Warden reads the comments on a page and rewrites the hostile ones, so the argument survives and the abuse does not. It runs as you scroll, in place, with no separate dashboard to check.
Free tier: 40 rewrites a day, no card required.
What it actually does
Warden reads the worst thing in a comment and rewrites it. Hate — slurs, threats, dehumanization, attacks on who someone is — is met with a firm, human boundary. Hostility — mockery, contempt, personal abuse — is turned into a plain, civil version that keeps the real point. Ordinary negativity, complaints and opinions are left alone. Every rewrite below is live output from the service.
"those inbred hillbillies aren't even real people, they're basically animals"
"People are people, whatever the disagreement."
Firm boundary"the service here was appalling and the staff clearly couldn't care less about customers"
"The service was appalling and the staff didn't care about customers."
Neutral · point keptHow it works
When a page loads, Warden collects the comment text you can see on it. Nothing from other tabs, nothing from your history, and no images.
Ordinary text is discarded before any judgement is made — on a normal page that is roughly two thirds of it. Only what survives that filter counts against your daily allowance.
What remains is sent to a large language model with a prompt written and tested for this one task. Anything it flags is rewritten in place, next to the comment that triggered it.
Three settings: attacks on people only, all hostility, or anything negative at all. You can change it at any time, and the page updates without re-reading anything.
What it is, plainly
Comment text is sent to Google Cloud (Vertex AI) in the EU — servers in the Netherlands, with our service hosted in London — to be judged. It is not processed on your machine. We do not store the text of the comments we judge, and we never sell data. Read the privacy policy.
Warden runs on a general-purpose language model. What is ours is the prompt, the guard rails around it, and the test suite that keeps it honest — not the model weights.
It sometimes rewrites something that did not need it, and it can miss things. It is a filter you control, not a moderator, and the original text is always one click away.
Measured, not claimed
Those figures come from a 43-case internal test set, run repeatedly. It is a small set that we wrote ourselves, so treat it as evidence that the thing works rather than an industry benchmark. We publish the numbers we have rather than adjectives we cannot support.
Forty rewrites a day, no card. If you want more, Guard is £9.99 a month (plus VAT) for 500 a day.