Workflow & Automation · Integration
Browse AI
Add Browse AI to your product for your customers, and give your AI agents governed access to it.
Browse AI turns a recorded browsing session into a reusable robot, and the API at api.browse.ai/v2 runs those robots rather than defining them. That is the main constraint: a robot must first be recorded in the web recorder, so an integration can list robots and start tasks but cannot create a scraper from scratch through the API. Running one is POST /v2/robots/{robotId}/tasks with inputParameters, which must include originUrl plus any inputs captured during recording, and the call returns a task in progress rather than data. Results arrive when the task finishes, either by polling the task or via a webhook, and are split into capturedTexts for single fields, capturedLists for repeating rows and capturedScreenshots for images. Monitors are the scheduled variant, re-running a robot and reporting changes, which is what most alerting use cases actually want. fastn holds each customer's API key, keeps the connection current and controls which robots an agent may run.
In your product
Embedded for your customers. Per-tenant auth, no per-customer code, maintained by fastn.
Let a customer connect their own Browse AI account so tasks consume their credits and their recorded robots.
Trigger a robot from your product against a URL a customer supplies and store the captured list rows.
Receive task webhooks and reconcile new rows against records you already hold, flagging changes.
Surface a customer's monitors and their last change events inside your own dashboard.
For your AI agents
Governed, audited access for the agents you build, through the MCP server.
Let an agent run an approved robot with validated input parameters and return the captured lists, with task credits audited per tenant.
Have an agent explain why a task failed when a site layout change breaks a recorded selector.
Allow an agent to read task results and monitor history without permission to delete robots.
Example prompt
Run the competitor pricing robot on this page and show me what changed since last week.
Set up Browse AI in 4 steps
- 01Enable the Browse AI connector from your fastn dashboard.
- 02Have each customer authorise their own Browse AI account, so calls run under their credentials rather than a shared key.
- 03Decide which processes, runs and queues your product needs, map those fields, then enable the actions and triggers you want.
- 04Call it from your product and expose it to your agents through the same governed connection.
Why teams use the Browse AI integration
What you get by embedding it with fastn instead of building it yourself.
- Ship a Browse AI integration without building it. Your customers connect their own Browse AI account inside your product and work their processes, runs and queues there, with no per-customer code on your side.
- Handle the part that actually costs time: runs are asynchronous and can fail long after they are accepted, so an outcome that never arrives must look different from one that succeeded. fastn owns the auth, token refresh, rate limits, pagination and breaking-change fixes, so a Browse AI update is not your on-call problem.
- One integration serves your product and your agents. The same governed Browse AI connection powers in-product features and gives AI agents scoped, audited access, so you start work in the automation platform your customers already run, and get the outcome back without wiring it twice.
Used by these teams
Compare with
Ansible
Automation Anywhere
Microsoft Power AutomateOften used alongside
Tools the same teams tend to run next to Browse AI, across other categories.
Amazon SES
Resend
Mailgun
PostmarkBrowse AI integration FAQ
How do I add a Browse AI integration to my product?
Enable the Browse AI connector in your fastn dashboard, then let each customer authenticate their own Browse AI account. fastn handles the OAuth flow, token storage and refresh per tenant, so there is no Browse AI client code in your app and no per-customer branch in your codebase. Setup is 4 steps.
Do my customers each connect their own Browse AI account?
Yes. Every connection is scoped to the individual customer, so each authorises their own Browse AI account and only ever sees their own processes, runs and queues. That per-tenant isolation is the point of an embedded integration: you support the long tail of customer setups without maintaining an integration per customer.
Can AI agents use this Browse AI integration?
Yes. The same connection is exposed to your agents through the fastn MCP gateway, with permissions scoped per tenant and every call audited. Let an agent run an approved robot with validated input parameters and return the captured lists, with task credits audited per tenant.
Who maintains the Browse AI integration?
fastn does. When Browse AI changes an endpoint, deprecates a field or alters its auth, the fix lands in the connector rather than in your backlog, and your customers' connections keep working.
Can my product start a Browse AI run and read its outcome?
Yes. Your product can trigger a process in the customer's own Browse AI account, pass it input, and take the result back as an event rather than polling for it.
What happens when a Browse AI run is slow or fails?
The failure surfaces with its error rather than as a silent timeout, and the run keeps its own identifier so a retry can be matched to the original. That matters more here than in most integrations, because a run that half-completed is not the same as one that never started.
What can I build with the Browse AI integration?
A common starting point: let a customer connect their own Browse AI account so tasks consume their credits and their recorded robots. Teams also use it for the other use cases listed above, and expose it to agents for governed reads and writes.
How much does the Browse AI integration cost?
It is included. Pricing is based on connected accounts, not on how many connectors you enable, so adding Browse AI does not change your per-connector cost. You can start free with 3 connected accounts.
Add Browse AI to your product
Start free with 3 connected accounts. No sales call required, and no per-customer integration code.