Missed-pickup call spikes
One holiday schedule change and the phones do not stop.
For haulers, MRFs and recycling operators
Cleaner routes, clearer reports
Driver exception notes, contamination reports, missed-pickup replies and environmental reporting drafts. Turn the text your operation already generates into action.
Faster replies
missed-pickup and billing questions
Structured exceptions
driver notes turned into data
Less report drudgery
first drafts from your figures
The problem
What is slowing you down today
Driver notes nobody trends
Blocked bins, overloaded carts and contamination are noted, then lost.
Reporting season
Tonnage, diversion and permit narratives pile up on the same few people.
Capabilities
Everything you need, nothing you don't
Exception note structuring
Turn driver notes into address, issue type and follow-up action as JSON.
Contamination letters
Polite, clear letters to customers explaining what went wrong and how to fix it.
Customer service drafts
Replies grounded in your service schedule and policy text.
Report narrative drafts
Narrative sections built from the figures you provide, for staff to verify.
Fail-over for busy days
Requests move to another eligible model if one is busy.
Cost per call
Tokens and price on every response, so pilots have a clear budget.
Use cases
What teams run on it
01
Route exception logs
Daily summaries of issues by route and driver.
02
Contamination outreach
Customer letters and tag-message wording.
03
Contact centre assist
Suggested replies for schedule and billing questions.
04
Environmental reporting
Draft narrative for permit and diversion reports.
How it works
From sign-up to production
- 1
Paste a day of notes
See structured exceptions in the playground.
- 2
Connect your routing system
Send notes to the endpoint with an API key.
- 3
Track and adjust
Watch usage and refine prompts as volume grows.
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
Does it work with our routing software?
If your system can send an HTTP request, it can call the endpoint.
Can output feed our database?
Ask for JSON with your field names and map the response directly.
Will it write our regulatory reports?
It drafts narrative from data you supply. A responsible person should verify figures and submit.
How do we start?
Sign up, use the free monthly token allowance and test with real notes in the playground.
Turn every route note into insight
Start with yesterday's exceptions, free.