Skip to main content
The Advanced Settings page configures advanced execution parameters for this project.

LLM Thinking

SettingDescriptionDefault
Enable ThinkingWhen enabled, the LLM provides detailed reasoning (thought) for each tool call. This improves traceability but increases token usage.Disabled

LLM Task Prompts

Customize the prompts that the system uses for entity extraction, correction detection, validation, and inference. Each prompt ships with a default system prompt, and you can expand it to view or edit the content.
PromptDescription
Entity Extraction PromptSystem prompt for extracting field values from user messages during data collection.
Correction Detection PromptDetects when a user corrects a previously provided value.
Field Validation PromptValidates extracted values against field rules and constraints before accepting them.
Field Inference PromptInfers missing field values from context when the user provides related information.

Escalation Templates

Customize the escalation confirmation messages that users see when a conversation hands off to a human agent. Each channel type has its own template:
ChannelDescription
Digital ChannelAppears in web chat and messaging apps. Supports markdown formatting and emoji.
Voice ChannelTTS reads it aloud on voice/phone channels. Keep it short and natural.
Plain TextFallback for SMS and channels without rich formatting support.
Each template supports {{reason}} and {{priority}} variables that the system substitutes at runtime with the actual escalation reason and priority level.

Danger Zone

The Danger Zone section permanently deletes the project and all its agents, tools, deployments, and settings. You can’t undo this action. Click Delete Project to proceed.

Settings Versions

The Settings Versions section lets you create versioned snapshots of all project settings. Click Create Version to save the current settings state. Versions enable deployment pinning, allowing you to associate a specific settings version with a deployment environment.