Research eats selling time
Reps spend the morning reading websites and old notes instead of talking to buyers.
For revenue teams
Pipeline at the speed of a good rep
Research the account, personalise the first line, summarise the discovery call, update the CRM. Let models do the busywork so your reps spend their day selling.
Faster prep
account briefs before the next call
Real personalisation
first lines grounded in your notes
Clean CRM
call notes summarised and structured
The problem
What is slowing you down today
Generic sequences
Merge tags are not personalisation. Prospects can tell, and reply rates show it.
Notes that never reach the CRM
The discovery call was great. The record says 'good call, follow up'.
Capabilities
Everything you need, nothing you don't
Account briefs on demand
Send your notes and public context in the prompt and get a one-page brief with likely priorities and questions.
Personalised openers at volume
Generate a tailored first line for every contact in a sequence, priced per call so you know the cost per touch.
Structured call summaries
Ask for JSON with next steps, objections and stakeholders, ready to post into your CRM fields.
Sequences that keep moving
Automatic fail-over means a busy model does not stall a batch of outreach.
Cost per touch
Every response carries its price, so your workflow can log what each email, brief or summary cost.
Lighter models for light work
Route formatting and classification to the lowest-priced chat model, and save heavier models for strategy.
Use cases
What teams run on it
01
Pre-call briefs
A tight summary of the account, open opportunities and the questions to ask.
02
Outbound personalisation
First lines and P.S. notes written from what you actually know about each prospect.
03
Discovery call recaps
Pain, budget signals, timeline and next steps pulled from your transcript.
04
Objection handling drafts
Suggested responses to common pushback, written in your team's voice.
How it works
From sign-up to production
- 1
Try a brief in the playground
Paste call notes and see the summary, tokens and price instantly.
- 2
Connect your sales stack
Call the endpoint from your CRM workflow or automation tool with a bearer key.
- 3
Roll out to the team
Watch daily and month-to-date usage in the console as more reps lean on it.
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
Does it read my CRM automatically?
No. You decide what goes into each prompt, typically via your own workflow or automation tool, and the model works only from that.
Can I get output in a fixed format?
Ask for JSON or a template in the prompt. Many teams map the result straight into CRM fields.
How much does a personalised email cost?
Each response includes its exact price, and the catalog shows per-token prices for every model before you call.
Can I limit how much a tool can use?
Accounts have a requests-per-minute rate limit you can set in settings, and every call is visible in history.
Give every rep a research assistant
Start free, measure cost per touch, scale with the pipeline.