TemplatesGet a demo →Book a meeting

Can I expense this? Answered from your own policy

Staff describe what they want to spend on and get the limit, the approver and whether a receipt is required, quoted from the policy line that sets it. Anything the policy doesn’t cover goes to finance rather than being reasoned into an allowance.

Finance · Someone asks · 7 steps · Reads your documentsA person is asked at “Ask a person”

AI Factory · Spend policy deskthe flow as it opens in the builder
QuestionQuestion
RetrieveRetrieve
AnswerAnswer
If / elseGrounded in the sources?
Answer shownAnswer shown
Ask a personAsk a person
Answer shownAnswer shown
7 steps in the flowDrag the canvas, or any step, to move it around.

Why teams run it

Finance teams answer the same spending questions all day, and staff who can’t get an answer either overspend or stall a purchase. The policy usually says what to do, but few people can find the clause that applies to their situation.

How it is governed

  • Answers quote the policy line that sets the limit or approver.
  • It is instructed not to reason its way to an allowance the policy lacks.
  • Escalated questions wait for a finance approval before anything is shown.
  • Every question and answer is kept in the run history.
Who runs it
Finance operations teams; Financial controllers; Budget holders and managers.
What you supply
Expense and procurement policy as knowledge sources.
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.
What teams usually change
Load regional or entity-specific policies as separate knowledge sources; Name the finance queue or person who rules on escalations; Make the check stricter, so uncovered questions always reach finance.
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.

Questions buyers ask

Does it approve spending?
No. It tells staff what the policy says, including who the approver is, and the approval itself happens in your existing process. Questions the policy doesn’t settle go to finance.
How does it handle different policies per country or entity?
Load each policy as its own knowledge source; answers cite the document they come from, so a reader can see which policy applied. Retrieval also respects each source’s own permissions.
What if someone asks about something the policy ignores?
The answer says the policy is silent rather than inferring a permission. Teams commonly tighten the check so those questions reach finance for a ruling.

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.