Menu
ProductReplay & DevToolsSignalsCall qualityWhy (AI)Live AssistCanvas recordingPrivacy & complianceSelf-hosted
SolutionsHealthcare & virtual careEngineeringSupportProduct teamsKiosks & monitoring
MorePricingDocsCompareTrust centerChangelogGlossaryAboutContactPress kit
Start free Talk to sales Log in

See it live. Talk it through. Fix it.

Co-browse rides the same masked DOM stream as the recording, so nothing new leaves the device and no screen share is needed.

Voice, drawing, and control are separate capabilities the user confirms one at a time.

One request, one answer.

Default is no.

Live Assist capabilities and their consent, from the lowest rung to the highest
CapabilityWhat the agent asksWhat the user sees firstHow it is revoked
Co-browseView your screen liveModal: agent name and company, can see this page as you see it with sensitive data hidden, cannot hear, click, or typeStop sharing in the banner, or close the tab
Voice callStart an audio-only callModal plus the browser's own microphone prompt; not recorded unless agreed separatelyHang up; mute is always one click
AnnotationsDraw on your screenModal: can highlight and draw pointers, drawings disappear after 10 s, cannot click or typeEsc clears and revokes
Remote controlClick and type for youStrongest wording, 10-minute expiry, user always has priorityEsc, any mouse or keyboard activity, Stop, expiry
  • Independence

    Declining or revoking a higher rung leaves lower rungs intact. Revoking co-browse ends drawing and control, but a voice call keeps going until the user hangs up.

  • Always visible

    A banner in a closed shadow root shows which capabilities are on, the agent's name, and a stop button per capability. Host CSS cannot hide it.

  • Policy can only narrow

    A tenant can disable rungs or require re-confirmation on navigation. No tenant can pre-accept anything on the user's behalf.

Free to run, even on locked networks.

  1. SDK live module, 25 KB, lazy
  2. Live fan-out ≤ 800 ms to the agent
  3. Voice relay audio only, no video
  4. Agent console live Player + DevTools
Voice uses Opus at roughly 40 kbps through an embedded relay, so calls connect from hospital and corporate networks where peer-to-peer fails. The same components ship in the self-hosted chart.

Honest about what browsers allow.

The agent interacts with the live mirror. Each action becomes a command the SDK dispatches as a synthetic event, with the user's own activity always taking priority.

Synthetic events are not trusted by the browser: file pickers, clipboard, fullscreen, and autofill will not fire. For those the agent gets a Guide fallback that highlights the target and asks the user to click. Typing into password and card fields, and anything under a mask attribute, is blocked by policy.

Every command is recorded in the session with the agent as actor, shown in the replay with a distinct cursor, and written to the audit log.

Why not drive a headless browser with the user's session?

It would require exfiltrating the user's authentication state to our servers. That is a security and compliance non-starter, so it is not offered and not planned.

Remote control 10 min
Priority
The user, always
Will not fire
File pickers, clipboard, fullscreen, autofill
Instead
Guide fallback
Blocked
Password, card and masked fields
Logged
Replay and audit log
Esc or any activity stops it

Product updates by email.

Leave a work email and we will tell you when something ships. Or book a demo with an engineer.

Free for 1,000 stored sessions a month, with unlimited seats. Create a workspace and add one script tag.

Start