Web Search

MeinGPT can pull current information from the internet into your answers. There are three ways to do this. All of them use the same search under the hood (our search provider Linkup) — they differ in how you start them, which model answers, and where the result ends up.

The three ways at a glance

• Web search in the chat — switchable on top of any model via the "+" menu.
• The "MeinGPT Web" model — a chat model with web search built in.
• Research app — its own app in the sidebar, with history and "Deep Research".

The actual mechanics are described below under Web search in the chat; the other two ways refer back to it.

Web search in the chat

The built-in Web Search tool gives the model access to current information from the internet.

Enabling it

You enable web search in three places:

• in the "+" menu of the chat input (Tools → Web search, see Chat input area)
• in an Assistant that has web search set up as a tool
• per step in a Workflow

Who creates the search query

You don't provide the search terms directly — the AI model currently running your chat does. It reads your prompt and formulates a search query from it. In doing so it may reuse terms, names or internal designations from your prompt or from the conversation context. In research mode it passes your request on to a research agent largely in full, so wording from your prompt can end up in the search queries almost unchanged.

Two modes

Depending on the task, the model picks between two approaches on its own:

• Direct search — a single search query for quick, single facts.
• Research agent — for broader questions: a dedicated research step that runs several searches in sequence and reads individual pages in full before summarizing the result. This also applies when you provide a specific page (e.g. "Read https://example.com/whitepaper↗ and summarize the three key claims").

Forwarding to Linkup

The search query created by the model is forwarded to our search provider Linkup, which performs the actual web search and returns the hits (GDPR-compliant; More information↗).

From result to answer

Linkup returns the found content (titles, excerpts, sources) to the model. The model evaluates it and writes the final answer in the chat — with a preview of the sources (title, description, favicon) and references to the pages used.

The "MeinGPT Web" model

Instead of switching web search on, you can select the model MeinGPT Web directly in the model picker. It is based on Claude Haiku 5.5, is fast and EU-hosted, and has web search permanently enabled — you can't turn it off here. The flow and result are the same as with web search in the chat. Use it when you want quick, source-backed answers without toggling anything.

Research app

In the sidebar under Apps → Research, web search is available as its own app — with a dedicated page instead of a chat toggle. Web search is always active here. The search runs via Linkup, and like the MeinGPT Web model the same fast model answers (Claude Haiku 5.5). Two things differ from web search in the chat:

• Deep research (toggle): Unlike in the chat, where the model itself decides whether to search briefly or research more thoroughly, you decide via a toggle here. When enabled, a more thorough, multi-step research runs (more searches, more pages read) with a more detailed, cross-checked answer and more sources. It takes longer but often delivers better research results.
• History: Every research is saved. Under Past research you'll find your previous research again — searchable via the field above.

The three ways compared

All three use the same Linkup search — here are the differences at a glance:

Privacy: what web search sends out

With a web search, the search text and, where applicable, page URLs go to the external search provider Linkup. MeinGPT does not attach chat history, attachments, data pool contents or user or organization identifiers to the request itself. They only reach the search provider if their content is part of the search text or a URL.

• Search in the chat, in assistants and with MeinGPT Web: the model writes the search query and sees everything in the conversation to do so, including attachments and data pool hits. If it reads a page, that page's URL also goes to the search provider, including a pasted internal URL.
• Research app: without Deep Research, the text you type goes to the search provider unchanged. With Deep Research, a research agent writes the queries.
• Filter: by default the search text is not filtered. If the privacy filter is active in your workspace, it replaces detected personal data and defined protected terms with placeholders. It does not recognize general confidential business content.

Restricting web search as an admin

• Web search tool: in the tool access policies you can switch the web search tool off for chats, assistants and workflows started inside MeinGPT.
• Advanced web search: a separate tool with its own switch. Switching off regular web search does not affect it.
• Research app: can be hidden or limited to teams. This does not switch off web search in the chat.
• MeinGPT Web model: can be blocked in the model configuration. This does not remove web search from chats that use other models.

Research skill

Web search ships the skill web-research: for research questions the AI prefers primary sources, checks numbers and dates against several sources, names contradictions and uncertainties and backs every important statement with a numbered source. The skill is available as long as web search is active in the chat.

Good to know

Applies to all three ways:

• Paywalled and login-protected pages are usually not accessible.
• Very recent events (last few hours) may be missing depending on indexing.
• JavaScript-heavy pages without server rendering sometimes return only skeleton content.

Restricting sources to specific domains

For the web search on this page, there is no platform setting that restricts sources to specific domains. If you want to allow only certain sites, instruct the model directly in the prompt:

"Research GDPR compliance, use only heise.de and golem.de as sources."

This works reasonably well in practice but is not a hard security boundary. For critical research, verify the result manually against the named sources.

Advanced Web Search with a technical domain whitelist

For cases where a domain restriction needs to be more than a recommendation — where it needs to be technically enforced — there's a separate, additionally activatable tool: Advanced Web Search (internally: linkup-web-search). Unlike the standard web search on this page, it passes the source selection directly to the search API instead of only recommending it via the prompt.

Difference from standard web search

Adding it as a tool

1. Open the assistant editor or a workflow step.
2. In the Tools section, switch to the Databases tab.
3. Activate Advanced Web Search.
4. Open its configuration via the gear icon.

Configuration fields

Prompting tips for better web search results