TemplatesGet a demo →Book a meeting

Every incoming ticket sorted and answered the way it deserves

When a ticket arrives from your help desk, the flow decides whether it is a bug, a billing question or a how-to request, then drafts from your help center accordingly. Anything else gets one line saying a person is needed.

Support · Something arrives from another system · 10 steps · Reads your documents

AI Factory · Ticket triagethe flow as it opens in the builder
When something arrivesIt arrives
RouteWhat kind of question?
RetrieveRetrieve — Bug report
RetrieveRetrieve — Billing answer
RetrieveRetrieve — How-to answer
AnswerPolitely decline
AnswerBug report
AnswerBilling answer
AnswerHow-to answer
Answer shownAnswer shown
10 steps in the flowDrag the canvas, or any step, to move it around.

Why teams run it

First-touch support spends much of its day reading tickets to decide what they are before anyone can help. A billing question answered like a how-to, or a bug report answered with a help article, costs a second contact and a less patient customer.

How it is governed

  • Only a correctly signed webhook call can start a run.
  • Billing answers are instructed never to estimate a charge.
  • Drafts are returned for your team; nothing is sent to customers.
  • Every ticket, its category and its draft are kept in the run history.
Who runs it
Support team leads; Support agents; Customer operations managers.
What you supply
Your help centre as a knowledge source.

It ships with test questions

  • The export button does nothing
  • Why was I charged twice in March?
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
Rename or add categories to match your queues; Point each path at its own sources, such as billing policies; Choose a different model for the classifying step.
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 reply to the customer?
No. The flow drafts a response and records it with the run; the template has no step that writes back to your help desk. Your agents review the draft and send it.
How does it decide what kind of ticket it is?
A model reads the ticket and picks the closest category by meaning rather than by keyword, and only that path runs. A ticket that fits no category takes its own path and gets a one-line note instead of a forced answer.
What does our help desk need to do?
Send new tickets to the flow’s webhook, signed with the secret shown on the agent’s triggers. A call without a valid signature is refused before any run starts.

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.