Let AI agents work in your signed-in Chrome browser with scoped access, human approval, and verified results
Stage
Not given
Not given
Founded
Not given
Not given
Based in
BR
Not given
Pricing model
Free trial
Not given
Pricing
US$120 per agent per month, with a 30-day free trial (card required, nothing charged until it ends). Larger teams pay less: the rate drops by $1 for each agent added through the ninth, settling at US$110 per agent from 10 onwards. You bring your own model key and pay the provider directly for tokens
Free: €0/month with 100 task credits per month and 1 connected browser. Pro: €5/month with 2,000 task credits per billing month and 5 connected browsers. Extra credits: 1,000 credits for €3 on Pro (do not expire).
Key features
AI software engineer agent
AI product manager agent
AI QA engineer agent
AI systems architect agent
AI SRE (Nadia Serrano)
GitHub, Linear, Slack and Microsoft Teams integration
Incident investigation workflow
Release verification
Granular permissions per agent
30-day free trial with no credit card charge
Redacted sensitive values including passwords, OTPs, card data, and API keys
Effect verification to prevent blindly repeating uncertain browser side effects
Integration with ChatGPT and Claude via MCP connectors
REST API and custom agent key support for own scripts
Task credit model with no separate browser-hour or AI model billing
What makes it different
No separate token metering—you bring your own model key and pay the provider directly
Agents operate only with permissions you explicitly grant and can revoke
All changes require human approval before reaching production
One price per agent regardless of specialization
Integrates with tools your team already uses
Keeps your signed-in sessions in your own Chrome profile instead of copying them to a remote browser fleet
Brings the agent into your existing browser instead of moving your browser to a remote server
Charges only for accepted tasks, not for browser hours or AI model calls
Prevents uncertain side effects from being blindly replayed through durable task state and effect verification
Treats all page content as untrusted data so websites cannot grant themselves new permissions