Be Your Own Freud
Six thinkers, six different ways of listening
Product Design · Concept · Build · 2026
Problem
AI therapy keeps converging on the same vaguely-warm chatbot. The neutrality is the problem.
Most LLM-therapy products refuse a point of view, and the result is a flat experience with no register to lean into. Be Your Own Freud is the opposite: six historical thinkers as advisors with distinct philosophical positions — Freud, Jung, Marcus Aurelius, Nietzsche, Laozi, Socrates — presented like editorial covers in a content library you'd pick a film from.
Apple-TV chrome, not chatbot chrome
Full-bleed portrait of this week's advisor, one line of their thinking, one button. The interface borrows from a media library because choosing a film is a less stigmatised gesture than asking a chatbot for help.
Each advisor has a point of view
Sigmund Freud reads everything as conflict between conscious and unconscious. Aurelius reframes through duty and impermanence. Laozi answers with paradox. Same user message, meaningfully different replies — because the prompts are doing real work, not styling.
Voice first, words second
Sessions open with 'What is troubling you?' and a single tap-to-speak microphone. Writing is the secondary input. The framing borrows from being heard rather than being assisted — the advisor is listening, not problem-solving.
The library
Six thinkers, six different ways of listening
Freud — Psychoanalysis
Jung — Analytical psychology
Aurelius — Stoicism
Key Insight
The chrome reframes the interaction
Visual register matters more than the engine. The underlying LLM call could be identical across all six advisors and the experience would still differ — because the user opens the app expecting a session, not a query. Editorial scaffolding does work that prompt engineering alone cannot.
The Journal — every insight you saved, kept in the voice of the advisor who delivered it. Filter by advisor to see how each one of them speaks differently inside your own life.
Stack & Tools
AI
design
code
Reflection
What I’d revisit
The 'Mirror' phase — a planned moment where the user's face is shown alongside a ghosted overlay of the advisor's visage during the session — is currently a styled placeholder. Real MediaPipe face-tracking would change the emotional weight of the session in ways the static comp can only hint at. Phase 2 work.
Next