Matching you can explain
Every suggestion lists why it fits. Must-haves are respected, and ties go to whoever is least busy.
Tesryn Lab · Care networks
Referral Engine
Match each enquiry to the right practitioner, with the reasons written down.
In pilot First built for a network of independent practitioners · 2026
01 — What it is
People reach a network through its website. Each enquiry is matched to the practitioners who fit it, on languages, approach, availability and the rest, and every suggestion carries its reasons. Practitioners keep their own availability current. Staff see the pipeline end to end and know what needs them today.
The moment it earns its keepSomeone asks for help on a Sunday night and wakes up matched to a practitioner who fits, with the reasons on the record.
What it proves we can do
02 — What it can do
Four things it does.
Availability in the practitioner's hands
Each practitioner says how much they can take on, and matching respects it.
A website the network edits in plain English
Ask for a change, see it, approve it, publish it. Undo is exact.
One pipeline, no lost enquiries
From first contact to a confirmed match, with what's waiting on whom.
03 — How it connects
What it shares with the rest of the Lab.
The same things we know how to do keep coming back in different industries. This is where this one sits: what it proves, and what else proves the same thing.
Matching a person can check Weights, hard requirements and capacity — arithmetic with its reasons attached, never a model's hunch. Also proved by Part Finder, Referral Platform, Insurance-aware Intake.
Say it, see it, approve it, publish it Changes described in words become structured edits with an exact preview and an exact undo. Also proved by Tesryn Signal, Command Center.
Plain language, no training day One action per screen, words the user already uses, and errors that say what to do next. Also proved by Tesryn Signal, Reconstruction Research Studio, Part Finder, Command Center, Tesryn Launch, Referral Platform, Insurance-aware Intake.
Only what's needed, deleted on request The least data that makes the thing work, with forgetting built in rather than promised. Also proved by Tesryn Signal, Referral Platform, Insurance-aware Intake.
The whole map — six sections, and everything that proves them.
04 — What it's held to
- Matching is arithmetic a person can check. AI can help write the rules; it never makes the match.
- Contact details and preferences only. No health records.
What it isn't. Not a health-records system, and no public ratings of practitioners.
05 — The recipe stays in the lab
We'll tell you what it can do. Not how it's built.
Yours would be your own build, on your systems, and you'd own it outright: code, documentation, no lock-in. What we bring to it is the practice — we've solved this shape of problem before, so you're not paying for the first attempt. The method stays ours. And if what you need isn't here at all, that's the usual case — it's how every skill on this page started.