flagship #3 · in development · waitlist open
tells.
what people mean when they don't say it.
opinionated ai that reads what people don't say. three cores: read a message, read a person, read a profile. forensic, sterile, ruthlessly precise — built to remove emotion from reading other humans, so you can see the signal you already feel but can't quite name.
// what tells does, in three flows
read a message
paste one message from one specific person. tells returns what they actually mean, their state right now, what they didn't say but meant, and the response they actually want vs the one they said they want.
read a person
upload a corpus of messages from one person. tells builds a forensic profile: avoidance topics, conflict patterns, manipulation signals, attachment markers, truth vs lying linguistic tells, strengths, six-month trajectory.
read a profile
drop a linkedin, twitter, instagram, tiktok, or dating-app url. tells returns the gap between performed self and actual self — what they curate, what they avoid, what they would say yes / no / "let me think" to.
join the waitlist.
we open access in waves as the cores harden. tell us which one you'd open first — we prioritise concrete uses over "just curious".