Sunday night planning
Teachers spend weekends adapting materials for every reading level in the room.
For schools, universities and edtech
More teaching, less prep
Lesson plans, differentiated materials, rubric-aligned feedback drafts and parent newsletters. Give educators time back and give edtech teams one endpoint to build on.
Faster prep
lesson plans and materials drafted
Differentiated by default
the same lesson at several levels
Clear cost per student
price on every call
The problem
What is slowing you down today
Feedback that arrives too late
Thirty essays, one rubric and a weekend. Students get comments after they have moved on.
Edtech costs that do not scale
If you build learning tools, unpredictable model bills make per-seat pricing a gamble.
Capabilities
Everything you need, nothing you don't
Lesson plan drafts
Objectives, activities, checks for understanding and exit tickets from a topic and a standard.
Differentiated passages
Rewrite a text at several reading levels while keeping the key vocabulary.
Rubric-aligned feedback drafts
Suggested comments mapped to your rubric criteria, for the teacher to edit.
Quiz and question banks
Multiple-choice and short-answer questions with answer keys.
Clear unit cost for edtech
Tokens and price on every response make per-student pricing predictable.
Cache for shared prompts
Identical prompts inside the cache window come back instantly and are not billed.
Use cases
What teams run on it
01
Weekly lesson planning
A full week's outline in your school's format.
02
Essay feedback drafts
First-pass comments for teachers to refine.
03
Parent communications
Newsletters and updates in clear, friendly language.
04
Tutoring apps
Explanations and practice questions served from your backend.
How it works
From sign-up to production
- 1
Plan one lesson
Try it in the playground with your topic and standard.
- 2
Build or connect
Call the endpoint from your learning platform with an API key.
- 3
Scale responsibly
Track usage in the dashboard and set a rate limit in settings.
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 it safe to send student work?
You control what goes into every prompt. Review your institution's privacy policies and remove identifying details before sending student content.
Will it grade for us?
It drafts feedback against your rubric. Teachers make the grading decisions.
Can edtech companies build on it?
Yes. Call it from your backend, keep keys server-side, and use per-call pricing to design plans.
Is there a free option?
Every account includes a free monthly token allowance.
Give teachers their weekends back
Plan next week's lessons on the free allowance.