How Checkobot works
Every check runs the same way. Here is what happens to an image and how the verdict is decided.
Two detectors
- Whole-image analysis looks at the entire picture for patterns typical of AI image generators and editors. It runs on every image.
- Face analysis is a dedicated face-forensics model for face swaps, AI face edits and synthetic faces. It runs when the image has a clear face.
The verdict
If either detector crosses its threshold, the verdict is AI and the result names the detector that fired. Otherwise it's No AI detected.
No AI detected means neither detector found signs at its threshold. Some AI images score under it, so we never label anything as untouched.
On accuracy
We don't quote a single "accuracy" number. A detector's results depend on its thresholds and on what it's tested on.
What we refuse
- Images under 256 pixels on the short side.
- JPEGs compressed below roughly quality 50.
- Files over 20 MB, and formats other than JPEG, PNG, WebP, AVIF, GIF, BMP and TIFF. HEIC photos from iPhones aren't accepted yet: export them as JPEG first.
- A refused image doesn't count against your free checks.
Versions
Every check records the model and the rules it was checked with, and the API returns both with each result. When either changes, old results keep the version they were made with.
What we store
We keep a SHA-256 fingerprint of each file, the verdict and the detector scores, so a result page can be shown and mistakes can be investigated. On free checks the image itself is checked in memory and discarded. Paid plans keep checked images in the owner's history (web checks by default, with a switch to turn it off; API keys only when asked).
What it's not for
- Audio, live video or liveness (printed photos held up to a camera, screen replays).
- IDs and documents, for now. ID and document checks are coming soon.