Iheb Marouani

Work02

Lead Generation Crawler

In productionEmployer

Agentic crawler that turns a filtered ICP into scored, source-attributed leads written back into the CRM.

Crawl results, scored against the profileSample data
4 leads written to the CRM
  • Planwerk Ostbau91timber spec on 3 projects, ad library hit
  • Architekten Reither84portfolio match, verified identity
  • Neubau Kollektiv72project scale match
  • Bauatelier Sund68portfolio match
  • Metallbau Krieger43sector mismatch
  • Immobilien Halbe21no verifiable identity
PrototypeAn interface sketch of this system, not a screenshot. Every figure, name and record in it is invented.
Built with
Python, Agentic workflows, Dataverse

The problem

A profile is only worth what it finds. The channel ICPs needed to become pipeline without a research team doing manual prospecting.

The system

Takes a filtered profile from the ICP engine, scans the open web for matching companies, scores candidates against the profile, and writes qualified leads into the CRM with the evidence that qualified them attached. CRM feedback on lead quality flows back to sharpen scoring.

How it is built

Agentic scraping workflow with per-source adapters, scoring against profile embeddings, idempotent CRM writes.

  1. 1

    Filtered profile

    A filtered ICP handed over from the profile engine.

  2. 2

    Open-web scan

    Agentic scraping workflow with per-source adapters finds matching companies.

  3. 3

    Scoring

    Candidates scored against the profile embeddings.

  4. 4

    CRM write-back

    Qualified leads written into the CRM idempotently, with the evidence that qualified them attached.