Skip to content

Shipping with Claude Code

Test, debug, secure, deploy and run what the agent built, without writing the code yourself.

acceptance teststest reviewdebugginglogsreproducing bugssecretsdependenciesauthinjectiondeploysenv varsmonitoringbackupscostsriskcapstone

Lessons

  1. 39.1Testing without coding: make the agent prove itClaude Code writes the tests. You decide what they must check, and you make sure they can actually fail. 30 min
  2. 39.2Debugging with AI: evidence before fixesDon't let the agent guess fix after fix. Make it find the cause first, with evidence. 30 min
  3. 39.3Security for vibe coders: what the agent won't askThe agent builds for honest users. You ask five questions so it's safe from everyone else. 30 min
  4. 39.4Deploy and operate what the agent builtShipping isn't the finish line. Know how to switch it on slowly, how to undo it, and which numbers to watch. 30 min
  5. 39.5When to ask a human: knowing your limitsThe agent makes every change feel equally easy. You decide which ones need an expert's eyes. 30 min
  6. 39.6Capstone: ship a real feature with Claude CodeOne real feature, start to finish. Claude Code does the typing; you make every decision and decide when it's done. 30 min

On the job: try it on your own project

Take one feature from your backlog and ship it with Claude Code, on a branch, through review. Write the acceptance tests first and check the tests Claude writes really test them. Ask it for a security pass on secrets, auth and inputs. Before deploying, write a short release checklist: env vars, monitoring, rollback plan, and the point where you would ask a human expert.

Can you do this now?

0/5. Anything you can't tick yet: reopen that lesson's practice ladder.