Skip to content
~/robynrocha.io
cd /systems

targeting-store/2026

Sub-Segment Store & Fit Filter

# The whole vertical scored and graded before any sourcing

context
Solo build
role
GTM Engineer
stack
Python · Claude Code · Postgres

Maps a vertical before any sourcing happens: sub-segment types, the buyer profiles inside them, the pairs that actually transact, and the economics of each. A weighted fit filter scores every segment on follow-up potential, reach, lifetime value, cycle length, and order frequency, then cuts the result into bands. Every later classification reads the grade as a lookup instead of re-deciding it.

$render targeting-store.mmd

No diagram code provided

rendering diagram…

T1the workflow

Graded Targeting Store

Before any sourcing happens, the vertical itself gets mapped: its sub-segment types, the buyer profiles that sit inside them, the pairs that actually transact, and the economics of each. A fit filter scores every sub-segment on a weighted blend of follow-up potential, reach, lifetime value, sales-cycle length, and order frequency, then cuts the result into bands.

The expensive mistake in outbound is deciding who is worth contacting one account at a time, inconsistently, forever. Doing it once at the segment level means that later, when a crawled site is classified, the grade is a lookup rather than a judgement call. Thousands of downstream decisions inherit one deliberate decision instead of re-litigating it under time pressure.

the full write-up

Workflows at this stage1