AI Studio Docs
AI Agents

Advance Settings

Max tokens, a fallback model, and Search Mode

  • Max tokens: a ceiling on how long a single reply can run, to bound latency and cost.
  • Fallback model: a second model or provider to retry with if the primary call fails or is cut off at its token limit, so a visitor gets a usable reply instead of an error. Leave it unset and a failed call simply fails, exactly as it always has.
  • Search Mode: trades retrieval depth for speed when the agent looks up relevant training content:
    • Fast: fewer matches, quicker answers.
    • Balanced: the default.
    • Thorough: more matches, slower but more likely to find something relevant in a large knowledge base.