One Jev-decided step
browser_actDelegates one browser action from a one-sentence instruction; Jev selects and executes the click, type, select, scroll, wait, or key press, then returns status and a fresh observation.
Instructions
Delegate exactly ONE browser action to Jev (click, type, select, scroll, back, wait, press Enter, or stop). Give a one-sentence instruction; Jev picks the operation and target element; code validates, executes, and re-observes. Paid: a fraction of a cent (~$0.0002, more on very dense pages). Returns status, the executed step with its confidence, usage.est_cost_usd, a fresh observation, and — when a text field needs content — status 'needs_text'/'needs_value' with the ref to fill via browser_type/browser_select, then call browser_act again. Pass field text via values; value contents are never sent to Jev.
Tool call template
Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.
{
"id": 1,
"jsonrpc": "2.0",
"method": "tools/call",
"params": {
"arguments": {
"instruction": "<instruction>"
},
"name": "browser_act"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| values | No | Field label → text to type. Keys should match labels from the observation, e.g. {"Search": "espresso"}. Contents never go to Jev. | |
| instruction | Yes | One sentence: the next action, e.g. "Click the Sign in link." or "Scroll down to the pricing table." |