Working With Coding Agents
A practical course for builders who want coding agents to become reliable collaborators, not unpredictable code generators. Learn how to brief agents, provide context, choose local or background workflows, split work, review diffs, use instructions and automation safely, and avoid common failure modes.
Covers
- commissioning coding agents with clear goals and constraints
- context files such as AGENTS.md and CLAUDE.md
- local, IDE, web, cloud, and background task choices
- task splitting, worktrees, subagents, and parallel review
- diff review, tests, hooks, routines, and safety gates
Doesn’t cover
- model benchmarking
- prompt jailbreaks or unsafe automation
- vendor pricing optimization
- full CI/CD platform setup
- secrets management implementation
Working With Coding Agents
A practical course for builders who want coding agents to become reliable collaborators, not unpredictable code generators. Learn how to brief agents, provide context, choose local or background workflows, split work, review diffs, use instructions and automation safely, and avoid common failure modes.
What this course covers
- Covers
- commissioning coding agents with clear goals and constraintscontext files such as AGENTS.md and CLAUDE.mdlocal, IDE, web, cloud, and background task choicestask splitting, worktrees, subagents, and parallel reviewdiff review, tests, hooks, routines, and safety gates
- Doesn’t cover
- model benchmarkingprompt jailbreaks or unsafe automationvendor pricing optimizationfull CI/CD platform setupsecrets management implementation
The Agent Contract
Set the working agreement before asking an agent to touch code.
6 steps
Commission Better Work
Write prompts that behave like useful engineering tickets.
6 steps
Context That Scales
Use project instructions and memory without turning them into clutter.
6 steps
Choose the Work Surface
Decide when to work locally, in an IDE, or in a cloud/background session.
6 steps
Split and Supervise
Run cowork-style workflows without losing control of the codebase.
6 steps
Review and Automate Safely
Turn agent speed into shippable work with tests, hooks, routines, and human review.
6 steps