Introducing /interact. Scrape any page, then let your agent take over to click, type, and extract data for you. Try it now →

What is live view in browser automation?

Live view streams an active browser session as a real-time visual feed so you can see exactly what the browser is doing while automation runs. Two modes exist: read-only streams (for monitoring dashboards and observability) and interactive streams (where a human can take over the mouse and keyboard directly). Without live view, debugging automated sessions means parsing logs after the fact; with it, you can observe, intervene, and verify in real time without needing direct server access.

FactorRead-only live viewInteractive live view
Human controlObserve onlyFull mouse and keyboard takeover
Primary use caseMonitoring dashboards, debuggingHuman-in-the-loop review, CAPTCHA handling
Embeddable in UIYesYes
Automation continuesUninterruptedPauses for human input

Live view is most useful when automated steps occasionally need human review: verifying a form fill before submission, handling unexpected CAPTCHAs, or confirming that the browser reached the correct page before extraction. Teams embed read-only streams in internal tools to monitor long-running scrapes, while interactive streams let an operator take over a session when the automation encounters something it cannot handle on its own.

Firecrawl's /interact endpoint returns both a liveViewUrl (read-only) and an interactiveLiveViewUrl (full human takeover) in every interaction response, making it simple to build tools that combine automated scraping with human-in-the-loop review.

Last updated: Apr 03, 2026
FOOTER
The easiest way to extract
data from the web
Backed by
Y Combinator
LinkedinGithubYouTube
SOC II · Type 2
AICPA
SOC 2
X (Twitter)
Discord