Back

INTOFLOW

Intoflow is an AI platform where a single agent runs the whole UX research cycle on its own — from the brief and recruiting respondents to live interviews, transcription, analysis, and a ready report. I started it as a side project so my team could run user research fast, without spending weeks on manual work.

Position
Designer, Frontend Developer
Sphere
AI / UX Research (SaaS)
Years
2025 – now
Services
Product vision
UX/UI Design
Frontend
Branding
Design System
Overview

Good UX research takes time. You have to find the right people, schedule and run every interview by hand, then spend days reading transcripts and writing up what you found. Intoflow takes that whole cycle and hands it to one AI agent.

Instead of hiring researchers and stitching tools together, the user describes the study once. The agent prepares the interview guide, talks to respondents in real time, transcribes and translates the conversations, analyses them, and turns everything into a report with insights, quotes, and an answer for every hypothesis.

Goal

Make the UX research cycle faster and cheaper without losing quality. The product is built for product teams, researchers, and startups that need quick customer development but don't have weeks to spend on it.

My role

This is my own side project. I owned the product vision and built it end to end:

  • Shaped the product idea and how the whole flow should work
  • Designed the entire UX/UI from scratch
  • Created the brand and the design system
  • Vibecoded the complete frontend on my own using AI tools, until it became a working product
  • Built it for my team to run fast UX research
How it works

The flow follows the same steps a researcher would, just automated:

  • Set up the study — a five-step form: context, goal, tasks, audience, and hypotheses. The AI suggests hypotheses based on what you enter, and you can edit them.
  • Prepare the interview — the AI generates an interview guide and a public link for respondents.
  • Collect interviews — respondents open the link, pick their language, and talk to the AI agent in real time. You can also upload audio or video from interviews you already ran.
  • Automatic processing — every interview is transcribed, translated when needed, and analysed.
  • Results — a full report with respondent profiles, a carousel of supporting quotes, a verdict on each hypothesis, and an AI chat to ask questions about the data.
Key features
  • Voice AI interviews in real time, in more than 10 languages
  • Automatic transcription, translation, and analysis of every interview
  • Auto-generated reports with insights, respondent profiles, and quotes
  • Hypothesis evaluation — confirmed or rejected, broken down by respondent
  • AI chat over the research data, with streaming answers
  • Workspaces for team collaboration and shared studies
  • Workspace branding shown to respondents — logo and brand colour
  • Token-based billing, with a quote shown before every paid operation
How it's built

The frontend is built on Next.js and Tailwind CSS, with React Query for server state, Jotai for local state, and Server-Sent Events for streaming AI chat. The AI interviews run through a voice agent, and LLM providers power the hypotheses, guides, analysis, and reports.