How to Schedule a Browse AI Robot to Check a Website

To schedule a Browse AI robot to check a website, open the robot in Browse AI, go to its Monitor tab, create a monitor, set the schedule and origin URL, choose any notifications, and save. The robot must be saved or approved, and the monitor must be saved before scheduled runs begin. Each run creates a task and uses credits according to the site and the data captured.

Schedule a robot from the Browse AI dashboard

1. Save or approve the robot. Create the robot and confirm it is saved or approved. Browse AI says a robot can have a monitor configured during creation or afterward. A schedule will not run until the robot is saved. Browse AI’s robot approval guide.
2. Open the robot’s Monitor tab. Select the robot in the dashboard and find Monitor. Choose the monitor-creation action. Browse AI’s help articles use slightly different labels, such as “Create a Monitor” or “Create new monitor,” so look for the monitor creation control rather than relying on an exact label.
3. Choose when it runs. Select a frequency and, where available, days of the week and a time. Options documented by Browse AI include hourly, daily, and weekly; its monitoring guide also lists minute frequency. Exact choices can depend on the monitor. Some schedules let you choose “Anytime.” Check the monitor’s timezone setting.
4. Set the origin URL and inputs. Enter the page the robot should start from and any input parameters the robot requires. Use the same kind of input values that you would provide when running it manually.
5. Name the monitor. Choose a descriptive name that identifies the site and purpose, especially if you will manage multiple monitors.
6. Configure alerts. Enable email notifications if you want to know when captured text changes. Confirm your email address is verified. For delivery into another workflow, use a supported integration or webhook where appropriate.
7. Save the monitor. Reopen its settings or monitor list to confirm the schedule, timezone, URL, and notifications are in place.

Browse AI describes a monitor as a recurring task schedule: each scheduled execution appears in task history. See its guides for website change monitoring and running a robot.

Choose a schedule that fits the page

Match the check interval to how often the target page changes and how quickly you need to know. A page that updates weekly usually does not need minute-by-minute checks; a short-lived listing or status change may call for a tighter interval if the monitor offers it and the credit budget supports it.

Need	Schedule to consider	Trade-off
Changes are occasional	Daily or weekly	Fewer executions, but a change may go unnoticed until the next run.
Changes matter within the day	Hourly, if available	Faster detection and more recurring tasks.
Changes are time-sensitive	A shorter interval if available	More frequent runs consume more task and credit capacity; verify the monitor’s choices.
The exact clock time is unimportant	“Anytime,” if offered	Lets the schedule run without selecting a specific time of day.

When a schedule supports selected weekdays and a time, pick the days and time that align with the site’s publishing cadence. A custom schedule guide also documents advanced RRULE-style patterns; check the current monitor controls and API documentation for the accepted format rather than assuming every dashboard monitor supports every pattern. Browse AI custom monitoring schedules.

Notifications and delivery

Email is the simplest choice when you only need an alert about captured text changes. In the monitor settings, enable the email notification option and save. If the alert does not arrive, verify the account email and inspect the monitor’s notification settings. Browse AI documents this flow in its monitoring notifications guide.

If the result needs to start another process, consider an integration or API workflow. Browse AI’s robot-running guide names Zapier, Make.com, and Pabbly Connect for event-triggered automation. A recurring dashboard monitor is usually sufficient for a single straightforward check; programmatic monitor management is useful when schedules or a fleet of monitors need to be controlled by code. Confirm current integration and webhook behavior in the vendor documentation before relying on a specific delivery path.

Manage monitors with the Browse AI API

Browse AI documents API operations for listing and creating monitors, with schedules represented in an RRULE-like string. This is useful for provisioning many monitors or managing schedules as part of an application. The exact endpoint, authentication, request body, and required fields are defined in Browse AI’s automated monitoring API guide; use that current reference to construct requests for your account. The retrieved documentation does not provide enough request details here to reproduce a reliable runnable API call, so do not copy an assumed endpoint or payload.

For a single recurring check, the dashboard workflow is easier to inspect and maintain. For code-driven management, account for API errors, validate the schedule string before creating monitors, and verify the created monitor in the dashboard.

