Admin crowding out care
Clinicians and coordinators spend hours on letters, summaries and forms that follow the same patterns.
For healthcare operations and health tech
Less admin, more care
Plain-language patient letters, referral summaries, scheduling messages and policy answers. Give clinical and admin teams back time, with you in full control of what is sent.
Less paperwork
first drafts for routine documents
Clearer letters
plain-language patient communication
You decide
exactly what data each prompt contains
The problem
What is slowing you down today
Instructions patients cannot follow
Discharge and prep instructions written for professionals leave patients confused and calling back.
Uncontrolled tools
Staff try consumer chat apps with no keys, no logs and no oversight.
Capabilities
Everything you need, nothing you don't
Plain-language rewrites
Turn clinical instructions into clear, friendly language at the reading level you specify.
Referral and note summaries
Condense long text into the structure your team uses, for a professional to verify.
Controlled access
Hashed API keys, per-account rate limits and a record of every request.
You control the inputs
Only what you put in a prompt is processed, so you can de-identify or minimise data before sending.
Templates you trust
Pin a named model for consistent output on a given document type.
Cost per document
Every call reports tokens and price, so pilots have a clear budget.
Use cases
What teams run on it
01
Patient letter drafts
Appointment, results-ready and follow-up letters in your organisation's voice.
02
Discharge instruction simplification
Easier-to-follow instructions for staff to review before they go out.
03
Policy and procedure Q&A
Staff answers drawn from the policy text you provide.
04
Scheduling messages
Reminders and prep notes tailored to the appointment type.
How it works
From sign-up to production
- 1
Review your obligations
Confirm with your privacy and compliance teams what data you may send to a third-party service.
- 2
Pilot with non-sensitive content
Start with templates, policies and de-identified examples in the playground.
- 3
Integrate with controls
Use dedicated keys, rate limits and request history to keep oversight.
Control
Built so you stay in charge
Keys you control
API keys are shown once at creation and stored only as a hash. Revoke any key instantly from Settings.
Spend you can see
Every request carries its own receipt: tokens in, tokens out, latency and price. Nothing is billed that you cannot trace.
Limits you set
Per-account rate limits and a free monthly allowance keep experiments safe before they become production.
Data you decide on
You choose exactly what you send. Repeat prompts can be served from your cache, and cache hits are never billed.
For developers
One endpoint. Every model.
Send a prompt and a capability, or name a model. One bearer key, one small JSON body, and a full receipt on every response.
curl https://YOUR-DOMAIN/api/ainf/inference \
-H "Authorization: Bearer $AI_INFERENCE_KEY" \
-H "Content-Type: application/json" \
-H "Idempotency-Key: order-1042" \
-d '{"prompt":"Summarise this ticket in one line","capability":"chat"}'Questions, answered
Is the service suitable for patient data?
You control what each prompt contains, and you are responsible for reviewing your own regulatory obligations before sending any personal or health information. We do not make compliance claims on your behalf.
Does it give medical advice?
No. It drafts and summarises text. Clinical decisions and anything sent to patients should be reviewed by a qualified professional.
What is stored about each request?
Request history keeps the model, token counts, latency, price and a short preview so you can audit usage.
Can we start small?
Yes. Every account has a free monthly token allowance for pilots.
Hand the routine writing to a model
Pilot on templates and policies first. Keep humans on every decision.