# Settings Guide

This page describes the settings available in the AGENTIC STAR marketplace edition admin console.

## Accessing the Admin Console

After deployment completes, open the admin console URL in your browser and sign in using the administrator email and password you provided at purchase.

![Admin console dashboard](https://developers.fd.agenticstar.tm.softbank.jp/en/assets/images/admin-dashboard-aa72f7354bbbf4a0cfebfbb27062a688.png)

> **note**
>
> A self-signed certificate is shipped by default, so your browser will show a certificate warning. Allow the exception to proceed. To configure a proper SSL certificate, see the [Domain Configuration Guide](https://developers.fd.agenticstar.tm.softbank.jp/en/docs/marketplace/basic/build/guide/domain-guide.md).

## Menu Structure

The admin console is organized as follows:

| Category              | Menu                    | Description                                       |
| --------------------- | ----------------------- | ------------------------------------------------- |
| —                     | **Dashboard**           | Overview of usage                                 |
| **User Management**   | Administrators          | Manage admins who can access the admin console    |
|                       | Users                   | Manage end users                                  |
|                       | Service Accounts        | Manage service accounts for API use               |
| **Agent Management**  | AI Persona              | Manage agent response personas                    |
|                       | MCP Servers             | Manage MCP servers                                |
|                       | LLM Settings            | Configure LLM providers and models                |
|                       | Agent Settings          | Register and manage custom agents                 |
|                       | Guardrail Settings      | Content Safety and PII masking                    |
|                       | Blocked URLs            | Manage URLs that agents are not allowed to access |
| **Master Data**       | Organizations           | Manage organization information                   |
|                       | Job Types               | Manage the job-type master                        |
|                       | Announcements           | Manage announcements for end users                |
|                       | Email Provider Settings | Configure the email provider                      |
| **Log Management**    | Audit Logs              | History of admin operations                       |
|                       | LLM Audit Logs          | History of LLM usage                              |
|                       | Reports                 | Review user reports                               |
|                       | Access Logs             | Access history                                    |
| **System Management** | Notification Settings   | Configure notification email sending              |
| —                     | **Version Management**  | Check the platform version and perform upgrades   |

## User Management

### Administrators

Manage administrator accounts that can access the admin console. The initial administrator is auto-created at purchase time.

### Users

Manage end users of AGENTIC STAR. You can add, edit, and disable users.

### Service Accounts

Create and manage service accounts for API access. Creating a service account issues a client ID and client secret used for API authentication.

For how to use the API, see the [Marketplace API Quickstart](https://developers.fd.agenticstar.tm.softbank.jp/en/docs/marketplace/basic/api/quickstart/call-api.md).

## Agent Management

### AI Persona

Register and manage response styles ("personas") for agents. By specifying `personaKey` on a chat invocation, you can switch the tone and voice of the agent's responses.

There are two kinds of personas:

| Kind         | Description                                                                                                             |
| ------------ | ----------------------------------------------------------------------------------------------------------------------- |
| **Official** | Personas shipped with the platform. They cannot be edited or deleted (and no additional locales can be added).          |
| **Custom**   | Personas created and managed by the tenant. You can register instructions in multiple locales for multilingual support. |

#### Main Settings

| Setting                | Description                                                                       |
| ---------------------- | --------------------------------------------------------------------------------- |
| **Persona Key**        | Persona identifier (1–64 characters, alphanumeric + hyphen + underscore)          |
| **Name**               | Display name of the persona                                                       |
| **Description**        | Summary of the persona                                                            |
| **Instruction**        | The persona / tone instruction passed to the agent (can be registered per locale) |
| **Tags**               | Tags for classification                                                           |
| **Enabled / Disabled** | Toggle whether the persona is selectable                                          |

### LLM Settings

Configure the LLM provider and model used by agents.

![LLM settings screen](https://developers.fd.agenticstar.tm.softbank.jp/en/assets/images/admin-llm-settings-ddabf6e24c71db141fac1ad4b76b104b.png)

| Setting                 | Description                                        |
| ----------------------- | -------------------------------------------------- |
| **Agent Type**          | The agent type the setting applies to              |
| **Model**               | Model name (LiteLLM format: `provider/model-name`) |
| **API Key**             | API key for the LLM provider                       |
| **Base URL**            | Endpoint URL for the LLM provider                  |
| **API Version**         | API version (`YYYY-MM-DD` format)                  |
| **Additional Settings** | Extra parameters in JSON format                    |

> **note**
>
> Sensitive values such as API keys are displayed as `********` after they are saved. If you do not change them, the existing values are retained.

### Agent Settings

Register custom agents to make them available on the platform.

