Back to Hub
Automation, AI, and AttributionCase Study 01

An Agentic Lead-Generation Pipeline That Checks Its Own Work

Make.comGeminiClaude CodeSupabaseClickUpPython

Executive Summary

Built an AI lead-scoring and outreach pipeline that sources, scores, and drafts its own outbound messages, then hands each finished message off for a person to send. The first version ran on Make.com and Gemini; the version running today was rebuilt on Claude Code as a set of Python agents, with a Supabase Postgres database as the single source of truth. Over its life it scaled throughput roughly 3x — sourcing, scoring, and drafting outbound at volume — while a person still reviews and sends every finished message.

The Challenge: Manual Work at the Limit

  • Manual bottlenecks

    Sourcing, screening, and data entry were linear manual work that capped how many leads could be handled at once.

  • Hours lost every week

    Qualification and outreach prep ate roughly 20 hours a week, a hard ceiling on scaling the pipeline.

The Solution: An Agentic Pipeline, Rebuilt to Last

  • Automated sourcing and scoring

    Scheduled collectors pull and deduplicate 100+ leads a day into one source of truth, and a model scores each against a written rubric before it reaches the board.

  • Generation that audits itself

    Two model families split the work so nothing grades its own homework: one scores, another drafts the message, and a separate pass checks that draft against the source before it ships.

  • A human sends the finished message

    The automation stops at a finished, source-checked document. A person reviews and sends it, so the pipeline is not a black box firing on its own.

The Breakthrough: Scale Without Losing Control

The pipeline moves each lead through the same path, unattended, up to the finished message — sourcing, scoring, and drafting at roughly 3x the original throughput, with a person sending every message that goes out. Hover any result to see it.

Source & dedupe
Scheduled collectors pull and deduplicate 100+ leads a day into one source of truth.
Score
A model scores each lead against a written six-dimension rubric.
Draft & self-audit
A second model drafts the outreach; a separate pass audits it against the source. Then a person sends it.
~3x throughput · self-auditing

Scaled roughly 3x

Monthly output grew about 3x — from ~344 to ~1,112 leads sourced a month and ~31 to ~133 reach-outs a month — as sourcing, scoring, and drafting moved from manual work to an unattended pipeline.

About 20 hours a week back

Automating sourcing, scoring, and drafting removed roughly 20 hours a week of manual screening and data entry, measured against 45 minutes per reach-out done by hand.

Nothing grades its own homework

One model scores the lead, a second drafts the message, and the first audits that draft against the source before it ships, with a fallback at every stage.

One source of truth

9,679 leads sourced and deduplicated into a single Supabase database, with 8,174 clearing an intentional first filter to the board. One place every number comes from.

Monthly throughput, early vs later

344
1112
Sourced / mo
31
133
Reach-outs / mo
roughly 3x the monthly throughput