Storm-day inbox floods
Thousands of customers ask the same question while your team is stretched thin.
For power, water and gas operators
Keep the lights on, and customers informed
Clear outage updates, tidy field notes, faster customer replies and first drafts of the long reports nobody enjoys writing. Built to keep up when the storm hits.
Faster updates
outage messages drafted in moments
Readable field notes
crew shorthand made clear
Steady under surges
fail-over when demand spikes
The problem
What is slowing you down today
Field notes in shorthand
Crew notes are terse and inconsistent, which makes asset history hard to trust.
Report season
Rate cases, reliability reports and board updates eat weeks of engineering time.
Capabilities
Everything you need, nothing you don't
Outage communication drafts
Send the incident facts and get SMS, email and web versions in a calm, consistent voice.
Field note clean-up
Expand crew shorthand into full asset records with location, work done and follow-ups.
Customer reply drafts
Answer billing and service questions from your own policy text, for agents to send.
Fail-over during peaks
If a model is busy when everyone needs answers, the request moves to another eligible model.
Cache for repeat questions
Identical prompts inside the cache window return instantly and are not billed.
Controlled, audited access
Hashed keys, rate limits and request history for every integration.
Use cases
What teams run on it
01
Outage notices
Consistent updates across channels as restoration estimates change.
02
Work order summaries
What was found, what was done and what remains, per asset.
03
Contact centre assist
Suggested replies for agents handling high-volume enquiries.
04
Regulatory report drafts
Narrative sections drafted from your data for engineers to refine.
How it works
From sign-up to production
- 1
Draft a notice in the playground
Paste incident facts and compare channel versions.
- 2
Integrate with your OMS or CRM
One authenticated HTTP call from your existing systems.
- 3
Prepare for peaks
Set rate limits per account and watch usage live in the dashboard.
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
Can it handle storm-day volume?
Requests are routed across eligible models with automatic fail-over. Your account's rate limit sets the ceiling, which you can adjust in settings.
Does it connect to our outage system?
It is a single HTTP endpoint, so any system that can make a web request can use it.
What about critical infrastructure data?
You decide what goes into each prompt. Keep sensitive operational detail out unless your policies allow it.
How is it billed?
Per token at the price listed for each model, after a free monthly allowance.
Be ready before the next storm
Set up your outage templates today, free.