Nextbrowser
Download
Use cases1:39 watch

Research Wikipedia with NextBrowser

Open Wikipedia through a managed NextBrowser session and build a concise, cited Empire State Building fact sheet from the visible article.

About this reference video

The video shows the source task and its recorded outcome. The guide below explains how to run that task through NextBrowser: choose a profile and browser toolset, start a session, then supervise your local agent in Chat and Live View. Interface labels and results can differ from the recording.

Go to the NextBrowser workflow ↓
Published · @AIWebAutomationLabWatch on YouTube ↗

Overview

A short fact sheet should preserve the distinctions made by its source, such as architectural height versus antenna height. NextBrowser lets the local agent read the article while you keep the source visible. The ClawBrowser toolset supplies the browser session for this example; task control stays in NextBrowser.

What happens in the video

The agent starts from a managed browser profile, opens the Wikipedia article for the Empire State Building, and returns a source-linked summary covering construction dates, height, location, and architecture. The article remains visible during the workflow, providing a direct source for the reported facts.

Before you start

  • NextBrowser on macOS or Windows, signed in through browser pairing
  • An installed and authenticated local agent: Claude Code or Codex from the ChatGPT desktop app
  • The target article and fields such as construction dates, height, location and architecture

Run this in NextBrowser

Follow these steps in your own NextBrowser workspace. The video summary records the source demonstration; your result needs the checks below.

  1. Prepare the NextBrowser session

    Select a NextBrowser profile using the ClawBrowser toolset, start its session and open the article. ClawBrowser supplies the browser runtime here; NextBrowser is where you choose the agent and supervise the task.

  2. Give the local agent a scoped task

    Select your local agent in NextBrowser. Confirm the active profile and tab for the Wikipedia article for the Empire State Building. Submit the prompt below in Chat after replacing its placeholders. The selected profile name is guidance for the agent; check the actual session in the sidebar and Live View.

  3. Collect the task evidence

    Ask the agent in Chat to read the article and return the requested fields with supporting section links. Keep architectural height distinct from tip or antenna height and distinguish construction dates from opening dates.

  4. Review the result against the browser

    Compare the fact sheet with the article in Live View. Keep the article open for inspection and record the access date; this is a summary of that source, not independent historical verification.

Send this prompt in NextBrowser Chat

Suggested prompt

Use the intended NextBrowser profile [profile name]. First confirm the running session, active tab and target site; stop if they do not match. Open the Wikipedia article for [subject]. Summarize [requested facts] from the page, distinguish dates and measurements clearly, and include the exact source URL so I can verify the result. Report source URLs, the actual amount collected and any incomplete checks. Keep this run to research; do not purchase, publish or change account settings.

Replace the placeholders, then send this in NextBrowser Chat with the intended profile and agent selected. This is a suggested task, not the recording transcript.

What to verify in your run

  • A concise fact sheet with article or section links and an access date
  • The source article left open in the selected session for verification

Questions about this workflow

Does the guide guarantee that the facts never change?

No. It documents the recorded workflow. Reopen the linked article when current facts or citations matter.

Can the same workflow use another source?

Yes. Replace Wikipedia and the subject in the prompt, then require direct source links in the output.

Keep exploring

NextBrowser documentation

NextBrowser documentation ↗Product guide: profiles, agents and sessions ↗Profile toolsets in the NextBrowser sidebar ↗

From the blog

Browser Automation, Finally Made Simple ↗

Explore the foundations of browser automation and structured research.

Related use cases

Web Scraping and Browser Research ↗

NextBrowser workflow adapted . Recording reviewed . Video source: published video and description.

More workflows to explore

← Browse all demos