Berges Web

Berges Web

Search and fetch when the answer needs primary sources. Pick Web from the sidebar; off by default so chats stay private.

Web is the interceptor for questions that need fresh sources. Pick it from the sidebar and the deep-thinking layer gains two tools: web_search for finding candidate sources and fetch_url for reading them in full. The model decides when to use them.

It's off by default. Berges AI is a private chat first; browsing on every turn would compromise that. Web is the explicit opt-in for the turns when current information actually matters.

How it works

What changes when you pick it.

Two tools

web_search returns title + URL + snippet for a query. fetch_url returns the main text of a specific page. The model typically searches first, then fetches the best result.

Iterative

A single message can include multiple searches and fetches. The model loops through tool calls until it has what it needs, then writes the final answer with the URLs it used.

Visible activity

Every search and fetch shows up as a badge in your message bubble ("Searched: X", "Fetched Y"). You can tell at a glance whether the answer came from the web or just the model.

Thinking-tier only

Tools never run on the fast layer. Easy questions stay snappy and offline; Web only kicks in once the cascade has escalated.

Reach for it when

Web is the right pick.

  • Current events, recent news, or anything that depends on this week's state of the world
  • Named entities the model might not know (new products, niche companies, recent papers)
  • Pricing, specifications, or release dates that change over time
  • Anything you'd want to cite a source for
Try it

Example prompts.

Not for

When to skip it.

  • × Casual chat or brainstorming. The Web interceptor adds latency and discloses your queries to a third-party search provider.
  • × Sensitive topics you don't want a search provider to see. The Brainstorm or Reasoning interceptors stay fully offline.
  • × Real-time data (live scores, stock ticks). Search results are minutes-to-hours stale; we're not a market data feed.
Questions

Things people ask about Web.

Who sees my search queries?

When Web is active, your search queries are sent to a third-party search provider (currently Brave Search). They process the query to return results and do not retain it for training. See the Privacy Policy for details.

Will Web make my chats slower?

Yes, when it actually uses the tools. Each search and fetch adds a round trip. A typical Web-assisted answer takes a few extra seconds compared to a non-Web answer.

Can the model fetch any URL?

Almost. We block private, loopback, and link-local IP ranges at the network level so the model can't poke at internal services. Public URLs work; size and time limits apply.

Do you store the search results?

No. Results are fed to the model for the turn and discarded. Only your message and the final assistant reply are persisted (encrypted at rest, same as everything else).