All case studies

AI app · In-product assistant

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.

For
Startups
Built as
21-Day Build
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.

  • Every

    Search permission-checked

    Using the same rules the product already applies.

  • Capped

    AI costs

    Per-user limits and caching keep the bill predictable.

  • 1

    Senior owner

    One engineer responsible for it after launch.

"We need to ship this AI feature, but the team is stretched and nobody owns it."

The problem

The roadmap has an AI assistant on it, investors are asking about it, and the engineering team is busy keeping the core product running. Nobody has time to own it properly.

The risks are real: an assistant that shows one customer's data to another, or an AI bill that grows faster than revenue.

What we build

Permission checks run before the search, not after, using the same rules the product already applies. The assistant can only see the records the signed-in user can see, and every answer links to those records.

Per-user limits and caching keep costs predictable. PostHog tracks which answers people found useful, so the next change is based on use, not guesses. A senior engineer owns it after launch.

The checks built in

One user's data can never reach another user's answer. Permissions are checked on every search.

Every answer links its sources, so users can check it themselves.

We watch it after launch and report what's being asked and what's working.

Typical stack

  • Next.js
  • Postgres
  • OpenAI API
  • Redis
  • PostHog
How we build AI features for startups

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. Support answer assistant

    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. Document extraction feature

    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

All startup case studies

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