Will you throw away my code and start again?

Usually not, and I will not pretend otherwise to sell a bigger project. Most AI-built prototypes are structurally fine and specifically insecure. The audit tells you which yours is, and if a rebuild genuinely is cheaper I will say so with reasons.

What is usually wrong with AI-built apps?

Database access rules, most often — tables readable or writable by anyone who finds the endpoint. Then API keys left in client-side code, authentication that checks the wrong thing, and no error handling on anything that touches money.

Which tools do you work with?

Cursor, Claude Code, Lovable, Bolt, Replit, v0 and the usual suspects. What matters is the stack it generated rather than the tool that generated it, and most of them land on Next.js, React and a managed database.

How much does it cost?

From $1,999 fixed, quoted after the audit so the number reflects what is actually there rather than a guess. The audit itself is the first three days, and you keep the document either way.

Do you use AI to build too?

Yes, daily — it is why fixed prices and short timelines work. The difference is that everything it writes gets reviewed by someone who can tell when it is confidently wrong, which is the part a prototype skips.

Can you keep building features afterwards?

Yes, either as another fixed sprint or the monthly partnership. But the security pass comes first, because building on a broken foundation just makes the eventual fix more expensive.

Ship It Live — $1,999 flat

Design + build + deploy · kickoff in 24h · limited slots

Book a 30-min call →

21 days · from $1,999 · fixed

Ship It Live · production sprint

You vibe-coded a prototype. I'll make it survive real users.

AI got you to something that works on your laptop. That last 20% — auth that holds, a database strangers cannot read, and a deploy that does not need you awake — is what this sprint is for.

Book a 30-min call →

See the 21-day plan

4.93★ / 32 reviews 75+ shipped Kickoff in 24h

Quick answer

A vibe-coded prototype — built with Cursor, Claude Code, Lovable, Bolt or Replit — can be taken to production in about 21 days from a fixed $1,999. The work is usually not rewriting it: it is securing the database, fixing auth, adding tests and making it deployable by someone other than the person who prompted it.

The plan

Day one to day 21, written down.

You get this schedule before you commit, not after. If a phase slips, that is mine to absorb — the price and the date were agreed before anything started.

Days 1–3

Audit

I go through what you have built and write down what is genuinely broken, what is risky, and what is fine. You get that document whether or not you continue.

Days 4–8

Security first

Database rules, auth, exposed keys. AI tools reliably get these wrong because a prototype that works and a prototype that is safe look identical from the outside.

Days 9–15

Make it hold

Error handling, edge cases and tests around the paths that matter. The difference between a demo and something you can leave running.

Days 16–19

Deployment

A proper pipeline, environments, monitoring and backups — so a deploy is a command rather than an evening.

Days 20–21

Handover

Walked through what changed and why, with the code left in a state another developer can pick up without archaeology.

What from $1,999 gets you

Everything needed to launch — nothing padding the invoice.

A written audit of what is actually wrong, before any work starts

Database access rules — the most common serious flaw in AI-built apps

Authentication and session handling reviewed and fixed properly

Secrets moved out of the client and into somewhere safe

Tests around the paths that would cost you money if they broke

A real deployment pipeline, so shipping is not a manual ritual

The code left readable, so the next developer is not stuck

30 days of post-launch support, included

Who books this

Built for

Founders whose AI-built prototype suddenly has real users on it

Non-technical builders who got far and then hit a wall they cannot see

Teams who need a security and quality pass before anyone pays for this

The honest part

When 21 days is the wrong answer.

A fixed deadline only works when the scope genuinely fits inside it. These are the cases where I will tell you so rather than take the booking.

Prototypes where the underlying idea has not been tested with users. Hardening something nobody wants is an expensive way to learn that.

Codebases so tangled that rebuilding is genuinely cheaper — I will tell you honestly if that is what I find in the audit.

Products needing formal compliance certification, which is a programme rather than a sprint.

Questions

Before you book

Building software by prompting an AI rather than writing the code yourself — a term coined by Andrej Karpathy in 2025. It genuinely works for getting to a prototype fast. Where it struggles is the unglamorous production layer: access rules, auth, error handling and deployment, because those failures are invisible until someone exploits or hits them.

Other sprints

30 days · from $2,500

SaaS MVP in 30 days

A working SaaS MVP with auth, billing and a real database — designed, built and deployed in 30 days. Fixed price from $2,500, code yours.

30 days · from $2,500

AI app in 30 days

An AI product designed and built around a real workflow, not a chat box — deployed in 30 days from a fixed $2,500, source code yours.

21 days · from $1,999

Web app in 21 days

An internal tool, dashboard or customer portal designed, built and deployed in 21 days. Fixed price from $1,999, source code handed over.

21 days from now, this could be live.

A 30-minute call decides whether the scope fits. If it doesn't, I'll tell you what would.

Book the call

All sprints