We won the Open Agentic AI Innovation Award at the first AAIF Technical Excellence Awards.We won the Open Agentic AI Innovation Award Read why

AI lead scoring that shows the reasons for every score

Every inbound lead researched, scored and routed

An agent checks each new lead against your ideal customer profile and routes it in the CRM, and a person approves the handoffs you choose.

Book a free consultation How we build agents
inbound-leads

  1. Research agentAgent

    1. crm.get_lead form answers and source
    2. web.fetch_company site, sector and team size
    3. crm.get_history past deals with the account

    A new demo request is enriched with company data and the account's history in your CRM.

  2. Scoring agentAgent

    1. scoring.apply_rules your fit criteria, in code

    Strong fit on sector and team size, but the buyer is outside your sales territories. Should it go to a rep?

    Needs a personLead outside your territoriesStrong fit on every other criterion
    Approved by Head of sales

  3. Routing agentAgent

    1. crm.assign_owner account executive by region
    2. crm.log_score score with its reasons

    Lead assigned with the score and its reasons, so the rep sees why it ranked high before the first call.

Example data. An agent at work in a team channel, with a person approving the step you choose.
Mixam: conversion to a final sale from about 20% to about 40%
Where agents help

Sales time goes to leads that were never a fit.

Agents do the research and the scoring, and your team decides who gets a call.

  1. 01

    Where it stallsReps research every lead by hand before calling.

    What we do An agent gathers form answers, company data and CRM history into one note per lead.

  2. 02

    Where it stallsNobody trusts a score they cannot explain.

    What we do Your fit criteria live in code, and each score lists the criteria a lead passed and missed.

  3. 03

    Where it stallsGood leads wait while reps sort the rest.

    What we do Agents score and route each lead as it arrives. Leads outside your rules go to a person.

What we build

What we build for lead scoring

Whatever comes in, every project is built from the same parts below, set up for your files and your systems.

Leads we score

  • Inbound form fills
  • Demo requests
  • Event and webinar leads
  • Website visitors
  • Partner referrals
  • Content downloads
  • Outbound replies
  • Existing accounts

How we build it

  • Lead research and enrichment

    Form answers, company websites and CRM history gathered into one note for each new lead.

  • Fit rules in tested code

    Your ideal customer profile written as rules and checked against deals you already won and lost.

  • CRM and inbox connections

    Scores, owners and notes written to your CRM with the access rights you set.

  • Routing rules your sales team agrees

    Territory and handoff rules agreed with your sales team and enforced in the system.

Not seeing your case? Tell us where your leads come from and we start from that pipeline.

Tell us about your workflow
How we build agents

Agents that work as part of your team

They work in the tools your team already uses, take on whole tasks and stop for a person where you decide.

  1. Routines: agents that start on a schedule, on new GitHub issues or on an API delivery.
  2. Connected systems: GitHub, Linear, Notion, Slack, Jira and other tools an agent may call, each connected with its own sign-in.
  3. Approvals log: each action that waited for a person, with who asked, who decided and when.
Routines: agents that start on a schedule, on new GitHub issues or on an API delivery.
Connected systems: GitHub, Linear, Notion, Slack, Jira and other tools an agent may call, each connected with its own sign-in.
Approvals log: each action that waited for a person, with who asked, who decided and when.

Screens from the workspace our agents run in, with example data.

Where it runs

Teams and industries that use it

Each page shows where agents fit in that team or industry.

Engineering in the open

We help build what agentic AI runs on

Open standards, open-source tooling and published research, all public, so you can check our engineering before you hire us.

Shaping agentic AI

Agentic AI Foundation

Vstorm was the first agentic AI engineering company to join the Agentic AI Foundation and received its 2026 Open Agentic AI Innovation Award.

Read the announcement

Open source

We build open-source agent tooling that other engineering teams install

10M+ PyPI downloads
4,000+ GitHub stars
33 public repositories

Framework contributors

When the framework breaks, we fix it at the source

We maintain our own open-source agent framework and contribute fixes to the frameworks our agents run on, through official partnerships with their teams. Breaking changes reach us before they reach your codebase.

Research

Our engineers and PhDs publish peer-reviewed research

Peer-reviewed papers on agent architectures, evaluation and AI security, and an open benchmark anyone can rerun against our results.

Track record

Frontier AI teams now build on what we shipped first

Our client agents were in production before most of today's agent frameworks had a stable release. You get a team that already knows what breaks between a promising demo and a system people rely on every day.

Case studies
All case studies
Engagement models

Ways to start

Each path starts with a free call with a founder or senior AI engineer. A build goes ahead only after its Proof of Value meets the agreed threshold.

Start with one workflow

We map one workflow with your experts and agree a success threshold before any build.

Best whenYou want the success test agreed before you commit to a build.

Book a free consultation
  1. Process redesign and build Best whenYou want one team accountable for the outcome.
FAQ

AI lead scoring, answered

What is AI lead scoring? +
AI lead scoring uses an agent to research each new lead, compare it with your ideal customer profile and give it a score with the reasons behind it. The agent reads form answers, the company website and CRM history, applies your fit rules in code and routes the lead to the right owner. Your sales team sets the rules and decides on leads that fall outside them.
Which leads suit AI lead qualification first? +
Start with inbound leads from forms and demo requests, where reps research before they know whether to call. Pick one source and one product line, write the fit criteria down with your sales team and test the agent on leads you have already won or lost. When its scores match your team's judgement on those past leads, add the next source.
Have you built AI lead scoring before? +
We have no published case on lead scoring yet. The closest builds work on the same inbound sales flow. Senetic's inbound sales email is answered in real time, in the customer's language, across 151 countries. Over 96% of Mixam's web-to-print orders are handled end to end without human help. For an engraved die maker, pricing went from about 30 minutes to a few clicks.
How do you keep AI lead scores explainable? +
The fit criteria sit in code your team can read and change, and the model gathers and reads the evidence. Each score lists the criteria a lead passed and missed, with the source for each one, such as a line on the company website or a past deal in the CRM. Every score is logged, so you can compare it later with what happened to the lead.
How do you know it works before the full build? +
We agree a success threshold with your team before the build and test the agent on your own cases in a Proof of Value. It measures accuracy and running costs, and the build goes ahead only when the threshold is met. Corrections from your team go back into the test set, so every later version is checked against them.
Who owns the system, and which models does it run on? +
You own the code, prompts, evaluation sets and rules by contract. The agents run in your environment on hosted or open-weight models. The model sits behind an interface in code, so you can change it when accuracy, speed or your hosting rules change, without rebuilding the agent.
Start with one workflow

Test one workflow on your own data

A Proof of Value shows accuracy and running costs before the full build.

Book a free consultationRead case studies