> For the complete documentation index, see [llms.txt](https://archer-bot.gitbook.io/archer.bot/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://archer-bot.gitbook.io/archer.bot/intents/web-search.md).

# Web Search & Market Research

Crypto moves too fast for an LLM's training data to keep up. When you ask Archer a question that depends on current information — news, regulation, recent launches, ecosystem updates — it routes through live web search instead of guessing from cached knowledge.

## Sample Input Queries

* *"What's happening with Ethereum lately?"*
* *"Any news about the Solana ecosystem?"*
* *"Latest crypto regulation news"*
* *"What did the Fed announce today?"*
* *"Has the SEC ruled on ETF approvals this week?"*
* *"Any updates on the Base ecosystem?"*

## What It Does

The `web_search` tool runs a live search and returns headlines with linked sources. Archer then summarizes the results in plain English in your thread, with the citations preserved so you can drill into anything that matters.

## When Archer Uses Web Search vs Stored Knowledge

* **Web search**: news, current prices in narrative form (e.g., *"is BTC up today?"*), regulatory developments, recent launches, anything time-sensitive
* **Stored knowledge**: how a protocol works in general, what an AMM is, the difference between L1 and L2, how to think about slippage

The agent decides based on the query — you don't have to ask explicitly.

## Sample Output Structure

```json
{
  "status": "OK",
  "query": "latest crypto regulation news",
  "results": [
    {
      "title": "SEC Approves Spot Solana ETF",
      "url": "https://...",
      "snippet": "The U.S. Securities and Exchange Commission approved...",
      "publishedAt": "2026-04-27T18:30:00Z",
      "source": "Reuters"
    },
    {
      "title": "...",
      "url": "...",
      "snippet": "...",
      "publishedAt": "2026-04-27T14:15:00Z",
      "source": "CoinDesk"
    }
  ]
}
```

## What Web Search Doesn't Do

* It doesn't open URLs and read full articles end-to-end — it works from headlines, snippets, and search-result summaries
* It doesn't trade on news. Archer never auto-executes based on a search result. You always drive the action.
* It doesn't give financial advice. Search results are summarized as information, not recommendations.
* It doesn't always provide perfect responses. Therefore, Web Search will eventually be deprecated in favor of agents that are more dedicated to optimized news retrieval. 


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter:

```
GET https://archer-bot.gitbook.io/archer.bot/intents/web-search.md?ask=<question>&goal=<endgoal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.