CAIN-42 MCPGateAGENTIC AI 75 · #66
Mobile browser agents for real-world errands
Google announced Chrome auto browse for bounded tasks such as appointments and parking reservations.
Last reviewed 2026-11-11
Agentic AI 75 / #66
2026 status: Announced rollout · Category: Browser agents
The 2026 development
Google announced Chrome auto browse for bounded tasks such as appointments and parking reservations.
The governance gap
An errand may spend money, accept terms or create a booking. The agent needs a bounded task, a payment ceiling and a clear stop before it commits.
Where CAIN-42 fits: Moat 5 — Predictive Trust & Blast Radius
Core question: What could happen before we let it happen? Pre-execution analysis of reach, exposure and consequence, including simulations.
Declare the errand's bounds before browsing: sites, spend, time and acceptable commitments. The firewall refuses a checkout or a terms acceptance outside the declaration.
How the wiring works
- Declare allowed sites, spend ceiling and commitment types.
- Score each action against the declaration.
- Pause before payment or binding terms.
- Record the confirmation and the receipt.
What is real today
LIVE A public route in this deployment exercises this mechanism today, within its stated scope.
The browser firewall demo evaluates fixed presets. It does not drive Chrome or book anything.
| Component in this repository | What the module says it is |
|---|---|
cain/browser/agent_firewall.py | Browser Agent Action Firewall. |
cain/commerce/mandate_guard.py | Agent Payment Mandate Guard. |
cain/argus/path.py | CAIN ARGUS — execution-path assurance (Prompt 14, section 7). |
Descriptions are the first line of each module's own docstring, read without importing it. A module path is a pointer into this repository, not a hosted endpoint. Its existence is checked by the test suite; its status for this use is the label above.
Check it yourself
- Run the live browser-agent demo
/api/v1/browser-agent-firewall/presets - Fire a live decision through the CAIN-42 pipeline
/fabric/try— the same enforcement path every product sits behind.
Commercial package
| Offer | Browser Errand Review |
|---|---|
| Buyer | Browser vendors and consumer platforms |
| Price (proposal) | $2,500–$5,000 per review |
| Bundle | Commerce & Payments — Delegated spending with a ceiling and a receipt. |
| Operator stream | Stream 2 of the 10-stream operator playbook |
Fintech, commerce platforms, marketplaces, treasury teams is the bundle buyer. The entry offer for this bundle is Payment-mandate review; browser-agent checkout review; the range is $2,500–$7,500 per review; integration from $10,000. A price on this page is a proposal, not a validated rate, and no customer is claimed.
Buy this as a product or service
CAIN-A75-066 — Browser Errand Review PILOT
A bounded pilot report: up to five scenarios, the relevant library engine or analysis, a written result and the stated limits. Engineering time is quoted per pilot.
Kind: Assessment · Price (proposal): $2,500–$5,000 per review · Lead time: 10 business days.
Open the product page · all 75 products
What this page does not claim
What this page is not. CAIN-42 is not affiliated with, endorsed by, integrated into, or shipped with the organisation named in the 2026 item. The item is public context; the page describes how CAIN-42 would govern that class of capability. No page here claims a customer, a partnership, a certification, a patent, or a production integration. Prices are proposals. Built by a three-person team.