Gluecrawl × AmbactiBring Gluecrawl into
the flow of work.
A little less busywork with Gluecrawl.
Job4 capabilities+
- Create a job
Create a job: Gluecrawl maps the site with an LLM, then scrapes it. Charges the job-creation cost upfront and mints a job that persists until deleted. To scrape the same site again, reuse the job with Run: Start instead of creating another one.
- Delete a job
Delete a job along with its runs, extracted rows and schedule
- Get a job
Retrieve a single job, including its mapping status and resolved columns
- Get many jobs
Retrieve the jobs on this account, newest first
Run5 capabilities+
- Download run items as CSV
Export a run's rows as a CSV file attached to the output item
- Get a run
Retrieve a single run, including its billing breakdown once it has settled
- Get run items
Retrieve the rows a run extracted, one n8n item per row
- Get many runs
List the run history of a job
- Start a run
Re-scrape a job that is already mapped, reusing its cached config. No mapping cost and nothing charged upfront; the run settles once it finishes. Rate limited to 10 requests per minute.
Frequently asked
questions.
What could an Ambacti integration do with Gluecrawl?
The documented operations include Job: Create a job; Job: Delete a job; Job: Get a job; Job: Get many jobs.
Could I keep a workflow read-only?
For a read-only workflow, limit account permissions to reading data and exclude actions that create, update, or delete records.
Will every action run automatically?
Choose which steps could run on their own and which should pause for review. Changes should follow the permissions and approval rules you set.
Do I need to review actions in Gluecrawl?
Decide which work could run on its own and which steps need your review.