Starter Instrumented boundary Govern browser & computer-use agents →

Govern a browser & computer-use agent with GOVENANT

Use GOVENANT and a browser / computer-use agent together — govern the browser & computer-use agents, not the framework. It clicked, it typed — but did the thing actually happen?

The use case

An operations team runs a computer-use agent to move data between two systems that have no API — it drives the browser, fills the forms, clicks submit.

The challenge

The agent reports every step “succeeded,” but a click can succeed and change nothing. There’s no return value to trust and no way to know, from the agent’s own logs, whether the record actually landed in the target system.

What the record reveals

GOVENANT ignores the click and checks the effect: did the row appear in the target system, did the status change? The record shows a 6% silent-failure rate — forms that submitted “successfully” but wrote nothing — that no screenshot log would ever have caught.

How it maps

The substrate: The downstream systems the agent touches: the record it created, the form it submitted, the value it changed — the effect, verified where it lands, not the screenshot of the click.

The path — Instrumented boundary: Add a thin hook at the action boundary — no access to prompts, reasoning, or models — so every action and its outcome is recorded.

GOVENANT shapea browser / computer-use agent source
Action rowEach attempted UI action — with the outcome checked in the TARGET system, not the click
Verified outcomeThe downstream effect: did the row appear, did the status change? A click can succeed and change nothing
Ownership gateConsequential targets (systems/forms the agent may change) registered as levers with owners
Miss“Submitted successfully” actions that wrote nothing downstream — the silent-failure rate

Run it

  1. Instrument the action boundary; check each action’s effect in the target system of record.
  2. Register consequential targets as gated levers; key completion to verified downstream effect.
  3. Sweep read-only over the target systems; review delivery vs. attempted actions and the silent-failure log.

The substrate shapes and acceptance tests are open (CC BY 4.0): developer integration · the portable schema.

What you can claim

A real integration wears the Built-on badge and publishes self-assessed levels with probe logs — open to challenge, never “certified.” For computer-use agents, a record that keys “done” to verified downstream effect is the difference between an impressive demo and a trustworthy operator.

Status — kept honest

It will never say “supported” or “certified” before a working example lands and its record is public — progress lives in the GitHub issue. Holding our own examples to the standard’s claims discipline is the product.

All sample projects · Govern browser & computer-use agents · All integrations · Run the audit