> ## Documentation Index
> Fetch the complete documentation index at: https://docs.subverseai.com/llms.txt
> Use this file to discover all available pages before exploring further.
# Chat Agent Configuration
> Full configuration reference for Chat Agents
## Identity
| Field | Type | Default | Description |
| ------------ | -------- | -------------- | ------------------------------------------------------------------------------------------------------------------- |
| Name | Text | — (required) | Unique identifier. Lowercase letters, numbers, and underscores only (e.g. `support_bot`). Must start with a letter. |
| Description | Text | `""` | Internal description of what this agent does. |
| 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 reasoning logs. Use during development; disable in production. |
***
## Agent Settings
| Field | Type | Default | Description |
| ---------------- | --------- | ------------------ | ---------------------------------------------------------------------------------------------------------------------------------------- |
| Greeting Message | Text | `""` | The first message the agent sends when a conversation starts. Leave blank if you want the user to write first. |
| Greeting Type | Dropdown | `Prompt` | **Prompt** — agent generates the opening message dynamically. **Say** — agent sends exactly what you typed. |
| Who Speaks First | Dropdown | `SubVerseAI Agent` | **SubVerseAI Agent** — agent opens the conversation. **User** — agent waits for the user to write first. |
| System Prompt | Text area | Empty | The main system prompt. Write the agent's role, tone, rules, and behavior here. Use the **Refine using AI** button to get AI 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. `0.0` = consistent and precise. `1.0+` = more varied and creative. |
***
## Session Settings
| Field | Type | Default | Description |
| ------------------------------- | -------- | --------- | --------------------------------------------------------------------------------------------------------------------------------------------- |
| Communication Method | Dropdown | `Two Way` | **Two Way** — agent sends and receives messages. **One Way** — agent only sends (e.g. broadcast mode). |
| Session Timeout (mins) | Number | None | Minutes of inactivity after which the session ends automatically. Leave blank for no timeout. |
| Remember Customer Interactions | Toggle | Off | Save a summary of each conversation to memory after the session ends. |
| Use Customer Interaction Memory | Toggle | Off | Pull relevant past conversation summaries into context at the start of a new session. Enable both for persistent memory across conversations. |
***
## Knowledgebase Settings
| Field | Type | Default | Description |
| -------------- | -------- | ------- | ---------------------------------------------------------------------------------------------------- |
| Knowledge Base | Dropdown | None | Attach a Knowledge Base so the agent can retrieve answers from your documents during a conversation. |
***
## Function Settings
| Field | Type | Default | Description |
| ----------------- | ------------ | ------- | -------------------------------------------------------------------------------------------- |
| Pre Call Tools | Multi-select | Empty | LLM tools that run automatically before the session starts (e.g. fetch customer data). |
| During Call Tools | Multi-select | Empty | Tools the agent can call mid-conversation (e.g. check order status, send an email). |
| Post Call Tools | Multi-select | Empty | LLM tools that run automatically after the session ends (e.g. update CRM, send a follow-up). |
***
## Agent Security Settings
| Field | Type | Default | Description |
| ---------------------------- | --------- | ------- | -------------------------------------------------------------------------------------------------------------------- |
| Allow List (Allowed Callers) | Text area | Empty | Regex patterns for contacts allowed to interact with this agent, separated by commas. Leave empty to allow everyone. |
| Block List (Blocked Callers) | Text area | Empty | Regex patterns for contacts that are blocked, separated by commas. Takes priority over Allow List. |
***
## Post Call Data Analysis
After each conversation, the agent can automatically analyze the transcript 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 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. |