---
title: "Request Web research with source links"
description: "Requesting Web research with source-linked claims lets your application reject incomplete results before a person reviews the sources."
lang: en
status: public-preview
lastUpdated: 2026-09-04
url: https://duale.ai/en/docs/web/request-web-research
---

## AI-generated summary

Define a dated public question, retain claim-linked sources and evidence gaps in the response model, and review material sources before accepting results.

- The acceptance contract specifies the public question, validity date, source types, and conflict reporting rules.
- The response model requires source material per claim but does not prove claim truth.
- SOURCE_REVIEW_REQUIRED is not an approval signal; open material sources and apply the full acceptance test.
- If response.model() raises an error, record response.task_id and check task state before submitting a replacement.

Summaries were generated by AI. Generative AI is experimental.

---

Use this guide after you can submit a typed task with the [Python SDK](https://duale.ai/en/docs/sdk.md). Request dated claims, final
source URLs, disagreements, and evidence gaps. Your application can reject an incomplete result before a person
reviews the sources.

## Define the acceptance contract

Before you submit the task, define:

- the public question and the date at which the answer must be valid;
- the material claims that need support and the preferred primary source types;
- how the result must report conflicts, missing dates, and evidence gaps;
- the claims that need a person or an independent rule-based check.

The coordinating agent delegates a bounded brief to the Web research executor; it does not copy the full task history.
Keep that brief public. Context isolation does not redact a credential, private URL, confidential passage, or unnecessary
personal data that the coordinating agent includes in the brief.

## Request source-linked fields

The following example is illustrative. It uses a placeholder topic and is not a tested, runnable example.

```python
import asyncio
from datetime import UTC, datetime, timedelta
from pydantic import BaseModel, Field

from duale import ask, create_sdk

class Evidence(BaseModel):
    final_url: str
    publisher: str
    published_at: str | None = None
    excerpt: str

class Claim(BaseModel):
    text: str
    sources: list[Evidence] = Field(min_length=1)

class WebResearchResult(BaseModel):
    answer: str
    claims: list[Claim] = Field(default_factory=list)
    disagreements: list[str] = Field(default_factory=list)
    evidence_gaps: list[str] = Field(default_factory=list)
    valid_as_of: str

async def main() -> None:
    async with create_sdk() as sdk:
        response = await ask(
            action=(
                "Research this public topic: <public, non-sensitive topic>. "
                "Give an answer valid as of <YYYY-MM-DD>. Prefer primary sources. "
                "For each material claim, return the final URL, publisher, publication date, "
                "and a short supporting excerpt from every source you use. Report disagreements "
                "and evidence gaps. Return no claim when the available pages do not support it."
            ),
            res=WebResearchResult,
            deadline=datetime.now(UTC) + timedelta(minutes=10),
            sdk=sdk,
        )
        result = await response.model()

        if not result.claims:
            print(response.task_id, "STOP: no supported claims")
            return

        print(
            response.task_id,
            "SOURCE_REVIEW_REQUIRED",
            len(result.claims),
            len(result.evidence_gaps),
        )

asyncio.run(main())
```

When the result contains at least one source-linked claim, the example prints:

```text
<task_id> SOURCE_REVIEW_REQUIRED <claim_count> <gap_count>
```

Choose a deadline that fits your workflow. The ten-minute deadline above is an example, not a web completion
guarantee.

The response model gives the final task result a fixed shape and requires source material for each returned claim. It
does not expose the internal Web research record or prove that a publisher is independent or a claim is true.

## Review the sources

`SOURCE_REVIEW_REQUIRED` is not an approval signal. Open the material sources and apply the full acceptance test in
[Sources and factuality](https://duale.ai/en/docs/web/sources-and-factuality.md). If a source fails, narrow the claim, request another
public source, or keep an evidence gap.

## Recover safely

If `response.model()` raises an SDK or validation error, record `response.task_id` and read [Errors and
reliability](https://duale.ai/en/docs/sdk/errors.md) before you submit another task. A submission with a new task identifier creates new
work.

Before you submit a replacement task, check the first task's state and any external effect from your registered tools.
[Secure integration](https://duale.ai/en/docs/security/secure-integration.md) explains repeat-safe tool design and approval.

If the result contains no supported claim, keep the gap. Change one search condition at a time or use another public
source.

## Related content

- [Sources, citations, and factuality](https://duale.ai/en/docs/web/sources-and-factuality.md)
- [How Web search works: delegated research and evidence](https://duale.ai/en/docs/web/how-web-search-works.md)
- [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)
- [Page access for the Web research executor](https://duale.ai/en/docs/web/page-access.md)
- [Know what the platform defends](https://duale.ai/en/docs/security/threat-model.md)

---

## Sitemap

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