Credits, cost, and capacity

A scheduled run is a robot execution and consumes task/credit capacity. The total is not a universal fixed price per check: it depends on the amount of data extracted and the site’s cost classification. Browse AI’s published credit guide lists these example rates:

Captured work	Standard site	Premium site
Minimum task cost	1 credit	2–10 credits
Rows	1 credit per 10 rows	2–10 credits per 10 rows
Screenshots	1 credit each	2–10 credits each
Single captured text values	1 credit per 10 values	2–10 credits per 10 values

These are vendor-published figures; actual usage depends on the robot’s outputs and the site’s classification. Estimate monthly use as scheduled executions multiplied by the expected credit cost per execution, then leave room for manual runs, retries, and changes to the captured data. Check the credit calculation guide and current pricing before choosing a plan, since plan terms can change.

Reliability and performance

• Use a stable origin URL. If a page requires a session or changing input values, confirm those inputs remain valid for scheduled runs.
• Check timezone and weekdays. A correct frequency with the wrong timezone can make alerts arrive at unexpected hours.
• Validate the robot manually first. Confirm it captures the intended fields before relying on repeated runs.
• Review task history. Compare recent outputs and failures so a changed page layout or expired access does not silently undermine the monitoring goal.
• Choose an interval based on the detection window. More frequent runs can detect a change sooner but consume more task capacity; slower intervals cost less and can miss brief changes.

Do not assume a monitor guarantees an alert for every kind of page change. Configure the captured fields to represent the change you care about, and periodically check that the robot still reaches and extracts those fields.

Troubleshooting

Symptom	Likely cause	What to do
No scheduled run appears	The robot or monitor was not saved, or the robot is not approved.	Save or approve the robot, save the monitor, then confirm it appears in the monitor list. Browse AI states that nothing runs on a schedule until the robot is saved.
The monitor runs at an unexpected time	The selected timezone or “Anytime” setting differs from your expectation.	Open the monitor settings and verify timezone, selected days, and time of day.
The run fails or captures the wrong content	The target page, robot steps, origin URL, or input values changed.	Run the robot manually with the same inputs, update its steps or inputs, then save and check a subsequent task.
No email alert arrives	Email notification is off, the address is not verified, or the captured text did not change.	Enable the change notification, verify the email address, and inspect task history to see whether the monitored text changed.
Credits run out sooner than expected	Frequency, extracted rows or fields, screenshots, retries, or premium-site classification increased usage.	Review actual task outputs and credit usage, reduce unnecessary capture volume or frequency, and consult the current credit guide.
API monitor creation fails	The schedule string, required fields, or authentication does not match the current API requirements.	Compare the request with the current API guide, validate the RRULE-like schedule, and inspect the response before retrying.

Or skip the browser setup

If the goal is a screenshot of a page on a schedule or as part of a workflow, ScreenshotNeo is a website screenshot API and MCP server. A single GET request returns a PNG, JPEG, WebP, or PDF. Its API documentation covers the available parameters.

curl -G "https://api.screenshotneo.com/v1/shot" -d access_key=YOUR_API_KEY --data-urlencode url=https://stripe.com -o shot.webp

import requests

r = requests.get(
    "https://api.screenshotneo.com/v1/shot",
    params={"access_key": "YOUR_API_KEY", "url": "https://stripe.com"},
    timeout=90,
)
open("shot.webp", "wb").write(r.content)

const q = new URLSearchParams({ access_key: 'YOUR_API_KEY', url: 'https://stripe.com' });
const res = await fetch(`https://api.screenshotneo.com/v1/shot?${q}`);

• Cookie banners are accepted and more than 60 known consent platforms, newsletter popups, and chat widgets are removed before the screenshot; each step can be turned off.
• Bot checks and CAPTCHAs, blank pages, timeouts, failed loads, and cache hits cost nothing. Responses indicate the page verdict and billing status in headers.
• An MCP server gives AI agents tools to take screenshots, get page information, and capture PDFs.
• 1,000 screenshots per month are free with no card. Paid plans start at $5 for 3,000 screenshots.

Sign up for ScreenshotNeo’s free 1,000 screenshots a month, with no card required.

FAQ

Can I create a monitor while creating the robot?

Browse AI says monitoring can be configured during robot creation or added later to an existing approved robot. The precise controls depend on the workflow.

Does a scheduled run count as a task?

Yes. Browse AI describes each recurring execution as a task, and it consumes credits based on the work and site.

Can I schedule checks only on selected weekdays?

Some monitor schedules provide weekday and time controls, and the custom schedule guide describes advanced RRULE-style schedules. Check the options shown for your monitor and account.

Is this the same as taking a screenshot of a page?

No. Browse AI runs a robot to collect configured data. For screenshot capture as the output, ScreenshotNeo provides a screenshot API and MCP server.