Correspondence backlogs
Officers spend days drafting replies that follow familiar patterns.
For public sector teams
Public service, in plain language
Plain-language notices, correspondence drafts, consultation response summaries and internal policy answers. Help teams serve residents faster, with you in control of every prompt.
Clearer notices
plain-language rewrites
Faster correspondence
first drafts for officers
Full visibility
every call in request history
The problem
What is slowing you down today
Notices residents cannot follow
Accurate but dense language drives calls, complaints and missed deadlines.
Consultations that drown teams
Hundreds of free-text responses need reading and summarising before a decision.
Capabilities
Everything you need, nothing you don't
Plain-language rewrites
Turn formal notices into clear language at the reading level you specify.
Correspondence drafts
Draft replies from the facts and policy text you supply, for an officer to review.
Consultation summaries
Group free-text responses into themes with representative points.
Visible, controlled access
Hashed keys, per-account rate limits and a record of every request.
Clear spend
Per-token prices are shown before you call, and every response reports its price.
You control the inputs
Only what you put in a prompt is processed, so you can minimise personal data.
Use cases
What teams run on it
01
Resident notices
Clear letters about services, changes and deadlines.
02
Casework replies
First drafts for officers to check and send.
03
Consultation analysis
Theme summaries to support decision papers.
04
Internal policy Q&A
Answers for staff from the guidance you provide.
How it works
From sign-up to production
- 1
Check your obligations
Confirm with your information governance team what data you may send to an external service.
- 2
Pilot with public content
Start with published notices and guidance in the playground.
- 3
Integrate with oversight
Use named keys, rate limits and request history to keep control.
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 approved for government use?
We make no compliance claims on your behalf. You control what each prompt contains, and you should review your own regulatory and information governance obligations before use.
Does it make decisions about residents?
No. It drafts and summarises text. Officers make every decision.
What is recorded about each request?
Request history stores the model, tokens, latency, price and a short preview for auditing.
Can we try it before committing?
Yes. Every account includes a free monthly token allowance.
Clearer letters, faster replies
Pilot on published content first. Officers stay in charge.