Browser & Web Action Tool

The Screenshot Capture Tool

Take a screenshot of the full page or a specific element so an agent can verify what a page looks like, keep visual evidence, or feed the image to vision analysis.

Explore VDF AI Agents
Live webActs on real pages and APIs
GovernedEvery request logged
AssignableTo research & ops agents
100%On-premise capable
The Live-Web Problem

Half the work lives behind a browser

Critical data and actions sit on web pages and third-party systems with no clean API. Without the ability to navigate, click, extract, and call endpoints, an agent is cut off from a huge share of the real work — and doing it by hand doesn’t scale.

01

No API, no access

Many systems only expose a web UI an agent can’t reach.

02

Manual gathering

People copy-paste from pages and PDFs because nothing else can.

03

Brittle scripts

Hand-written scrapers break the moment a page changes.

04

Ungoverned egress

Uncontrolled outbound web calls are a security and compliance risk.

How the Tool Works

Screenshot Capture, without the risk

Capability

What it does

Capture a visual image of the page.

it captures a screenshot of the full page or a specified element.

Tool
Screenshot Capture

Assignable to any agent

ScreenshotVisualEvidenceGoverned

How it works

Predictable, inspectable behavior

Designed to be reliable.

captures run in the governed browser and are stored in your environment, so an agent produces visual evidence and inputs for analysis without anything leaving your perimeter.

Governed
Policy + Audit

Every call logged

ScopedLoggedGovernedOn-prem

Governance

Private, governed, on-premise

Runs inside your perimeter.

Browsing and web calls run through a governed, on-premise gateway with allow-listing and full request logging, so agents reach only the sites and endpoints you permit — and every action is auditable.

100%
On-Prem

Per-tenant, logged

On-premRBACAudit logSovereign
Inputs

Parameters

The screenshot_capture tool accepts these inputs when an agent calls it. Required inputs are flagged.

Name Type Required Description
selector string Optional Optional element to capture; omit for the full page.
full_page boolean
default: false
Optional Capture the entire scrollable page.
In depth

How the Screenshot Capture tool works in practice

An agent that operates a browser needs proof of what it saw. The Screenshot Capture tool produces that proof: a pixel-accurate record of the page — full page, viewport, or a single element — taken inside the governed browser session and stored in your environment. When a workflow later gets audited, “what did the portal actually display before the agent clicked submit?” has a visual answer.

Three patterns dominate. Visual QA: capture after a deploy or content change and let Image Analysis judge whether the page rendered correctly. Evidence: staple the screenshot to the run record of an irreversible action, next to the structured page state from Browser Snapshot. Reporting: drop captures into the documents that Report Compile assembles, so stakeholders see the page, not a paraphrase of it.

Captures never leave your perimeter — relevant when the pages being photographed are logged-in internal systems — and each one is tied to the agent, session, and URL that produced it, which is precisely what separates governed browsing from a scraper with a screenshot habit.

Where it pays back

Where Screenshot Capture pays back

Visual QA

Confirm a page rendered as expected.

Evidence

Keep a visual record of a state or result.

Vision input

Feed a screenshot to image analysis.

Reporting

Include page images in an agent’s report.

How VDF AI connects it

Assigned to agents, orchestrated as networks

On VDF AI, an industry’s use cases map to agents, and you assign tools like this one to those agents. Compose multiple agents into a governed, on-premise network.

  1. 1
    Industry Your sector Finance, healthcare, telecom, government, and more.
  2. 2
    Use Case A job to be done Concrete workflows the business needs solved.
  3. 3
    Agent A specialized worker Governed AI agents that execute the use case.
  4. 4
    Tool Screenshot Capture The capability you assign to an agent.
  5. 5
    Network Agents, orchestrated Many use cases and agents, working as one.
ROI Snapshot

What changes after you assign it

Automated
Manual web steps removed
Any site
Even those with no API
Traceable
Every action audited
100%
Runs on infrastructure you control
FAQ

Questions about the Screenshot Capture tool

What is the Screenshot Capture tool?

It captures a screenshot of the full page or a specified element. Assigned to a VDF AI agent, it runs under role-based policy with full audit logging so the capability is safe to use in production.

Can it capture the whole page?

Yes. Set full_page to true, or pass a selector to capture a single element.

Where is the image stored?

In your own environment; nothing is sent to a third party.

Full page, viewport, or a single element — what exactly gets captured?

Your choice per call: the visible viewport by default, the entire scrollable page with full_page: true, or one element when you pass its selector — useful for capturing just the error banner, the chart, or the form that matters.

What format is the output and where does it go?

A PNG image stored in your own environment and attached to the agent run that produced it. From there it can be embedded in a report, kept as evidence, or handed to Image Analysis for a model to interpret what the page showed.

What inputs does the Screenshot Capture tool need?

It has no strictly required inputs, and optionally accepts selector and full_page. Each parameter is validated when an agent calls the tool, and the full call is logged for audit.

Which tools pair well with Screenshot Capture?

Screenshot Capture is commonly assigned alongside Browser Snapshot, Image Analysis, and Browser Navigate. On VDF AI you compose several tools and agents into a single governed, on-premise network.

Does it run on-premise?

Yes. Like every VDF AI tool, it can run on-premise or in your sovereign cloud, scoped per user and audit-logged, so your data never leaves your perimeter.

How do agents use it?

You assign the tool to an agent under a role-based policy; the agent calls it as one step in a task, and several agents and tools can be orchestrated together as a governed VDF AI Network.

Put Screenshot Capture to work

See the Screenshot Capture tool assigned to an agent and orchestrated in a governed, on-premise network.

Try it free on VDF AI Deploy on your own infrastructure