Simulated: the agents, the services, their replies, and the clock are fake. No real agent or service takes part.
Try this
- Press Ask for access. When an agent asks in the chat, press a Grant button.
- Watch the receipt stream and the Receipt JSON panel. Set the clock to 60x and wait, or press Revoke.
- Press Agents try again. Read the Denied receipt.
Chat with your agents
Grants
Receipt JSON (newest receipt)
No receipt yet.
Receipt stream
How it works
Pain point
People cannot easily see, limit, or end what an agent can do for them.
Problem statement
An agent asks for access, and the person has no clear view of what it holds. Grants do not end by themselves.
What sparked it
Mozilla's W3C WebExtensions group notes (issue 1041) that no browser-level primitive exists for a user to see, scope, or withdraw an agent's access.
Why this approach
Each grant has a task, a scope, and an end time. A grant ends by itself, and every use writes a receipt.
Hypothesis tested
We believed that a grant with a task, a scope, and an end time gives a person control. If it holds, people can tell what an agent may do and when that access ends.
How to try it
- Open the Prototype tab and press Ask for access.
- Press a Grant button, or press Deny.
- Set the clock speed to 60x and press Revoke, or wait for the grant to end.
- Press Agents try again and read the Denied receipt.
What this does not do
- It does not talk to a real agent or a real service.
- A receipt is a plain record. Nothing signs it.
- A receipt does not stop a bad use.
Notes
- Who would pay: compliance and GRC teams, and privacy officers (assumption).
- First customer: a company with a customer-data audit due.
- Weak spot: receipts prove what happened. They do not stop it.
- Feedback: which of the three time limits would you pick for a real agent?
Traces
| Step | Prompt | Model | Tool | Date |
|---|
Cost
| Step | Model | Input tokens | Output tokens | Cost (USD) |
|---|---|---|---|---|
| Total | ||||
Measured: the author runs used 203,100 tokens in total. Estimated: the split into input and output tokens (90 percent input, 10 percent output) and the dollar cost, at $2 input and $10 output per million tokens for Sonnet 5.5 (about $0.57). The run reported one total only. The lead session's planning, research, and publishing are not included. The prompts in the Traces section are listed in the order they were given.