Sightline checks every new listing's photos with an AI vision model the moment they're posted. Anything that breaks your marketplace's rules is pulled aside for a person to decide, so the storefront stays clean at a scale no team could watch by hand.
New listings hit the public feed the moment they were posted. No team could eyeball every photo in time, so unsafe and off-policy items reached buyers before anyone noticed.
Each image is checked against the marketplace's rules the instant it's posted. The vast majority clear on their own; only genuine edge cases stop for a reviewer, who still makes the final call.
New listings never wait for a nightly batch. They flow in, get seen, and only the doubtful ones stop for a person.
Watches the new-listing feed and batches the images per listing. A cutoff-link check means it only processes what's new since the last run, so it keeps up continuously.
A FastAPI backend sends each image to Gemini 2.5 Flash with your policy prompt, and gets back approved / not-approved plus a reason, as clean JSON. Not-approved listings get flagged.
Flagged listings land in a role-based console. A reviewer marks each handled or files a report; an admin sees every scan run and what's active right now.
Sightline reads the policy prompt you write, not a fixed allow-list. These are the kinds of checks a marketplace typically turns on.
Weapons, replicas, and regulated goods flagged before a listing ever reaches the feed. prohibited-items
Knock-off logos, clasps, and packaging caught straight from the photo. counterfeit
Health, medical, or performance claims printed on a label get held for a human. health-claims
Phone numbers, emails, or handles in an image that route the sale away. off-platform
NSFW or graphic imagery kept out of a general-audience storefront. explicit
Items matching recall notices or safety bans surfaced for review. recalled
Too-good-to-be-true framing and known scam layouts get a second look. fraud
Stock shots or mismatched images that misrepresent the actual item. misrepresentation
Any rule you can write in plain language becomes a check the model runs. custom-policy
The reviewer and admin console the flagged listings land in, switch views from the rail.
The storefront stays clean at a scale no human team could watch manually, with a person still making the final call.
Policy-driven image moderation wired to a real model, returning structured verdicts you can store and act on, not a demo notebook.
AI handles the volume; a role-based console keeps a person on every real decision, with reviewer and admin views that match how teams actually work.
Continuous ingest and logged runs, built to run unattended and stay caught up with a marketplace's live feed.
Moderation runs on the fast, low-cost Gemini vision tier, so scanning the whole feed costs cents, not headcount. One photo plus the policy prompt goes in; one short JSON verdict comes back.
Estimated on public Gemini fast-tier list pricing (about $0.30 to $0.50 per 1M input tokens): a listing photo plus the policy prompt in, one short JSON verdict out. Downscaling images and caching the policy prompt push it lower still.
Sightline was built by Braynex for marketplaces that can't afford to let a bad listing reach a buyer.