---
title: "How Web search works: delegated research and evidence"
description: "Duale AI Web search delegates a bounded question to a dedicated executor that searches, reads, and returns a compact evidence package."
lang: en
status: public-preview
lastUpdated: 2026-09-04
url: https://duale.ai/en/docs/web/how-web-search-works
---

## AI-generated summary

The coordinating agent delegates a bounded research question to a Web research executor that searches, reads, and compares sources in an isolated context, then returns a structured evidence package.

- The executor receives only the brief, not the parent conversation or document history.
- The executor has only Web search, page reading, and completion tools available.
- The evidence package includes a concise answer, claims, sources, citations with excerpts, and unresolved gaps.
- Each cited source must be marked as read; search extracts alone cannot serve as citations.

Summaries were generated by AI. Generative AI is experimental.

---

When a task needs public evidence, the coordinating agent delegates a bounded question to a dedicated Web research
executor. An executor is a specialist agent that handles one delegated unit of work. It runs a short, source-led review
in its own context: it searches, reads, compares, and reports before the coordinating agent continues the main task.

```mermaid
flowchart TD
    accTitle: How a delegated Web research run reaches a task result
    accDescr {
      The coordinating agent keeps the main task conversation and document
      history. It sends only a bounded research brief to a dedicated Web
      research executor. That executor creates focused queries, reviews
      candidate pages, reads selected sources, and returns a compact evidence
      package. The coordinating agent uses that package in the final task result.
    }
    Task[Main task conversation and documents]
    Agent[Coordinating agent]
    Brief[Bounded research brief]
    Research[Dedicated Web research executor]
    Queries[Focused queries]
    Pages[Selected public pages]
    Evidence[Claims, sources, excerpts, and gaps]
    Result[Terminal task result]
    Task --> Agent
    Agent --> Brief
    Brief -->|new research context| Research
    Research --> Queries
    Queries --> Pages
    Pages --> Research
    Research --> Evidence
    Evidence --> Agent
    Agent --> Result
```

## Delegate one research question

The coordinating agent decides whether the task needs external evidence. For a broad or unclear subject, it first asks
for a small evidence brief before it splits the work further. For a focused subject, it can delegate the research
directly.

The router starts a new executor for that brief. The new context contains the brief, not the parent conversation,
document history, or tool results. The executor has only Web search, page reading, and completion tools. It cannot call
your registered tools or delegate the work again.

This separation keeps the research question apart from the wider task strategy. It also keeps full page content inside
the research context: the coordinating agent receives the condensed evidence package, not every raw search result and
page.

## Run a bounded source review

The Web research executor turns the brief into an evidence checklist and several focused queries. It batches independent
queries instead of sending one result back to the coordinating agent at a time. Search returns candidate pages ordered
for relevance. The executor then opens the most useful pages and works from their extracted content and final URLs, not
from search extracts alone.

Within the same delegated run, the executor can refine its queries, compare publishers, reject weak or duplicate
sources, and record evidence gaps. The loop is bounded: it stops when the evidence is sufficient, when
new searches add no material information, or when the research limit is reached.

## Return evidence, then finish the task

The executor returns one structured package to the coordinating agent. It contains a concise answer, individual claims,
sources that it reviewed, claim-linked citations with excerpts, and unresolved gaps. The evidence contract requires the
executor to mark each cited source as read; it cannot use a search extract alone as a citation.

The coordinating agent combines this package with the rest of the task. Your terminal SDK result still follows the
response model that your application requested. The SDK does not add the internal research package as a separate field,
so request source fields in the final model when your application must retain them.

This process gives the coordinating agent several reviewed sources and explicit gaps. It does not make every source
independent or every claim true. [Request Web research](https://duale.ai/en/docs/web/request-web-research.md) shows how to retain source
fields. [Sources and factuality](https://duale.ai/en/docs/web/sources-and-factuality.md) explains how to review them.

## Understand the data boundary

Only the delegated brief enters the Web research context. Parts of that brief can become public search queries. Include
only the detail needed to find the evidence, and do not include secrets.

[Data protection](https://duale.ai/en/docs/security/data-protection.md) covers query and page-request paths. [Page
access](https://duale.ai/en/docs/web/page-access.md) covers supported page behavior. [Troubleshoot Web
search](https://duale.ai/en/docs/web/troubleshooting.md) covers missing or unreadable sources.

## Related content

- [Web search: delegated, source-led research for agent tasks](https://duale.ai/en/docs/web.md)
- [Troubleshoot Web search when results are missing or blocked](https://duale.ai/en/docs/web/troubleshooting.md)
- [Sources, citations, and factuality](https://duale.ai/en/docs/web/sources-and-factuality.md)
- [Request Web research with source links](https://duale.ai/en/docs/web/request-web-research.md)
- [Page access for the Web research executor](https://duale.ai/en/docs/web/page-access.md)
- [Keep context across long-running work](https://duale.ai/en/docs/agent-harness/context-continuity.md)

---

## Sitemap

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