Email Agent Configuration - SubVerse AI

Identity

Field	Type	Default	Description
Name	Text	— (required)	Unique identifier. Lowercase letters, numbers, and underscores only (e.g. `support_email_bot`). Must start with a letter.
Description	Text	`""`	Internal description of what this agent handles.
Architecture	Dropdown	`Prompt Based`	Prompt Based uses a system prompt. Conversational Flow uses a visual node-based builder.
Debug Mode	Toggle	Off	Outputs extra internal logs. Use during development; disable in production.

Agent Settings

Field	Type	Default	Description
Greeting Message	Text	`""`	Rarely used for email agents — the agent typically responds to incoming email rather than initiating.
Greeting Type	Dropdown	`Prompt`	Prompt — dynamically generated opening. Say — sends exact text verbatim.
Who Speaks First	Dropdown	`SubVerseAI Agent`	Set to User for email agents so the agent waits for an incoming email before responding.
System Prompt	Text area	Empty	The main system prompt. Describe the agent’s purpose, tone, rules, and how it should handle different types of emails. Use the Refine using AI button for assistance.

Large Language Model Preferences

Field	Type	Default	Description
LLM Model	Dropdown	— (required)	The AI model powering this agent. Each model shows its speed and reasoning ratings.
Thinking Level	Dropdown	`Default`	Extended reasoning depth. Options: Default, Low, Medium, High, Very High. Higher = better reasoning but slower.
Max Tokens	Number	None	Maximum tokens the LLM can generate per response. Leave blank to use the model’s default.
Temperature	Slider	`0.5`	Response creativity. For support emails, a lower value (0.2–0.5) is usually better.

Session Settings

Field	Type	Default	Description
Communication Method	Dropdown	`Two Way`	Two Way — agent reads and replies to emails. One Way — agent only sends.
Session Timeout (mins)	Number	None	Minutes after which an idle email processing session ends automatically.
Remember Customer Interactions	Toggle	Off	Save a summary of each email thread to memory after the session closes.
Use Customer Interaction Memory	Toggle	Off	Pull relevant past email summaries into context when the same sender emails again. Enable both for continuity across separate email conversations.

Knowledgebase Settings

Field	Type	Default	Description
Knowledge Base	Dropdown	None	Attach a Knowledge Base so the agent can look up answers from your documents when composing replies.

Function Settings

Field	Type	Default	Description
Pre Call Tools	Multi-select	Empty	LLM tools that run before the agent processes the email (e.g. fetch customer account info).
During Call Tools	Multi-select	Empty	Tools the agent can call while composing its reply (e.g. check order status, look up ticket history).
Post Call Tools	Multi-select	Empty	LLM tools that run after the reply is sent (e.g. create a support ticket, log to CRM).

Agent Security Settings

Field	Type	Default	Description
Allow List (Allowed Callers)	Text area	Empty	Regex patterns for email addresses allowed to trigger this agent, separated by commas. Example: `.*@yourdomain\.com` to allow only your domain. Leave empty to allow all senders.
Block List (Blocked Callers)	Text area	Empty	Regex patterns for email addresses that are blocked, separated by commas. Takes priority over Allow List.

Post Call Data Analysis

After each email session, the agent can automatically analyze the conversation and extract structured data.

Field	Type	Description
LLM Model	Dropdown	The AI model used to run the post-session analysis. Can differ from the main agent model.
Parameters	Form / JSON	Define the data points to extract from each email conversation. Switch between Form (add parameters one by one) and JSON (paste a raw JSON schema).

Parameter fields:

Field	Description
Parameter Name	The key name for this data point (e.g. `summary`, `user_sentiment`).
Details	Description of what this parameter represents and how to extract it.
Type	Data type: `string`, `boolean`, `number`, etc.
Required	Whether this parameter must be present in every analysis output.