Grade every demo request within hours, against standards you can read.
Every demo request is graded A to D within hours by a decision model, against standards written in plain language and drafted from your own CRM history. Your sales team reviews the grades in its own app.
Every demo request graded A to D with the reason, the owner and where follow-up stands. Overrides and notes are records with history.
Lead scoring at an AI video company
An AI video company grades every demo request this way, and its sales team reviews the grades in its own app.
Read the lead-scoring story →- Demo requests load from HubSpot through a managed connection, with the history of their properties.
- A decision model grades each one A to D against standards drafted from your own CRM history, with a one-line reason.
- Change a standard by editing a sentence, then regrade. No training pipeline.
- The sales team works the grades in its own app: owner, status, notes and overrides.
What it covers
Grades with reasons
Demo requests from HubSpot, with the history of their properties, graded A to D within hours with a one-line reason.
The sales team's review queue
Owner, status, notes and a grade override with its reason, kept in the ontology and joined to the grade.
Standards in plain language
Edit a standard and regrade the period. No retraining.
Versioned standards
Every grade records which version of the standards produced it, so old and new grades can be compared before a change is kept.
Built from typed blocks
No new product to buy: the blocks below, written by an agent into your workspace's repository and deployed with one command.
None required.
$ segmentstream deploy
Every block ships together from one git repository your company owns. SegmentStream runs it.
- HubSpot score properties
- MadKudu
- custom ML scoring
Our engineers draft the grading standards from your CRM history, check them against past outcomes with your sales team, and run grading on new demo requests.
Enterprise, with our engineers
Our engineers draft the grading standards from your CRM history, check them against past outcomes with your sales team, and run grading on new demo requests.
Self-serve, with your own agent
Connect HubSpot and tell your agent what a good lead looks like. It writes the ingestion, the grading standards and the review queue.
Related solutions
Read more
Questions
Do we need to train a model?
No. A decision model grades each lead against standards written in plain language, drafted from your own CRM history. Change a standard by editing the text.
How fast is a lead graded?
Within hours of the demo request arriving in HubSpot, on a schedule you choose.
Where do the grades live?
In your workspace's warehouse. What the sales team decides (owner, status, notes, an overridden grade) is in the ontology, joined by the HubSpot contact id.
Rather have it built for you? Start a pilot.
Our engineers draft the grading standards from your CRM history, check them against past outcomes with your sales team, and run grading on new demo requests.
- 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 software, built by agents, owned by you.
$ segmentstream workspace create acme --region eu --subdomain acme
▸ Created workspace acme · database, warehouse and a private git repository
$ segmentstream workspace WORKSPACE-ID clone acme && cd acme
▸ your agent writes the five folders and runs the checks
$ git add -A && git commit -m "First version"
$ segmentstream deploy
▸ app, ontology API and MCP tools live for your invited members
Our engineers build the first version on your data in two weeks, at a fixed price.
Or join the waitlist for self-serve:
Self-serve opens to the waitlist first.