Check tiers

Exact diff

Fetches the page, pulls out the readable text, and compares it byte for byte against the last snapshot. Any difference is a change. Identical text is silence. No AI is involved, which is the point on quiet pages where every change matters: legal documents, DPAs, subprocessor lists, specs, regulatory registers. Nobody A/B tests a DPA. When the text moves, someone meant it to.

Evidence: a unified diff of exactly which lines changed, shown in the alert and in the timeline.

Where it struggles: noisy pages. Point it at a marketing page with rotating testimonials and it will report every rotation, correctly. That means the tier is wrong for the page.

Semantic (AI)

On each check, a model reads the fresh page alongside two things: the last snapshot and your prompt. It answers one narrow question, did the change the user described actually happen?, and only a yes becomes an alert. The rotating testimonial is noise. The trial quietly dropping from 14 days to 7 is the thing you asked about.

Evidence: one summary sentence, the before and after excerpts behind it, and a confidence score. The score is the model's own uncertainty, surfaced instead of hidden. A 72% alert deserves a second look in a way a 96% one does not, and you can calibrate that per monitor.

Browser agent

Some pages are empty shells without JavaScript: pricing calculators, dashboards, anything rendered client-side. The agent tier launches a real Chromium browser, loads the page, and waits for it to settle. It can dismiss cookie banners, open tabs, and scroll to reach the content your prompt needs. The rendered result then goes through the same semantic judgment.

Evidence: everything the semantic tier gives you, plus a full-page screenshot of the page exactly as it was checked, attached to the timeline (“Page as checked”).

Not sure whether you need it? View the page's raw source in your browser. If the content you care about is not in there, you need the agent.

Choosing: the simple rule

• The page is quiet and every change matters → exact diff.
• The page is noisy and only some changes matter → semantic.
• The content isn't in the HTML until a browser runs it → browser agent.

Tier is set per monitor, and changing it is a dropdown, not a migration. A common pattern is to start on exact diff for a week to learn how a page behaves, then switch to semantic with a prompt written against the noise you actually saw.

Availability: exact diff and semantic are on every plan, including Free. The browser agent is on paid plans. If a downgrade puts a monitor's tier outside your plan, the monitor keeps its configuration and starts again once the plan allows it. See teams & billing.