Claude Code consulting: what to look for before you hire anyone

Claude Code collapsed the distance between “described” and “built”. One operator with it can now ship what used to take a team: real applications with auth, databases, deploy pipelines, and documentation. That collapse created a consulting wave, and most of the wave is people who have automated a demo, not an operation.

Five checks separate the two. None of them require technical knowledge to run.

1. Ask what they run for themselves

Builders who use these tools on their own businesses have felt the failure modes with their own money. Ask: what do you operate in production, for yourself, today? A specific answer with numbers and dates is the strongest signal available. Our own answer is on the proof pages: a 41-agent fleet running a three-company group, 5,450 runs, zero failures, 13 days, as of July 2026.

2. Ask where the code will live

The only acceptable answer is: in your accounts. Your GitHub, your database, your hosting, your API keys. Any variation of “on our platform” means you are renting your own system, and the exit cost is a rebuild.

3. Ask for the definition of done, in writing

Claude Code makes building fast, which makes scope discipline MORE important, not less, because a fast builder can generate plausible-looking software past the point anyone checks it. A written scope with acceptance criteria is what keeps speed honest.

4. Ask how failures surface

Anyone can wire an agent that works on the happy path. The question that finds professionals: “when your agent hits input it cannot handle, what happens?” The right answer involves validation before the run, checks after it, logging, and a stop-and-ask default. Silent failure is the expensive kind.

5. Ask what happens after handover

Docs a new hire could follow, a recorded walkthrough, and a support window are the baseline. If the builder’s revenue depends on you never understanding your own system, their documentation incentive is exactly backwards.

The pattern behind all five

Every check is a receipts test. The tooling is genuinely powerful, which means the differentiator is no longer “can they build it” but “have they operated it”. Our version of passing that test is the AI Workforce Sprint: fixed price, your infrastructure, written scope, recorded handover. Hold us to the same five questions; the answers are on this site.