PersonasPlus
by @wagborba
Generate synthetic user personas with AI from behavioural parameters and real data (NPS, feedback, call transcripts), then interview them in a real-time streaming chat.
Installation & usage
README summary
Generate synthetic user personas with AI from behavioural parameters and real data (NPS, feedback, call transcripts), then interview them in a real-time streaming chat.
Generate synthetic user personas with AI and interview them interactively. Build detailed personas from behavioural parameters and real inputs — call transcripts, NPS reports, feedback exports — then talk to them in a real-time streaming chat. A 5-step wizard for behavioural persona parameters. Upload real documents (PDF, DOCX, XLSX, CSV, TXT) to ground a persona. Interview mode: SSE streaming chat, notes and export. Multi-provider: OpenAI, Anthropic (Claude), Google Gemini and DeepSeek. API keys and default models managed in the app UI (stored locally, never exposed to the frontend). Stack: Next.js 14 (App Router), TypeScript, Tailwind CSS, Prisma + SQLite, Zustand.
Auto-extracted from the repository README. The authoritative steps live in the repository on GitHub.
Full README
PersonasPlus
Generate synthetic user personas with AI and interview them interactively. Build detailed personas from behavioural parameters and real inputs — call transcripts, NPS reports, feedback exports — then talk to them in a real-time streaming chat.
What's inside
- A 5-step wizard for behavioural persona parameters
- Upload real documents (PDF, DOCX, XLSX, CSV, TXT) to ground a persona
- Interview mode: SSE streaming chat, notes and export
- Multi-provider: OpenAI, Anthropic (Claude), Google Gemini and DeepSeek
- API keys and default models managed in the app UI (stored locally, never exposed to the frontend)
Run it
npm install --legacy-peer-deps
cp .env.example .env.local
npx prisma migrate deploy
npm run dev # http://localhost:3000
Stack: Next.js 14 (App Router), TypeScript, Tailwind CSS, Prisma + SQLite, Zustand.