Follow-ups
Somebody has to send the third reminder. It doesn't have to be somebody.
Chasing is the work everyone means to do on Friday: the certificate that expires next month, the client who hasn't sent their bank statements, the renewal nobody started.
Chase log · renewals
- Day 0Certificate requested from client
- Day 7Reminder sent, second notice
- Day 10Received. Checked: right policy, in date
- Day 142 clients silent, handed to a person
What this produces, shown with sample data.
The short version
It keeps the list. It asks, reminds on a schedule you set, escalates to a named person when the deadline gets close, checks that what arrived is the right document, and files it.
Every chase has a clear end: the document arrived or it didn't. That makes it easy to grade, and a good first job for most businesses.
Where it runs
Where this kind of tool runs today, and where we'd build it next.
| Industry | Job | Status |
|---|---|---|
| Accounting & legal | Filing-season document chase | Playbook ready |
| Insurance | Certificates and renewals | Playbook ready |
| Real estate | RERA quarterly progress pack | Playbook ready |
| Freight | Carrier onboarding documents | Playbook ready |
Start to finish
- 1
Write down correct
We take last season's chase list and what actually happened to each item. Each one gets the answer a person on your team would sign. That set becomes the test it is graded on.
- 2
Build inside your tools
It works where the work already happens: WhatsApp, email, your POS, CRM or practice software. Nobody learns a new tool.
- 3
Run it with a person approving
For the first weeks a person approves what it sends. We loosen that only where the scorecard says it has earned it.
- 4
Grade it every month
The test re-runs monthly and whenever the model underneath changes. You get the score and the list of what it got wrong.
It stops when it should
The worst chaser is the one that reminds a client who paid yesterday. Every chase checks the system of record before it sends anything.
If nobody can write down what correct looks like, we don't build it yet.
Tell us the job your team hates. We'll tell you if AI can do it.
A 30-minute call with the people who would build it. No technical knowledge needed: just describe the job, how often it happens, and how you check it's done right.