Skip to main content
A workflow’s source is the set of URLs it extracts from. There are two ways to set it:
  • Let the agent find it. Describe what you want and Kadoa’s agent detects the source from your prompt. For example, “Get me all job postings from sandbox.kadoa.com/careers” resolves to the careers page automatically.
  • Paste your own URLs. Provide one or more specific URLs to extract from exactly those pages.
To see a workflow’s sources, select the website name in the workflow header. To change them, ask the agent. The agent prompt box with the source detected from the description

​
Paste one or more URLs

When you already know the exact pages, paste them into the setup prompt:
  • A single URL for one page.
  • A list of URLs when you have a specific set of pages from the same site, and you don’t need a whole section or category.
For many similar pages that follow a pattern, describe it in your prompt (for example, “go through pages 1 to 50”) and the agent generates the URLs for you.

​
Source rules

  • One workflow covers one website. Subdomains and country domains of the same name count as one website, such as acme.com and careers.acme.co.uk.
  • To extract from a specific set of pages on one site, list their URLs.
  • For many similar pages that follow a pattern, describe the pattern in your prompt, for example “go through pages 1 to 50”. The agent generates the URLs.
  • Kadoa extracts from HTML, XML, RSS, JSON, and PDF content.
A new workflow runs once unless you give it a schedule. See Scheduling.

​
Supported data types

Kadoa supports following content types by design:
  • HTML
  • XML
  • RSS …
  • XML
  • RSS
  • JSON
  • PDF