Menus written at 1am
New seasonal menu tomorrow, and the descriptions still say 'chicken, sauce, greens'.
For restaurants and restaurant tech
More time on the floor, less at the laptop
Menu engineering copy, review replies, shift notes, allergen-aware descriptions and catering quotes. Hand the writing to a model and get back to your guests.
Mouth-watering menus
descriptions that sell the dish
Every review answered
thoughtful replies in minutes
Tighter shifts
clear notes from FOH to BOH
The problem
What is slowing you down today
Review guilt
You know you should reply to every review. Service comes first, every time.
Shift notes on a napkin
The walk-in was running warm and the 86 list changed. The closing team never heard.
Capabilities
Everything you need, nothing you don't
Menu engineering copy
Describe your stars and puzzles so they sell, from your ingredients and the story behind each dish.
Review reply drafts
Warm, specific responses that thank regulars and handle complaints with grace.
Shift note summaries
Turn rushed notes into a clean handover: 86 list, prep status, equipment issues, VIPs.
Catering and event quotes
Draft proposals from your packages, headcount and the client's brief.
Built for restaurant tech
POS, reservations and ordering platforms call one endpoint, with price on every call.
Cheap where it can be
The router picks the lowest-priced model that can do the job.
Use cases
What teams run on it
01
Seasonal menu launches
Descriptions, specials board copy and social posts for the new menu.
02
Review replies
A response for every review across your listings.
03
FOH and BOH handovers
Shift notes everyone actually reads.
04
Prep list drafts
Prep lists drafted from covers forecast and par levels you provide.
How it works
From sign-up to production
- 1
Rewrite one dish
Paste ingredients into the playground and taste the difference.
- 2
Bring in your tools
Connect your POS or ops platform with an API key.
- 3
Roll out to every location
A key per site, with usage tracked 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
Do I need to be technical?
Not to start. The playground works in your browser. Your tech provider can wire up the endpoint later.
Can it handle allergen information?
It writes from the ingredients you give it. Always have a staff member verify allergen details before publishing.
Will review replies sound like us?
Include your tone and a couple of past replies. Approve each draft before posting.
What does it cost?
Per token, shown for each model before you call. Every account starts with a free monthly allowance.
Get back to the pass
Rewrite tonight's specials board in a minute. Start free.