Ask-your-data agent

Ask the business a question and get the answer, not a report request.

A plain-English question box over your own records. The model turns the question into a query, the database does the arithmetic, and the answer arrives with the query that produced it.

Built with Claude, Supabase, Next.js, Vercel.

The situation you are probably in

Every question worth asking queues behind the one person who can write the query. How many of these did we do last year, which customers have not ordered since spring, what did this cost us in March. Each one is a request, a wait and a reminder, so most of them are never asked at all.

What we do about it

We put a question box over the database you already have. The model's job is to turn a question into a query; it never produces the number itself, because the database does the arithmetic and cannot round in your favour. Every answer shows the query it ran, so a sceptical finance person can check it rather than take it on trust. Questions the data cannot answer come back saying so.

Typical engagement. Two to four weeks over a database that already exists, then a monthly line to widen what it can answer as people find the edges.

Where this already runs

Running inside a catering business built from thirty years of paperwork: staff ask about customers, past events and pricing in plain English and get an answer from the live records, without opening a spreadsheet or asking anyone to build a report. The same database holds the priced menu the business quotes from.

Most builds of this shape start with the two-week assessment: we map the process as it runs today, cost it, and write the scope. The fee is credited in full against the build.

Start with the two-week assessment

What you receive.

Concrete things, not outcomes on a slide. This list is the scope of the engagement.

  1. 1

    A question box over your live records, for people who will never write a query

  2. 2

    Every figure computed by the database, with the model writing the sentence around it

  3. 3

    The query shown under each answer, so any number can be checked at source

  4. 4

    A clear answer when the data cannot support the question, rather than a confident guess

  5. 5

    Access rules, so a person only ever queries the records they are allowed to see

  6. 6

    A log of what was asked, which shows you the reports worth building next

A good fit when

  • Your records are already in one database, even an untidy one
  • People wait on someone else to answer routine questions about the business
  • The same handful of questions come round every week

The right starting point when

Not sure which of these is you? Describe the process and we will point you at the right one, on this page or another.

Price it before you commission it

Put the hours the task takes today, the salary of the person doing it and any quote you hold through the payback calculator. It shows the yearly saving, the payback period and the arithmetic behind both. Free, and nothing is stored.

Run the payback numbers

Things you can check.

Figures from our own systems that this service draws on. Each one names its source.

120+
tables of business data you could export tomorrow
380+
working screens and system connections in daily use
25+
business systems already connected: CRM, email, ads, payments

Every figure names its source. How we count. The investing system runs on a broker paper account, not real money.

Make the next AI project one the business can measure.

Thirty minutes with the founder, no slides. You will know what the right solution looks like, what it would take to build, what it should return, and which part to start with.

Replies come from a named person in Dubai within one working day.