Grade every lead the moment it arrives.
Grade every demo request A to D against standards written in plain language, drafted from your own CRM history. It runs in production for an enterprise SaaS company and needs no model training or data science backlog.
Lead scores nobody trusts, from models nobody can explain.
Rules-based scoring rots within a quarter. Custom ML needs a data scientist, a training pipeline and months before anyone trusts it. Even then, nobody can explain why a lead scored 63.
Replaces HubSpot score properties and Custom ML scoring pipelines.
- Every demo request graded A to D with a probability and a reason
- Standards drafted from which of your past leads became opportunities
- Edit the standard in plain text, with no retraining
- Grades in an app your sales team opens, and back on the CRM record
How it works
- 01
Connect HubSpot
Contacts, demo requests and the history of their properties load from your CRM.
- 02
Learn from your history
Your past year of demo requests shows which profiles became opportunities, and how often.
- 03
Write the standards
Grades A to D are written as plain-language standards you can read and edit.
- 04
Grade every lead
A decision model grades each new lead with a probability; sales sees it in an app and on the record.
Enterprise, with our engineers
Our engineers connect your CRM, derive grading standards from your past deals, validate them against real outcomes, and put the grades on every record in your CRM.
Self-serve, after launch
Install the Lead Scoring app, connect HubSpot, and let it draft grading standards from your last year of demo requests. Review the standards, then let it grade new leads every day.
Install from the marketplace
Everything below installs into your workspace as code. Use it as it is, or change anything.
Lead Scoring
Grade every demo request A–D against standards you can read and edit.
App
Pipeline Analytics
Conversion, velocity and ageing for every pipeline stage.
App
Account Scoring
Grade every account against your ideal customer profile.
App
HubSpot
Contacts, companies, deals and the history of every property.
Connector
Salesforce
Leads, accounts, opportunities and field history.
Connector
Jev evaluation
A decision model for classifying and scoring records.
AI model · TypeSafe AI
Product-Led Sales
Accounts ready to buy, found in product usage.
App
Questions
How are leads graded?
A decision model reads each lead's facts (role, company, source, what they wrote) and grades it against standards written in plain language. The standards are drafted from which of your past leads became opportunities.
Do we need to retrain a model?
No. Change the text of a grade's definition and the next lead is judged by the new standard. Every grade comes with a probability and an explanation.
Which CRMs work?
HubSpot today, through a managed connection. Other CRMs are connectors our engineers or your agent can add.
Rather have it built for you? Start a pilot.
Our engineers connect your CRM, derive grading standards from your past deals, validate them against real outcomes, and put the grades on every record in your CRM.
- One solution, on your data, in your own workspace
- First version live in two weeks
- Parity proven before anything is switched off
- Fixed scope and price, credited to your contract if you continue
Not ready for a pilot? Send the form anyway with your question. An engineer will reply, not a sales rep.
How the pilot worksYour company’s context, ready for every agent.
$ segmentstream workspace create acme --region eu
▸ workspace ready · data, objects, metrics and access rules in one place
▸ connect Claude, ChatGPT or Cursor with one connector
▸ tell your agent: “add our billing API as a source”
Our engineers build the first version on your data in two weeks, at a fixed price.
Or join the waitlist for self-serve:
Pilots are open now. Self-serve opens to the waitlist this fall.