Let AI agents work in your signed-in Chrome browser with scoped access, human approval, and verified results
AI agent grounded in customer journey context for enterprise CX operations
Stage
Not given
Established
Founded
Not given
2016
Based in
Not given
NL
Pricing model
Not given
Not given
Pricing
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).
Trial: 30-day free trial with 2 users and 5 journeys, capped AI use. Management and Strategic plans require custom quotes based on journey count. Minimum spend shown represents around 5 journeys, with per-journey fees decreasing as more journeys are added. Annual invoicing upfront.
Key features
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
Ask in plain language and receive answers grounded in customer journeys
Surfaces insights and identifies where friction is accumulating
Generates executive briefs, sprint inputs and stakeholder reports
Cites sources for every claim with specific journey steps and research pieces
Aligns business KPIs and voice of customer data to customer journeys
Skills framework for standardized, repeatable AI tasks
Role-based access controls and enterprise security
No data sharing with third-party AI providers
TheyDo MCP for integration with external AI systems
What makes it different
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
Every answer cites sources and cannot hallucinate because it only reasons over your data
Turns raw transcripts and notes into structured journey insights in minutes instead of weeks
BrowserPair
TheyDo Agent