The truth was in the texts the whole time.
Upload a real conversation and a council of up to 10 different AI models reads it independently, then hands you their consensus on the red flags, communication patterns, and attachment styles hiding in how they talk to you. Instant. Private. Built on AI that never stores a single word.
10 AI minds. One honest verdict.
Most apps ask a single AI. We convene a council of up to 10 different AI models — each built and trained by a different lab — to read your conversation independently. Then we hand you their consensus. No single model's blind spot. No one voice to fool.
You're not crazy. You're just missing the pattern.
When you're inside it, the same messages can mean ten different things. From the outside, the pattern is obvious.
One minute they adore you, the next you're the problem. You can never tell which version you'll get.
You re-read the same texts at 2am, trying to figure out what's actually real.
Everyone says "trust your gut" — but your gut keeps getting talked out of it.
The patterns are sitting right there in your messages. We help you see them clearly — with the receipts.
Clarity in three steps. About 60 seconds.
Export your chat
In WhatsApp, open the chat → Export Chat → Without Media. You get a simple .txt file. Takes ten seconds.
Upload it privately
Drop the file in. It's analyzed in-memory on a no-retention AI and never written to a database. Ever.
The council reads it
Up to 10 different AI models read your chat independently and vote. You get their consensus score with the exact quotes behind every flag — plus a chat that has read the entire conversation.
Not vague vibes. A real, evidence-based read.
A council of up to 10 AI models
Up to 10 different AI models, each trained differently, read your chat independently — then we give you their consensus. One read, ten minds.
Red-flag score
A clear 0–100 read on how concerning the patterns are — not a guess, a measurement.
Evidence, not opinions
Every single flag is backed by the actual messages. You see exactly why.
Attachment styles & risks
See whether they — and you — lean secure, anxious, or avoidant, and the risks that come with it.
Honest about both sides
It reads your patterns too. Built for growth, not ammunition.
Chat with your texts
Ask "is this gaslighting?" and get a grounded answer, with quotes.
Truly private
No-retention AI. Your messages are never stored or used to train anything.
This is what clarity looks like.
A real report names the pattern, scores the severity, and shows you the messages behind it.
Your most private conversations stay private.
This is the most personal data you own. We treat it that way.
- No-retention AI. Analysis runs on AWS Bedrock under a no-retention configuration: your messages are never used to train any model.
- Raw messages, never stored. Your conversation is processed in memory to build the report and is never written to our database.
- Your reports, your control. Saved reports are encrypted at rest, tied to your account, and you can delete any of them anytime.
- No account to start. Get your first read without signing up.
never stored.
Start free. Go deeper for the price of a coffee.
See if there's something here.
- ✓ Your red-flag score
- ✓ Your first flag, with evidence
- ✓ Fully private
The whole picture.
- ✓ 10 full reports every month
- ✓ Every red flag, with the evidence
- ✓ Both attachment styles + your own patterns
- ✓ Unlimited chat-with-your-texts
- ✓ Need more? Credit packs (10 / 20 / 50) — cheaper the bigger
Ready to stop second-guessing?
Drop in a WhatsApp export and get your read in about a minute. Private the whole way.
How do I export a WhatsApp chat?
- Open the chat in WhatsApp
- Tap the contact name → Export Chat
- Choose Without Media
- Save / AirDrop the file, then drop it here
📸 iMessage / iPhone: screenshot the conversation (scroll and grab a few), then drop the images above — we read who said what from the bubble colors.
🖥️ On a Mac: open Terminal and paste this one line (no download, no security prompt):
curl -fsSL https://checkforredflags.com/imessage-mac.command -o /tmp/cfrf.command && bash /tmp/cfrf.commandPick a chat — it copies it to your clipboard, then paste above. (If it can't read Messages, grant Terminal Full Disk Access and rerun.)
🔒 Analysis runs on a no-retention AI. Your raw messages and screenshots aren't stored.
Everything you're probably wondering.
Is this actually private?
Your raw messages are processed in memory to build the report and are never saved to our database or used to train any model (analysis runs on AWS Bedrock, no-retention). Your generated reports are saved to your account encrypted so you can revisit them — and you can delete any of them anytime. No account is required to get your first read.
Is this a medical or psychological diagnosis?
No. It's an informational read on communication patterns, backed by the actual messages — not therapy and not a clinical diagnosis. It describes behaviors and patterns; what you do with that clarity is up to you.
What if I use iMessage?
Use the paste box on the uploader: open the chat, select the messages, copy, and paste them in — no export needed. WhatsApp's "Export Chat" .txt also works. (Native iMessage/screenshot import is on the way.)
Will the other person know?
No. You're analyzing your own conversation. Nobody is contacted or notified.
How accurate is it?
Every flag is tied to specific quotes, so you can judge each one yourself. It surfaces patterns with evidence — it doesn't pretend to read minds. You stay the decision-maker.
Can I cancel or get a refund?
Pro is $3.99/month and you can cancel anytime from the billing portal. See our Refund Policy for the 7-day refund window.
Trust your gut. Then check the receipts.
Get an honest, evidence-based read in about a minute — completely private.
Check my texts — freeWhich one is you?
We found these people in the chat. Tap your name so we know whose side is whose.
10 AI models are reading your chat
0 of 10 models have weighed in