clay-jev-people-ranker

# TypeSafe JEV Lead Scoring with Clay CLI

An Agent Skill and Python workflow for **Clay lead scoring**, **B2B prospect qualification**, and **AI-powered people search ranking** with **TypeSafe JEV**.

## Quick answer

This project uses the official Clay CLI to retrieve people who match deterministic filters such as job title, company size, industry, seniority, and location. It then uses TypeSafe JEV to make the harder semantic decision: does each person actually match the intended role and qualification criteria?

The included JEV use case targets current operating Founders and Co-Founders. It filters false positives such as founding investors, founding employees, former founders, and people working in a Founder's Office before downstream enrichment.

The workflow is designed for GTM engineers, RevOps teams, sales operations, CROs, BDMs, SDRs, recruiters, and developers building programmable lead-qualification systems.

## What is JEV?

JEV is TypeSafe AI's first public System One model. Instead of generating long-form text, it returns typed decisions and probabilities that software can evaluate directly.

This workflow uses two TypeSafe primitives:

- **Choice** classifies the candidate as an operating founder, investor or board member, founding employee, founder-support role, or unclear.
- **Noul** estimates whether the candidate clearly and currently holds an operating Founder or Co-Founder role.

Code then applies explicit thresholds to those outputs. This makes JEV useful as a fast decision layer for classification, routing, scoring, verification, filtering, and reranking—not as a replacement for generative writing or multi-step reasoning.

Official background:

- [Introducing System One Models and JEV](https://typesafe.ai/blog/introducing-system-one-models-and-je