Classify website changes
When PhantomBuster detects a change on a monitored page, have OpenRouter judge whether the change is significant before anyone is alerted.
See all PhantomBuster + OpenRouter integrations or talk to a human
4.9/5 on G2·
Google for Startups Accelerator
How Knit builds this workflow
The Agent researches both APIs and wires the trigger on one side to the action on the other — no pre-built connector required. Here is the vocabulary it has to work with.
PhantomBuster Explore PhantomBuster →
TriggersFires when a scrape, crawl or robot run finishes in PhantomBuster.
Fires when PhantomBuster returns a new batch of extracted data.
Fires when PhantomBuster detects a change on a monitored page.
Extracts the content of a web page with PhantomBuster.
Starts a crawl of a whole site in PhantomBuster.
Runs a saved scraper, task or robot in PhantomBuster.
OpenRouter Explore OpenRouter →
TriggersFires when OpenRouter returns a completion, prediction or other result.
Fires when a request to OpenRouter errors or times out.
Fires when a fine-tuning job in OpenRouter finishes.
Sends a prompt to OpenRouter and returns the model's response.
Sends text, an image or other data to OpenRouter and returns the model's output.
Uses OpenRouter to classify or extract structured data from text or images.
More PhantomBuster + OpenRouter workflows
Summarize each scraped page
When a scrape completes in PhantomBuster, send the page content to OpenRouter and store the summary it returns.
See details
Extract structured fields from results
When PhantomBuster returns a new result, ask OpenRouter to pull out the fields you need, such as product name and price.
See details
See all PhantomBuster + OpenRouter integrations → · Browse the full workflow library →
Common questions
Can Knit build “Classify website changes” between PhantomBuster and OpenRouter?
Yes — describe it in the box above and Knit's Integrations Agent researches PhantomBuster and OpenRouter's public API docs (or your own uploaded docs) and builds a working workflow, whether or not either app already has a pre-built connector.
How long does it take to build?
Minutes to a first working version, not weeks — you test it against real data before it goes anywhere near production.
Why send scraped pages to an AI model?
Scraped HTML and text are noisy. Passing each PhantomBuster result to OpenRouter lets you pull out prices, names or key points in a consistent shape instead of cleaning the data by hand.
Can the model decide which pages to scrape next?
Yes. You can have OpenRouter produce a list of URLs or search terms, then run a scrape in PhantomBuster for each one.