> ## Documentation Index
> Fetch the complete documentation index at: https://docs.prisme.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Agent Settings

> Configure retention, sharing, memory, and safety controls

Agent settings let you control how your agent stores data, who can access it, and what safety measures are in place.

## Accessing Settings

1. Open any agent in Agent Creator
2. Go to the **Settings** section
3. Navigate between tabs for different configuration areas

## General Settings

Basic agent configuration:

| Setting         | Description                |
| --------------- | -------------------------- |
| **Name**        | Display name for the agent |
| **Description** | What the agent does        |
| **Category**    | Organizational category    |
| **Tags**        | Keywords for discovery     |
| **Icon**        | Visual identifier          |

## Sharing & Access

Control who can use your agent.

### Visibility Levels

When you publish, choose visibility:

| Level            | Who Can Access                      |
| ---------------- | ----------------------------------- |
| **Private**      | Only you                            |
| **Organization** | Anyone in your organization         |
| **Public**       | All platform users                  |
| **Restricted**   | Specific users or groups you choose |

### Managing Access

For restricted visibility:

1. Go to Settings > Sharing
2. Click **Add Access**
3. Search for users or groups
4. Select the access level
5. Save

### Access Requests

When users request access to your agent:

1. You'll receive a notification
2. Go to Settings > Sharing > Requests
3. Review the request and message
4. Approve or deny

## Retention

Control how long data is kept.

### Conversation Retention

How long to keep chat history:

* **Inherit from organization** - Use org-wide default
* **Custom** - Set specific retention period (7-365 days)
* **No limit** - Keep indefinitely

### Document Retention

For uploaded files:

* Same options as conversation retention
* Applies to files attached in conversations

### Artifact Retention

For generated content (code, documents):

* Controls how long canvas artifacts are stored

<Note>
  Retention settings affect only future data. Existing data follows the policy that was active when it was created.
</Note>

## Memory

Configure how your agent remembers information.

### Session Memory

Remembers context within a conversation:

* **Enabled by default** for Light Agent and above
* Persists until conversation ends

### Long-term Memory

Remembers information across conversations:

* Available for Full Agent and Orchestrator profiles
* Stores facts, preferences, and context
* Searchable by the agent for relevant memories

To configure:

1. Go to Settings > Memory
2. Enable long-term memory
3. Set the maximum memories to recall (default: 50)
4. Save

<Tip>
  Long-term memory works best when you instruct the agent on what's worth remembering. Add guidance in your Instructions.
</Tip>

## Model Settings

Advanced model configuration:

| Setting             | Description                                        |
| ------------------- | -------------------------------------------------- |
| **Model**           | Primary AI model to use                            |
| **Fallback Models** | Backup models if primary fails                     |
| **Temperature**     | Creativity level (0 = deterministic, 1 = creative) |
| **Max Tokens**      | Limit on response length                           |

### Budget Limits

Control resource usage:

| Limit                | Description                            |
| -------------------- | -------------------------------------- |
| **Max Turns**        | Maximum back-and-forth in agentic loop |
| **Token Budget**     | Maximum tokens per conversation        |
| **Tool Call Budget** | Maximum tool calls per conversation    |

See [Runtime Safeguards](./runtime-safeguards) for what happens when a budget is reached and the other built-in protections that don't require configuration.

## Safety & Guardrails

Protect users and your organization.

### Input Guardrails

Filter incoming messages:

* **Profanity filter** - Block offensive language
* **PII detection** - Warn about personal information
* **Topic restrictions** - Block certain subjects

### Output Guardrails

Filter agent responses:

* **Hallucination check** - Flag uncertain claims
* **Sensitive content** - Block inappropriate responses
* **Compliance check** - Ensure regulatory adherence

### Action Approval

Require confirmation for sensitive operations:

| Policy           | Behavior                           |
| ---------------- | ---------------------------------- |
| **Auto**         | Tools execute automatically        |
| **Always Ask**   | User confirms every tool call      |
| **Ask External** | Confirm calls to external services |
| **Ask First**    | Confirm first call, then auto      |

Configure per-tool or as a default for all tools.

## Channels

Configure how your agent is accessed.

### Web Chat

The default chat interface:

* Enabled by default
* Customizable welcome message
* Suggested prompts for users

### API Access

Programmatic access:

1. Enable API access in Settings > Channels
2. Copy the endpoint URL
3. Use your API key to authenticate

### Embeds

Embed the chat widget on websites:

1. Enable embedding
2. Configure allowed domains
3. Copy the embed code
4. Add to your website

## Danger Zone

Irreversible actions:

### Unpublish

Remove the agent from public access while keeping the draft:

1. Go to Settings > Danger Zone
2. Click **Unpublish**
3. Confirm

The agent becomes draft-only. Existing conversations are preserved.

### Delete

Permanently remove the agent:

1. Go to Settings > Danger Zone
2. Click **Delete Agent**
3. Type the agent name to confirm
4. Click Delete

<Warning>
  Deletion is permanent. All conversations, test cases, and analytics data will be lost.
</Warning>

## Next Steps

<CardGroup cols="2">
  <Card title="Publish your agent" icon="rocket" href="./creating-agents#publishing--sharing">
    Make your agent available to others
  </Card>

  <Card title="View analytics" icon="chart-line" href="./analytics">
    See how users interact with your agent
  </Card>
</CardGroup>