FR EN

07 November 2025

BDS1 - Brained DeepSearch 1

BDS1 is an agent that alternates between searching (internet and/or RAG) and reasoning to respond to complex queries, “x4” means that it has 4 cycles.

Easy customization: It’s easy to modify it to suit a research field, your use, an LLM, or other purposes.

It’s recomended to use tools designed for BDS1 (like Brained Search) because these tools return only the important information and don’t overload the LLM context with unnecessary information. LLMs provide much more interesting answers if their context is not overloaded.

It is often very useful to add a RAG search tool because vector-based search is much more effective than web search.

Prompt System

Its prompt system is in English because that’s generally the language that LLMs understand best. if you speak another language besides English, for best results, I recommend writing your queries in English and translating the response, or you can modify an instruction at the end of the system prompt so that it writes the response in your language:

Write a structured response that:

Usage Tips

With some LLMs, it’s best to start with: “Follow your system prompt’s process to write a … (guide, article, report, study, analysis, detailed comparison, etc.)”

You can provide a URL and specify whether you want it to request a summary (summarize this URL: the_url.com) or the entire page (scrape this URL: the_url.com) which will take more tokens in context than the summary. These two functions are in the Brained Search main tool.

Sharing

If you modify it and share it in the Open WebUI community or elsewhere, please share the link here or in the domains pages if it’s specific to a domain .