# Browse AI integrations: robots, tasks and monitors

> Update robot cookies, run a robot task and create a monitor in Browse AI, and start a workflow when Browse AI sends “Task finished”.

**Canonical page:** https://tray.ai/connectors/browse-ai-integrations/
**Categories:** Data and analytics
**Connects through:** HTTP Connector

## Overview

Browse AI trains robots to extract data from websites and monitor pages for changes, without writing scraping code, and delivers the results to spreadsheets or other tools. Tray.ai connects to Browse AI through the HTTP Connector, so your workflows can call the Browse AI API alongside the rest of your stack.

## Use cases

### Robots

Read and update robots in Browse AI from any Tray.ai workflow. The Browse AI API covers calls such as list robots and get a robot.

- List robots
- Get a robot
- Update robot cookies

### Tasks

Read tasks in Browse AI from any Tray.ai workflow. The Browse AI API covers calls such as run a robot task and list tasks.

- Run a robot task
- List tasks
- Get a task

### Monitors

Read, create, update, and delete monitors in Browse AI from any Tray.ai workflow. The Browse AI API covers calls such as list monitors and create a monitor.

- List monitors
- Create a monitor
- Update a monitor

### Bulk runs

Read and create bulk runs in Browse AI from any Tray.ai workflow. The Browse AI API covers calls such as create a bulk run and list bulk runs.

- Create a bulk run
- List bulk runs
- Get a bulk run

### Webhooks

Read, create, and delete webhooks in Browse AI from any Tray.ai workflow. The Browse AI API covers calls such as list webhooks and create a webhook.

- List webhooks
- Create a webhook
- Delete a webhook

### Browse AI events

Start a Tray.ai workflow the moment something happens in Browse AI. Browse AI sends events such as task finished and table export finished to a Tray.ai webhook trigger.

- Task finished
- Table export finished

## Challenges Tray.ai solves

### Keeping Browse AI credentials out of logs

A raw API call usually means pasting a key or token into the request, where it ends up in step inputs, logs, and screenshots.

**How Tray.ai helps:** Store Browse AI credentials once as a Tray.ai authentication and reference them from the HTTP Connector. Tray.ai masks authentication values in logs, so the secret never shows up in a step's input or output.

### Going from the Browse AI API docs to a working call

Translating an example request from API docs into a workflow step means copying the method, URL, headers, and body by hand.

**How Tray.ai helps:** Paste a cURL example from the Browse AI API docs into the HTTP Connector and Tray.ai fills in the method, URL, headers, and body for you.

### Handling files and non-JSON responses

Not every API answers in JSON. Some return XML, files, or binary data, or expect a multipart upload.

**How Tray.ai helps:** The HTTP Connector parses JSON and XML responses, returns files you can pass to the next step, and sends multipart form data for uploads.

## Frequently asked questions

### Does Tray.ai connect to Browse AI?

Yes. Tray.ai connects to Browse AI through the HTTP Connector, which calls the Browse AI API directly. Any call the Browse AI API documents can run as a step in a Tray.ai workflow.

### How does Tray.ai authenticate with Browse AI?

The Browse AI API uses a bearer token. You save it once as a Tray.ai authentication, and the HTTP Connector adds it to every request.

### Can I get a dedicated Browse AI connector?

Browse AI runs through the HTTP Connector rather than a dedicated connector. If your team wants one, the Tray.ai connector SDK can build a dedicated Browse AI connector from the Browse AI API.

## Learn more

- Intelligent Integration: https://tray.ai/platform/intelligent-ipaas/
- Merlin Agent Builder: https://tray.ai/platform/merlin-agent-builder/
- Agent Gateway for MCP: https://tray.ai/platform/agent-gateway/
- Book a demo: https://tray.ai/contact/