02 / PUBLIC-SAFE MATCHING LAB

A useful introduction. Not a verdict on a person.

Change the inputs and see different reasons to connect. This is a categorical teaching model—not the production matching algorithm.

The experience is public. The recipe isn’t.Production weights, thresholds, scoring formulas and group optimization are deliberately excluded.

YOUR SAMPLE SIGNALS
Things you enjoy
Your chapter
Social energy

Illustrative people and signals. Nothing is saved to the live product.

WHICH PRODUCT QUESTION MATTERS?
Maya

Maya

A starting point for this lens

PilatesRestaurantsNew-ish to NYCA lively table
Rhea

Rhea

A starting point for this lens

PilatesA lively table
Nina

Nina

A starting point for this lens

RestaurantsNew-ish to NYC

Maya & Rhea & Nina: a conversation to explore.Shared interests are an opening—not enough to guarantee group fit.

What the real system has to handle

01

Structure

Capture explicit interests, intent and context.

02

Constrain

Respect eligibility, membership and event-specific rules.

03

Consider the group

Think beyond a strong pair to the experience around the table.

04

Explain & review

Show grounded commonalities; allow host review in the Delhi pilot.

Public architecture summary. NYC and Delhi have separate flows and matching implementations.