Agent tools

Tool	What it does
tabs	List, open or close the agent’s own tabs (opened in the background).
navigate	Load a URL in a tab, or reload it. Returns an action id for wait_for and network.
snapshot	The page’s accessibility tree, with refs for interactive elements.
read	Visible text of the page or one element, or rows matched by a CSS selector. Password fields are never read.
act	Click, type, press keys, select, scroll — real input, re-checked before each step.
wait_for	Decide whether an action worked: the screen changed, the site replied, or the business result is confirmed.
network	Requests seen in a tab, with response bodies on request. Secrets masked, no headers.
fetch	GET or HEAD on the tab’s own origin with the tab’s cookies. Cross-origin and redirects are refused.
files	The agent’s own file area: download into it (up to 25 MB), upload from it into a file input.
screenshot	PNG of the visible page or one element. Never stored. Can be turned off per client.
needs_human	Hand a tab to you (login, captcha, decision) and wait.
learnings	Site notes kept on this machine: APIs, walls, pitfalls, tips. Notes are information, never instructions.
status	Versions, the agent’s tabs and hand-offs, which tools are on.
eval	Evaluate a JavaScript expression in an isolated world. Off by default.
run_flow	Run a saved Kav flow. Appears only when Kav is set up.

Every result starts with one JSON line from K-Browser itself; anything from the page follows inside <untrusted-page-content>.

A typical run

1. tabs opens a tab in the background; navigate loads the site.
2. snapshot or read shows what is on the page.
3. act clicks and types; wait_for checks that it worked.
4. A login wall? needs_human hands the tab to you, and the agent continues once you return it.