---
title: "Page access for the Web research executor"
description: "Page access lets the Web research executor read a public HTTP or HTTPS URL, rendering JavaScript and returning extracted Markdown, title, and final URL."
lang: en
status: public-preview
lastUpdated: 2026-08-31
url: https://dev.duale.ai/en/docs/web/page-access
---

## AI-generated summary

Page access lets the Web research executor read a public HTTP or HTTPS URL, receiving extracted Markdown, page title, and final URL.

- The application receives no browser tab, page structure, or browser object.
- Related reads by the same executor can reuse cookies and origin storage from visited pages.
- Page access does not support login workflows, form completion, or credential entry.
- It supports public web content only, not local files, private networks, or other URL schemes.

Summaries were generated by AI. Generative AI is experimental.

---

Page access lets the Web research executor read one public HTTP or HTTPS address. It renders page JavaScript and gives
the executor extracted Markdown, the page title, and the final URL. Your application does not receive a browser tab,
page structure, or browser object.

Page JavaScript can make normal site requests and change site-side state. A repeated page read repeats the external
request. Page access does not provide a supported login workflow.

## Capability boundary

| Page access does                                              | Page access does not                                                              |
| ------------------------------------------------------------- | --------------------------------------------------------------------------------- |
| Open a public HTTP or HTTPS URL                               | Provide supported access to arbitrary protocols, local files, or private networks |
| Render JavaScript before extraction                           | Give your application a live tab or page structure                                |
| Report the title and final URL after navigation               | Prove that the page is safe, correct, or authoritative                            |
| Extract supported page or online-document content as Markdown | Preserve the source layout or return a screenshot or PDF                          |
| Reuse limited site state for related reads                    | Click controls, complete forms, enter credentials, or run a login workflow        |

A URL can open but return little or no usable Markdown. Access controls, a visual-only layout, an unsupported format, a
large document, or an extraction failure can cause omissions. Use another public representation if you need the exact
layout or complete source file. [Troubleshoot Web search](https://dev.duale.ai/en/docs/web/troubleshooting.md) gives the safe recovery paths.

## Session state

Related reads by the same Web research executor can reuse cookies and origin storage set by visited pages. This supports
public sites that need continuity across more than one read. It does not restore a live tab, provide durable application
storage, or create a supported sign-in flow.

See [Data protection](https://dev.duale.ai/en/docs/security/data-protection.md) for the page-cache rule and [Threat
model](https://dev.duale.ai/en/docs/security/threat-model.md) for how external page text can affect later work.

## Network and site boundaries

Page access supports public web content only. It does not provide supported access to local files, private-network
destinations, or other URL schemes. See [Security](https://dev.duale.ai/en/docs/security.md) for the controls and residual risks of web access.

Public availability does not grant a right to collect or reuse content. Follow the publisher's terms and the [Duale AI
Terms of Use](https://dev.duale.ai/en/legal/cgu.md).

## Related content

- [Web search: delegated, source-led research for agent tasks](https://dev.duale.ai/en/docs/web.md)
- [How Web search works: delegated research and evidence](https://dev.duale.ai/en/docs/web/how-web-search-works.md)
- [Sources, citations, and factuality](https://dev.duale.ai/en/docs/web/sources-and-factuality.md)
- [Request Web research with source links](https://dev.duale.ai/en/docs/web/request-web-research.md)
- [Troubleshoot Web search when results are missing or blocked](https://dev.duale.ai/en/docs/web/troubleshooting.md)
- [How an agent finds an answer in your documents](https://dev.duale.ai/en/docs/libraries/what-agents-can-do.md)

---

## Sitemap

See the full [Markdown sitemap](https://dev.duale.ai/sitemap.md) for all pages.