Extract monitors

An extract target watches the pages of a site that fit your instructions. Detection is always semantic: a judge decides whether a confirmed text difference on a tracked page matters.

Fields

Field	Default	Notes
`url`	Required	Root URL to start from.
`instructions`	Required	1–2,000 characters on which pages and facts to track and which changes to report.
`schema`	Summary and key points	Optional JSON Schema, up to 20,000 characters serialized and 12 levels deep.
`max_pages`	`10`	1–50 pages to track.
`max_depth`	None	0–10 link levels from `url`. `0` tracks only `url`.
`follow_subdomains`	`false`	Also consider pages on subdomains.

How a run works

A discovery crawl picks up to max_pages pages that fit instructions and schema, and it refreshes that set periodically. Each run fetches the tracked pages again, confirms text differences, and asks the judge whether they matter, using confidence_threshold as described in Change detection. Extract monitors never compare extracted data. schema gives the judge extra context and shapes the baseline data on Retrieve a monitor, which refreshes about once a day. Changes contain diffs, summaries, and evidence, not data in your schema’s shape.

Example

Track a competitor’s product lineup across up to 20 pages, two link levels deep.

{
  "name": "Competitor product lineup",
  "target": {
    "type": "extract",
    "url": "https://example.com",
    "instructions": "Track product names, plan tiers, and feature limits. Ignore blog posts and job listings.",
    "max_pages": 20,
    "max_depth": 2
  }
}

Targets: detection rules and how to update a target.
Runs and changes: what an extract change contains.
Retrieve a monitor: where the baseline data appears.

Get started

Web data

Entity Enrichment

Automation

Account and billing

Production

Fields

How a run works

Example

​Fields

​How a run works

​Example

​Related

Fields

How a run works

Example

Related