Berges Reasoning

Berges Reasoning

Structured, step-by-step thinking on demand. Pick the Reasoning interceptor from the sidebar when you want the model to slow down and show its work.

Reasoning is one of three interceptors Berges AI ships with. Pick it from the sidebar and the deep-thinking layer switches into a mode tuned for structured, multi-step thought: lay out the inputs, work through them in order, land on a conclusion.

It's the right choice when the answer matters more than the prose, and when getting to the answer requires staying organized through more than one or two hops.

How it works

What changes when you pick it.

Lower randomness

Reasoning uses a low sampling temperature, which keeps the model consistent across runs. Ask the same question twice and you should get a similar shape of answer, which is what you want for analysis.

A reasoning-first system prompt

On top of whatever model is running, Reasoning layers a system prompt that asks for steps, evidence, and a conclusion. The Berges-style framework is the proprietary part.

Thinking-tier only

Reasoning only kicks in on escalated turns. Easy questions still go through the fast layer untouched, so you don't pay the cost of structured thinking on a trivial question.

Reach for it when

Reasoning is the right pick.

  • Math and quantitative problems
  • Multi-step decisions (e.g. "should I refinance given these numbers")
  • Debugging or root-cause analysis
  • Comparing options against explicit criteria
  • Anything where you'd want to see the work, not just the answer
Try it

Example prompts.

Put it to work

Things to do with Reasoning.

Questions

Things people ask about Reasoning.

When should I not use Reasoning?

When the question is easy or open-ended. Reasoning makes the model slower and more methodical, which is the wrong shape for "give me five name ideas" or "what time is it in Tokyo".

Is Reasoning the same as "think hard"?

Related but not identical. Saying "think hard" (or "think harder") in a message forces escalation to the deep-thinking layer for that turn. Reasoning, when selected, also escalates and additionally applies the structured-thinking system prompt.

Does Reasoning work with all models?

Yes. Interceptors operate on top of whichever model the cascade picks, so the Reasoning system prompt and lower temperature apply regardless of whether the underlying model is Kimi, DeepSeek-Pro, or MiniMax.