ML Clustering · LangGraph · ProductLoop

Persona Validator

Stop building for imaginary users. ML clustering generates real segments from behavioral data, then AI agents stress-test your feature ideas against them.

The Problem

Most personas in product teams are fiction. Someone interviewed 5 users a year ago, wrote up "Marketing Mary" and "Developer Dave," and the team has been building for them ever since. The segments don't reflect real behavior, and feature decisions based on them are essentially guesswork.

The Approach

Two-phase system. First, ML clustering on actual behavioral data (usage patterns, engagement signals, conversion paths) to generate data-backed segments. Second, 6 LangGraph agents that take these validated personas and stress-test feature ideas against them: "Would this segment use this feature? What would break?"

The agents argue with each other — one advocates for the feature, another plays devil's advocate, a third evaluates from a business viability angle.

The Result

Working MVP tested on real product data. Personas you can actually trust because they're derived from behavior, not interviews. Feature validation that catches blind spots before engineering starts building.

My Role

Concept to MVP, solo. Designed the validation framework, built the ML pipeline, the 6-agent system, and the Streamlit interface.

More projects
← Back to the interactive portfolio
Hlib Havryliuk · Senior AI Product Manager · Berlin & Vancouver · Email · GitHub · LinkedIn