Reasoning Effort in AI Assistant

Reasoning effort controls how much time and computation AI Assistant uses to work through a request.

A lower effort level usually produces a faster response and uses fewer AI limits. A higher effort level may produce a more thorough response, but it can take longer and use AI limits faster.

View the Applied Reasoning Effort

Open the agent menu in AI Assistant to see the reasoning effort applied to the current chat.

In the initial experimental version, the menu displays Agent default. The effort level is predefined and read-only.

How Reasoning Effort Works

AI Assistant applies the predefined reasoning effort to each request. It does not automatically change the effort based on the complexity of the question.

The exact effect of an effort level can vary depending on the active LLM provider and model. LLM providers support different reasoning settings, so GoodData maps the applied effort to the closest supported provider behavior.

Current Limitations

The following limitations apply while the feature is experimental:

• You cannot configure the default reasoning effort for an agent in Agent Builder or Agent Hub.
• You cannot override the reasoning effort for an individual question.
• The effort level does not change automatically based on question complexity.
• The effect of the applied effort may vary between LLM providers and models.