The reading list never ends
New papers every week, and no time to read past the abstract.
For research and biotech teams
Faster from paper to protocol
Literature summaries, protocol and SOP drafts, lab notebook clean-up and structured extraction from methods sections. Spend more time at the bench and less at the keyboard.
Faster reviews
literature summarised by section
Cleaner records
notebook entries structured
You decide
exactly what each prompt contains
The problem
What is slowing you down today
SOPs that drift
The bench practice changed. The SOP did not.
Notebook entries in shorthand
Rich experimental detail, impossible to search a year later.
Capabilities
Everything you need, nothing you don't
Literature summaries
Methods, findings and limitations from the paper text you supply.
Structured extraction
Pull reagents, concentrations, conditions and outcomes into JSON.
Protocol and SOP drafts
Turn bench notes into clear, numbered procedures for review.
Reasoning-capable routing
Send analytical questions to a reasoning model and formatting to a lighter one.
Controlled access
Hashed keys, rate limits and a history of every request.
Cost per experiment
Tokens and price on every call, so grant budgets stay predictable.
Use cases
What teams run on it
01
Journal club prep
Structured summaries of this week's papers.
02
Methods extraction
Comparable tables of conditions across studies.
03
SOP updates
Redlined procedures from current bench notes.
04
Notebook clean-up
Searchable, consistent entries from rough notes.
How it works
From sign-up to production
- 1
Review your obligations
Confirm what data your policies and agreements allow you to send to an external service.
- 2
Start with published work
Summarise open literature in the playground.
- 3
Integrate with controls
Dedicated keys per lab, rate limits and request history.
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 we send clinical or patient data?
You control what each prompt contains, and you are responsible for reviewing your regulatory obligations before sending personal or clinical data. We make no compliance claims on your behalf.
Is output reliable enough for regulated documents?
Treat it as a draft. Qualified scientists should verify every protocol, figure and claim.
What about unpublished IP?
Only what you send is processed. Set internal rules for what may be shared with an external service.
How is it priced?
Per token, shown per model before you call, after a free monthly allowance.
More bench time, less busywork
Summarise this week's papers on the free allowance.