AI User Personas
Local-first workspace to create and version structured user personas — goals, frustrations, evidence with provenance, and a synthetic-vs-real confidence meter.
The Problem
User personas tend to be either over-polished marketing fiction or scattered notes nobody trusts. The missing piece is provenance: which claims about a user are backed by real interviews or analytics, and which are educated guesses? Without that, teams can’t tell a grounded persona from a synthetic one, and personas quietly drift from evidence.
What I Built
A local-first workspace for creating, editing, filtering, and archiving structured user personas. Each persona is a validated record — archetype, role, summary, goals, frustrations, motivations, behaviors, needs, use-case scenarios, tags, and a draft/active/archived status — backed by a JSON Schema as the canonical domain model.
Evidence and Confidence
The differentiator is evidence provenance. Every persona carries evidence items tagged by source — interview, survey, analytics, or synthetic — and a ConfidenceMeter surfaces how much of the persona rests on real data versus assumption. A persona seeded from a product thesis reads as 45% confidence with its evidence flagged synthetic, so no one mistakes a hypothesis for a finding.
The v1 architecture is human-authored through a validated form, with the schema and evidence model already shaped to accept an AI-assisted generation pipeline (raw inputs → evidence items → persona draft → review) as the next step.