TemplatesGet a demo →Book a meeting

Budget questions

Answers spend questions from an export — totals by cost centre, by month, over budget — with the arithmetic done in code rather than by a model.

Finance · Someone asks · 5 steps · Your database

AI Factory · Budget questionsthe flow as it opens in the builder
QuestionWhat do you want to know?
Query a databaseRead the rows
Work out the numbersTotal the spend
AnswerExplain the result
Answer shownThe answer
5 steps in the flowDrag the canvas, or any step, to move it around.

Why teams run it

Answers spend questions from an export — totals by cost centre, by month, over budget — with the arithmetic done in code rather than by a model.

How it is governed

  • Every run keeps its input, each step’s output, its time and model cost, and any decision.
  • In the builder, anything that would change a record or send a message is simulated; reads run for real.
What you supply
A database connection under Admin → Databases, or a spreadsheet file.

It ships with test questions

  • Which cost centre spent the most last quarter?
What “a person approves” looks like in the product: the run stops, the banner says what approving will do, and until someone decides, nothing leaves the system. A demo workspace on synthetic data.

From template to a live agent

The same builder, tests and release review apply to a template as to anything built from scratch.

Open it as a working flow
Every step, source, branch and approval is already in place, and every one of them can be changed before it runs on your data.
Prove it before it ships
An evaluation set can gate the release, so a change that breaks an answer never reaches anyone. A question it cannot answer from the sources leaves the gate unproven, not passed.
Keep a person on the decisions
A run that needs a decision stops and says exactly what approving will do, and who it is waiting for.
Publish where people work
A form, an embedded widget, Microsoft Teams or a scheduled batch — with its own access and limits per deployment.
Step 02, in the product: an evaluation set that gates the release. A question it cannot answer from the sources leaves the gate unproven, not passed. A demo workspace on synthetic data.

See it run on your own data

We open it in the builder, point it at a sample of your documents and systems, and run it with you.