Does it read our CRM directly?

It reads account notes and contribution history once they are loaded as knowledge sources, not the CRM itself at the moment you ask. The brief is as current as those sources.

Will it make up a contribution figure it can’t find?

It is instructed to leave out anything the sources do not say, and every claim carries a citation. For computed contribution figures, the Contribution monitoring and Payment reconciliation templates read your ledger directly.

Can it answer questions across employers?

It can, within what the retrieved passages cover; its test questions include which employers have open cases. For a complete list, a question answered from your database is more reliable than one answered from notes.

Walk into every employer conversation knowing the full relationship

Name a participating employer and the flow briefs the relationship manager from your account notes and contribution history: members, contribution record, open cases, and the last contact with what was agreed. It ends with one recommended next step and the reason for it.

Sales · Pensions & retirement · Someone asks · 4 steps · Reads your documents

Walk through it Run it on your data

AI Factory · Employer relationship briefthe flow as it opens in the builder

QuestionQuestion

RetrieveRetrieve

AnswerAnswer

Answer shownAnswer shown

4 steps in the flowDrag the canvas, or any step, to move it around.

Why teams run it

Relationship managers prepare for an employer call by searching account notes, contribution reports and case logs, and still arrive unaware of the complaint someone else handled last month. The employer notices, and the fund looks like several organizations rather than one.

How it is governed

Retrieval respects each source’s own permissions for the person asking.
It leaves out anything the sources do not say, rather than filling gaps.
Every claim in the brief is cited to a source passage.
Every brief is kept in the run history.

Who runs it: Employer relationship managers; Employer services teams; Heads of member and employer services.
What you supply: Your CRM’s account notes and contribution history as knowledge sources.

It ships with test questions

Brief me on our largest employer
Which employers have open cases?

A run waiting for a person in the product, with Approve and Reject buttons. The banner asks whether to approve the round and send the escalations, and states that approving sends nothing: nothing leaves the system. Below it, the run's time, cost and steps. — 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: Add case logs or meeting notes as further knowledge sources; Change the brief’s sections to match how your team reviews accounts; Ask for talking points instead of a single next step.

An evaluation set in the product, named Plan documents: answers with sources. It passes at 80 percent, gates releases and last scored 100 percent. Two checks: the answer cites at least one source, and it never contains I don't know. Below it, the questions it asks. — 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 read our CRM directly?: It reads account notes and contribution history once they are loaded as knowledge sources, not the CRM itself at the moment you ask. The brief is as current as those sources.
Will it make up a contribution figure it can’t find?: It is instructed to leave out anything the sources do not say, and every claim carries a citation. For computed contribution figures, the Contribution monitoring and Payment reconciliation templates read your ledger directly.
Can it answer questions across employers?: It can, within what the retrieved passages cover; its test questions include which employers have open cases. For a complete list, a question answered from your database is more reliable than one answered from notes.

Related templates

All 60 templates

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.

Get a demo Book a meeting