> ## Documentation Index
> Fetch the complete documentation index at: https://docs.trychainshift.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Naver AI Briefing

The `model` value is `NAVER_AI_BRIEFING`. Any behavior not listed here follows the [Supported models](https://docs.trychainshift.ai/en/models.md) table as-is.

## Where answers are collected

Naver AI Briefing answers are collected from the **"AI Briefing" block shown at the top of the Naver integrated search results page**. The prompt is entered as the search query to run a Naver integrated search, and the AI Briefing that appears at the very top of the results is collected. It is the Naver counterpart of Google's [Google Overview](https://docs.trychainshift.ai/en/model-specifics/google-overview.md), occupying the same position.

![An AI Briefing block shown at the top of Naver integrated search results](https://mintcdn.com/chainshift/KXnwIlgcCQxzYS5X/images/models/naver-ai-briefing-web.png?fit=max\&auto=format\&n=KXnwIlgcCQxzYS5X\&q=85\&s=8c652bc032380db632d5660216cd5f4a)

The Naver integrated search screen used for collection. The prompt is entered as the search query, and the body and sources of the 'AI Briefing' block at the top are collected.

Collection conditions are as follows.

* Collection happens **without signing in**. An account's search history and personalization settings do not affect the results.
* **The prompt is entered verbatim** as the search query. It is not rewritten or shortened to keywords.
* **Naver integrated search results** are used. The "AI" tab at the top is collected by a separate model, [Naver AI Tab](https://docs.trychainshift.ai/en/model-specifics/naver-ai-tab.md).
* **Only the `KR` region** is supported. It is a Korean service, so answers are not collected in other regions.

Screen elements map to answer object fields as follows.

| Screen element | Field | Notes |
| - | - | - |
| AI Briefing body | `content` | Full text in the expanded state. Original markdown is at `markdownURL` |
| Source chips next to sentences and items, cards at the top | `sources` | URL, title, and domain of each source the answer cites |
| — | `fanouts` | Not provided. Always an empty array |

> [!NOTE]
>
> **Some questions never get an AI Briefing.** Naver does not show an AI Briefing for every search query. For such prompts there is no answer to collect, so the run ends as `FAILED`. This is the expected outcome, not a collection error. No credits are deducted. A temporary collection failure also ends as `FAILED`, and the response alone does not tell the two apart. Run the same prompt once more; if it ends as `FAILED` again, treat it as a question that gets no AI Briefing.

## Model-specific behavior

Because it is a Korea-only service, answers are collected only in `KR`.

* Do not mix it into runs for other regions. If you put both `CHATGPT` and `NAVER_AI_BRIEFING` in `models` and set `region` to `JP`, the ChatGPT collection is rejected as well.
* Fan-out is not provided. `fanouts` is always an empty array.


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.