Unbillable drafting
Senior people spend evenings formatting proposals and rewriting status reports nobody reads closely.
For consultancies, agencies and firms
Bill for insight, not first drafts
Proposals, statements of work, research memos, meeting minutes and weekly status reports. Let models handle the first pass so your people spend billable hours on judgment.
Faster proposals
from discovery notes to draft
Cost per client
price returned on every call
Consistent quality
your templates in every prompt
The problem
What is slowing you down today
Knowledge stuck in heads
The best engagement summary lives in one partner's inbox. New staff start from scratch.
AI spend you cannot recharge
When AI helps on a client engagement, you need to know what it cost to pass it through fairly.
Capabilities
Everything you need, nothing you don't
Proposal and SOW drafts
Feed discovery notes and your template, get a structured draft with scope, assumptions and timeline sections.
Meeting minutes that matter
Turn a transcript into decisions, owners and dates your client can sign off.
Cost per engagement
Every response returns tokens and price, so you can log cost against the client or matter it belongs to.
Reasoning on demand
Route analysis-heavy work to a reasoning-capable model and routine edits to a lighter one.
Repeat requests at no charge
Identical prompts inside the cache window are served from cache and not billed.
You control the inputs
Nothing goes to a model except what your prompt contains, so your team decides what client material is used.
Use cases
What teams run on it
01
Proposal first drafts
Executive summary, approach and timeline from your discovery call notes.
02
Weekly status reports
Progress, risks and next steps compiled from your team's updates.
03
Research memos
Structure findings from source excerpts into a clear memo with open questions.
04
Engagement close-outs
Lessons learned and reusable assets captured before the team moves on.
How it works
From sign-up to production
- 1
Build your prompt library
Refine prompts for proposals, minutes and reports in the playground.
- 2
Issue keys by practice
Give each team its own key, and log the price on each response against the client it served.
- 3
Integrate where you work
Call the endpoint from your document tools or automation platform.
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 I attribute AI cost to a client?
Yes. Every response includes its tokens and exact price, so your integration can record cost against the client or engagement that triggered it.
What about confidential client material?
You choose exactly what goes into each prompt. Check your engagement terms and professional obligations before sending sensitive content.
Can it follow our house templates?
Include the template and an example in the prompt and ask the model to fill it.
How is usage billed?
Per token at the catalog price for each model, after a free monthly allowance. Metered usage is invoiced every 30 days.
Give your experts their evenings back
Start with the free allowance and a single proposal. See the difference by Monday.