
CCDV-F Exam Study GuideGet ready for the Claude Certified Developer: Foundations exam by organizing what you already know, filling your gaps in the Claude API, and practicing with original questions. Independent guide with its own cases, exercises and practice questions, written from Anthropic's public documentation. Not affiliated with Anthropic and with no exam material.Open →
Your engineering team ships production code with coding agents, with a human reviewing every cycle.