Extract structured fields from results
When Cloud BOT returns a new result, ask Google AI Studio (Gemini) to pull out the fields you need, such as product name and price.
See all Cloud BOT + Google AI Studio (Gemini) integrations or talk to a human
Google for Startups AcceleratorHow 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.
Cloud BOT Explore Cloud BOT →
TriggersFires when a scrape, crawl or robot run finishes in Cloud BOT.
Fires when Cloud BOT returns a new batch of extracted data.
Fires when Cloud BOT detects a change on a monitored page.
Extracts the content of a web page with Cloud BOT.
Starts a crawl of a whole site in Cloud BOT.
Runs a saved scraper, task or robot in Cloud BOT.
Google AI Studio (Gemini) Explore Google AI Studio (Gemini) →
TriggersFires when Google AI Studio (Gemini) returns a completion, prediction or other result.
Fires when a request to Google AI Studio (Gemini) errors or times out.
Fires when a fine-tuning job in Google AI Studio (Gemini) finishes.
Sends a prompt to Google AI Studio (Gemini) and returns the model's response.
Sends text, an image or other data to Google AI Studio (Gemini) and returns the model's output.
Uses Google AI Studio (Gemini) to classify or extract structured data from text or images.
More Cloud BOT + Google AI Studio (Gemini) workflows
See all Cloud BOT + Google AI Studio (Gemini) integrations → · Browse the full workflow library →
Enterprise-grade security
Common questions
Can Knit build “Extract structured fields from results” between Cloud BOT and Google AI Studio (Gemini)?
Yes — describe it in the box above and Knit's Integrations Agent researches Cloud BOT and Google AI Studio (Gemini)'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 Cloud BOT result to Google AI Studio (Gemini) 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 Google AI Studio (Gemini) produce a list of URLs or search terms, then run a scrape in Cloud BOT for each one.