Drop a screenshot or paste a text exchange — saidwhat detects gaslighting, guilt-tripping, coercion, and other manipulation patterns using dimensional analysis, not keyword matching. Built from analysis of 8,400+ labeled manipulation conversations across 6 types and 4 relational contexts. Upload → Analysis → Conversation. After the analysis, you can ask follow-up questions. "Was there more context here?" or "What would a healthy version of this exchange look like?"
No reviews yetBe the first to leave a review for SaidWhat.App
Maker
📌
Hey Product Hunt — I'm Chris, veteran and solo founder of ROSE Corp.
I built saidwhat because people kept sending me screenshots of conversations asking "is this normal?" They couldn't put their finger on what was wrong, but they knew something was off.
Standard tools can't help with that. Sentiment analysis says "negative" — no kidding. Keyword matching catches "you're crazy" but misses the more dangerous kind: "I'm just worried about you" said in the right pattern at the right time.
saidwhat uses dimensional analysis. Gaslighting attacks your sense of reality (Ψ) and your selfhood (q) simultaneously — that specific combination is its fingerprint. Guilt-tripping weaponizes relational history (ρ). Each type has a mathematical signature derived from thousands of real conversations.
You paste a conversation. It tells you what's happening, which dimensions are under pressure, and what the person on the receiving end is probably experiencing. Then you can ask follow-up questions.
The philosophy is "translation, not judgment." The tool reveals the pattern. What you do with that is yours.
False positives in this space cause real harm, so the system has a built-in Veritas check — if there isn't enough data or if there's a reasonable non-manipulative explanation, it says so instead of guessing.
One veteran, one framework, one goal: help people see what they're already feeling.