About
Trust, with the receipts attached
Synthetic images are now good enough that looking closely does not work. Sens exists so that anyone, not just forensics experts, can ask “is this AI?” and get an answer that explains itself.
Sens is built by Sens Center, Inc., a small, independent, self-funded team. It started as a platform for publishing data and research. Along the way the hardest problem turned out to be the one everyone shares: knowing whether what you are looking at is real. Checking content for AI generation is now the whole product, for images and for text.
Evidence over scores
A single percentage hides more than it shows. Every Sens verdict lists the signals that produced it, how strong each one is, and what could not be checked. When only the visual detector has an opinion, the verdict says so.
Private by design
Checks run in your browser. The file never leaves your device unless you sign in and choose to save a report. AI summaries are generated from the extracted metadata, not the image.
Standards first
Signed Content Credentials (C2PA) are the strongest evidence available and Sens treats them that way. Detectors fill the gaps when provenance has been stripped, with the caveats spelled out.
Open and in the open
The code is on GitHub, the Chrome extension is open source, and the detector is benchmarked against a labeled public corpus so its accuracy claims can be checked. If a verdict is wrong, tell us: it is how the detector gets better.