TemplatesGet a demo →Book a meeting

Every Monday, a count of member records that need fixing

Early every Monday the flow queries your administration system for records with gaps or conflicts, counts them by issue in code, and says which the fund can usually fix itself. Data problems reach your team as a weekly count, not as a surprise at retirement.

Operations · Pensions & retirement · On a schedule · Every Monday at 06:30 · 5 steps · Your database

AI Factory · Member data quality · run 1230a real run on synthetic data · recorded Sep 11, 2026
On a scheduleOn a schedule2 ms
Query a databaseFind the records with issues128 ms6 rows
Work out the numbersCount by issue10 ms3 rows
AnswerWrite the report2.1 s
Answer shownThe answer
5 of 5 steps ran2.3 s end to end$0.002 model costDrag the canvas, or any step, to move it around.
Asked: “Which member records need attention this week?”

The member records that need attention this week are those with the following issues, listed from most common to least common:

  1. No email address for an active member - 863 records. This issue can usually be fixed from records the fund already holds if there are other contact details available, or it may require the member to supply their email address.
  1. A second, different address for a member - 267 records. This issue typically needs the member or their employer to confirm the correct address.
  1. Same name and date of birth as another member - 8 records. This issue usually requires verification from the member or their employer to ensure the correct identification of the individuals involved.

Why teams run it

Member data degrades quietly: a date of birth never captured, a beneficiary never named, the same national identifier on two records. Nobody notices until a benefit has to be paid, and by then the fix means tracing a member or employer who may be hard to reach.

How it is governed

  • Read-only: SELECT queries through a connection an administrator sets up.
  • Counts are computed in code; the model is told never to recalculate them.
  • It reports and changes no member record.
  • Every run is kept in the run history.
Who runs it
Pension administrators; Data quality leads; Pension operations managers.
What you supply
A read-only database connection to your member administration system, with the checks pointed at your own tables.
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 checks of your own, such as missing addresses or stale salaries; Move the schedule to suit when your team plans its week; Rewrite the queries for your own member and beneficiary tables.
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 fix the records it finds?
No. It reads and counts; the connection is read-only and the template has no step that writes back. Correcting a record stays with your administrators.
Can we see which members are affected, not just the counts?
The report as shipped gives counts by issue. The query already returns the member numbers, so the flow can be changed in the builder to list them.
Can we run it outside the schedule?
Yes. Anyone with access can start it by hand, and switching the schedule off keeps its settings while nothing fires it automatically.

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.