AI Coding Agents
Understand agentic coding tools like Claude Code, Cursor's agent mode, and Codex-style CLIs — how they plan, edit, run commands, and where they need a human in the loop.
Agentic coding tools can plan, edit, and run commands with little supervision. These lessons cover how the plan-act-observe loop works, how to steer it with good task instructions, and the sandboxing and review habits that keep autonomous file and shell access safe.
What Are AI Coding Agents?
Learn how agentic coding tools differ from autocomplete and what makes them capable of multi-step, multi-file work.
7 min read →Claude Code, Cursor Agent, and Codex-Style CLIs Compared
Compare the major agentic coding tools on where they run, how much autonomy they default to, and what workflow each fits best.
7 min read →Prompting and Steering a Coding Agent
Write task instructions that give a coding agent enough constraint to succeed without micromanaging every step.
7 min read →Safety, Review, and Guardrails for Coding Agents
Understand the real risks of giving an autonomous agent shell and file access, and the controls that keep that access safe.
7 min read →