AI apps for startups

Your AI feature, built in production code and working in 21 days.

Fixed price after a short scoping call. Working in 21 days from access, or your build fee back. Then we keep it running.

Working in 21 days from access, or your build fee back. Half paid only when it works. Full terms

In your words

What founders tell us.

  • We need to ship this AI feature but the team is stretched.

  • Our prototype works in a demo but breaks with real users.

  • We need someone senior to own the backend and the AI.

  • We tried AI and it got things wrong.

Fit

Who it's for.

Funded or making money

Startups and tech companies with a budget for building, led by a founder, CTO or head of product.

AI that needs to ship

An AI feature, an AI product or a full-stack app that has to be built or finished, and a date it has to work by.

A team that's stretched

Your own engineers are too few or too busy to ship it on time without dropping something else.

The work

What we build.

Front end to back end, in production code your own engineers can read, run and take over.

An AI feature in your product

Search, assistants, document processing or recommendations, added to the product you already have.

A first version of a new product

A first working version of a new AI product, scoped to what real users need first.

A prototype made solid

A demo that works on stage but breaks with real users, rebuilt to handle them.

A senior engineer to own it

Someone senior to own the backend and the AI, available on request once the first build is working.

The process

From first call to working software.

  1. 30 minutes

    Free call

    We talk through what you need built and tell you honestly whether we're the right team for it.

    Our promise: No pitch if it isn't worth it.

  2. A short session

    Scoping session

    We agree exactly what the first working version does, and it ends in a fixed price.

    Our promise: A fixed price before any build starts.

  3. 21 days from access

    21-Day Build

    Your AI feature or first version, built in production code from front end to back end.

    More about 21-Day Build

    Our promise: A first working version in 21 days from access, or your build fee back. Half paid only when it works.

  4. Monthly

    Monthly care

    We watch it, fix it and keep it working as real users arrive and the AI models change.

    Our promise: We stay responsible after launch.

A dedicated senior engineer

Need someone senior to own the backend and the AI for longer? A dedicated senior engineer is available on request.

Startups

AI features we buildfor startups.

Each one is built in production code, with the parts that keep it working once real users arrive.

  1. Next.jsPostgrespgvectorClaude APIIntercom
    1. 1Ticket arrivesFrom Intercom or the in-app help form.
    2. 2Sorted by topicThe model tags topic and urgency, and urgent ones jump the queue.
    3. 3Docs searchedOnly your help articles and past answers are searched for the facts.
    4. 4Reply draftedA draft that links the sources it used, or says it doesn't know.
    5. 5Agent sends itEdits are saved and become test cases for the next release.

    AI app · Customer support

    100%Answers sourced

    Support answers from your own docs, or an honest "I don't know".

    Tickets are sorted by topic and urgency, answered from your own help articles with the sources linked, and sent by a support agent who can edit the draft.

    How the support answer assistant works
  2. ReactNode.jsS3GeminiZod
    1. 1File uploadedPDFs, scans or photos, stored privately against the user's account.
    2. 2Fields readThe model pulls out dates, names, totals and terms into a fixed format.
    3. 3Checked in codeEvery field is validated, so a wrong date or total can't get through.
    4. 4Unsure fields flaggedAnything the model isn't sure of is highlighted for the user to confirm.
    5. 5Saved to the appClean records the rest of the product can search and report on.

    AI app · Document processing

    EveryField validated

    Upload a contract, get clean data back.

    Users upload PDFs, scans or photos. The AI pulls out the dates, names, totals and terms into a fixed format, and anything it isn't sure of is highlighted for the user to confirm.

    How the document extraction feature works
  3. Next.jsPostgresOpenAI APIRedisPostHog
    1. 1User asksA plain-English question inside the product.
    2. 2Permissions checkedOnly records that user is allowed to see are ever searched.
    3. 3Answer builtThe reply links to the records it came from, so users can check it.
    4. 4Costs cappedPer-user limits and caching keep the AI bill predictable.
    5. 5Usage trackedWhich answers helped and which didn't, to guide the next change.

    AI app · In-product assistant

    EverySearch permission-checked

    Answers from each user's own data, and nobody else's.

    Users ask questions in plain English inside the product. Answers come only from records they're allowed to see, with links back to each one and a cap on AI costs.

    How the in-app data assistant works

All startup case studies

Before you hire anyone

What buyers worry about, and what we do about it.

Book a free 30-minute call

What we do about it

Hiring someone unproven

We show you a working demo, and half the build is paid only when it works.

Cost or scope running away

You get a fixed price before anything is built.

Security

Your accounts, your keys, a signed NDA, and our access removed when the work ends.

Getting locked in

You own every account and every line of code from day one.

AI getting it wrong

A person checks it until it's accurate.

Breaking what already works

The new system runs next to the old one until it works.

Included

What you get, whatever we build.

You own everything

Every account, key and line of code is yours from day one. Nothing is locked inside our accounts.

A person checks the AI

Anything the AI does for your customers or your money is checked by a person until it's accurate.

Signed NDA from day one

We sign an NDA before we see anything, and basic security is in place from the first day of work.

FAQ

What founders ask first.

See every question

It depends on the job, so we don't quote a number before we've seen it. For businesses, the Ops Map ends in a fixed price for the build. For startups, the scoping session does. Either way you know the price before any build starts.

An AI feature added to your product, a first version of a new product, a prototype made solid enough for real users, or a senior engineer to own the build. All of it in production code, front end to back end.

Yes. A demo that breaks with real users is one of the most common things we're asked to fix. The scoping session looks at what's there and fixes a price for making it solid.

Yes. We build in your repository, in production code your own engineers can read and take over. If you don't have a codebase yet, we set one up that you own.

The 21 days start on the day we have the access we agreed we need: logins, API keys, repositories and so on. If what we agreed isn't working 21 days after we get access, you get the build fee back. The full conditions are on our guarantee page.

The build fee is split in two. The second half is only paid once the build does what we agreed it would do.

You do, from day one. We build in accounts you own, the code lives in your repository, and the keys are yours. If we stop working together, nothing has to be moved or bought back.

Anything the AI does for your customers or your money is checked by a person until it's accurate. You see what it gets right and wrong before anyone relies on it.

Working in 21 days from access, or your build fee back. Half paid only when it works. Full terms

Book a free 30-minute call