Use cases / Clawbrowser demo / 0:46
Test website availability across 30 locations
Run regional browser checks and collect accessibility results, final URLs, and screenshots in a multi-region report.
Overview
A homepage can behave differently across locations. This Clawbrowser demo checks the public Stake.com homepage from 30 geographic locations using authorized testing endpoints and records the outcomes.
What happens in the video
The task requests 30 isolated regional checks of the public Stake.com homepage. The agent runs sessions sequentially, corrects tab and screenshot handling, and records loading and verification states. A final table shows regional observations, URLs, timings, and screenshot paths, including partial outcomes. This is a test report, not evidence of successful access in all 30 locations.
Before you start
- A public URL and authorized testing endpoints.
- Locations and a definition of a successful load.
Step-by-step guide
Practical steps for adapting the recorded task. The video summary above describes the demonstrated result; these checks guide your own run.
Define the test
Select the public page and regions. Keep the scope focused on page availability rather than treating it as validation of every service feature.
Run isolated checks
Run one regional session at a time with a fresh profile for each location, as requested in the recording. Preserve region, final URL, screenshot, and outcome. The agent corrects unexpected tabs and screenshot failures before continuing the batch.
Compare outcomes
Compile the structured report and preserve failures. A failed observation may reflect network or session conditions as well as a site restriction; retain evidence for diagnosis.
Try this prompt
Check [public URL] from [locations] using authorized testing endpoints and isolated browser sessions. Record region, accessibility outcome, final URL, and screenshot. Export a report that distinguishes failed observations from successful loads.
Adapt the placeholders to your task. This is an example prompt, not a transcript of the recording.
Results
- A regional observation table for the requested 30-location test, with partial results visible.
- Final URLs, timings, and screenshot references for investigating load outcomes.
Questions about this workflow
Does a homepage test validate the whole service?
No. Account and transaction journeys need their own tests. This scope covers public-page behavior.
Does a failed load prove a regional block?
No. Preserve the error and screenshot to investigate network, session, redirect, and site behavior.
Put the workflow to work
Prepare the browser connection, then adapt the guide to your task and check its output.
Set up Clawbrowser →Related reading
- How to Build an AI Agent That Browses the Web (Python + CDP) →
Read the implementation background for an agent that observes pages and performs browser tasks.
Explore the broader use case
Guide reviewed . Source: published video and description.
Related video guides
2:29Stream an OpenClaw browser session from Docker
View a container-based OpenClaw browser session through a live Clawbrowser stream and inspect remote activity.
Watch & read the guide
4:18Set up Clawbrowser on Linux with Docker and Hermes
Follow Linux browser installation with Docker and Hermes, including runtime startup and the verification mismatches shown in the recording.
Watch & read the guide
1:29Watch VirusTotal signup and browser verification
Follow a VirusTotal signup form and verification check in Clawbrowser, ending with the browser's signup-success confirmation.
Watch & read the guide