#### Basic Information

| Setting          | Description                                                                |
| ---------------- | -------------------------------------------------------------------------- |
| **Agent ID**     | Agent identifier (lowercase alphanumeric and hyphens, up to 63 characters) |
| **Display Name** | Display name of the agent                                                  |
| **Description**  | Description of the agent                                                   |
| **Icon**         | Upload an icon image (PNG / JPEG, 512 KB or less)                          |
| **Tags**         | Tags for classification (comma-separated)                                  |

#### Docker Image

| Setting               | Description                                       |
| --------------------- | ------------------------------------------------- |
| **Registry**          | Container registry URL (e.g., `myacr.azurecr.io`) |
| **Image Name**        | Image name (e.g., `my-org/rag-agent`)             |
| **Image Tag**         | Image tag (default: `latest`)                     |
| **Image Pull Secret** | Authentication secret for a private registry      |

#### Resources

| Setting                    | Description                              |
| -------------------------- | ---------------------------------------- |
| **CPU Request / Limit**    | CPU allocation (e.g., `500m`, `2000m`)   |
| **Memory Request / Limit** | Memory allocation (e.g., `512Mi`, `4Gi`) |

#### Storage

Enable this when persistent storage is required.

| Setting           | Description                                     |
| ----------------- | ----------------------------------------------- |
| **Storage Size**  | Capacity (e.g., `10Gi`)                         |
| **Mount Path**    | Mount path inside the container (absolute path) |
| **Storage Class** | Kubernetes storage class                        |
| **Access Mode**   | Access mode                                     |

#### Status

| Setting     | Description                |
| ----------- | -------------------------- |
| **Enabled** | Toggle the agent on or off |

#### Environment Variables

You can set custom environment variables. The following reserved variables are injected automatically by the platform and do not need to be configured manually (registering a variable with the same name results in an error).

**Always injected**

- `EXECUTION_ID`
- `CONVERSATION_ID`
- `USER_ID`
- `AGENT_ID`

**Injected conditionally**

- `USER_ORGANIZATION_ID`
- `USER_ORGANIZATION_LABEL`
- `USER_JOB_ROLE`
- `USER_JOB_LABEL`
- `USER_BIO`
- `USER_LANGUAGE`

Custom environment variables can be marked as secret (with masked display) and as required.

#### Additional Settings (JSON)

Specify agent-specific extra parameters in JSON format.

#### ACR Secret Management

When using a private Azure Container Registry, you can have an authentication secret created automatically from a username and password.

### Guardrail Settings

Configure content safety and personal information protection for AI outputs.

![Guardrail settings screen](https://developers.fd.agenticstar.tm.softbank.jp/en/assets/images/admin-guardrails-settings-4605af72aa7eb04bbf7d597cd31e818b.png)

#### Content Safety

**Prompt Shield Detection**

Detects and blocks jailbreak attacks. Can be turned on or off.

**Moderation Detection**

Sets the detection level for harmful content.

| Level | Description                                     |
| ----- | ----------------------------------------------- |
| **0** | Disabled                                        |
| **2** | Recommended (detect moderately harmful content) |
| **4** | Lenient (detect only severe content)            |
| **6** | Minimum (detect only extremely severe content)  |

Detection categories: violence, sexual content, hate speech, self-harm.

#### PII Masking

Automatically detects and masks personally identifiable information (PII). Up to 189 categories are supported (the count varies by cloud provider).

Examples of detection targets:

- Identifying info (phone numbers, email addresses, My Number, etc.)
- Financial info (credit card numbers, account numbers, etc.)
- Medical info (insurance numbers, medical records, etc.)
- Location info (addresses, GPS coordinates, etc.)
- Credentials (passwords, API keys, tokens, etc.)

##### Backend per Cloud Provider

| Provider  | Backend                                         | Supported Languages               |
| --------- | ----------------------------------------------- | --------------------------------- |
| **Azure** | Azure AI Language - PII Detection               | Multilingual (including Japanese) |
| **AWS**   | Bedrock Guardrails `sensitiveInformationPolicy` | Multilingual (including Japanese) |
| **GCP**   | Cloud DLP                                       | Multilingual (including Japanese) |

On AWS, we recommend handling ContentSafety (content moderation / prompt shield) and PII detection in **a single Bedrock Guardrail**. Both are evaluated with one `apply_guardrail` API call, so the only IAM permission required is `bedrock:ApplyGuardrail`.

### Blocked URLs

Manage URLs that agents are forbidden to access.

#### Restriction Granularity

| Feature                                 | Granularity | Description                                                                                                                                                                                                        |
| --------------------------------------- | ----------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
| **Base feature (shipped by default)**   | Domain      | Outbound traffic from the Pod is checked by ExtAuth Service (Envoy sidecar-based authorization). Because HTTPS hides the path inside the TLS tunnel, in practice this acts as a domain (+ port) level restriction. |
| **Extension (optional implementation)** | URL (path)  | If the agent itself uses the SDK's `ConfigAccess.get_banned_urls()` and inspects URL strings inside its tools, path-level restriction becomes possible.                                                            |

> **tip**
>
> Both features share the same "Blocked URLs" configuration (the `banned_urls` table), so registration in the admin console is unified. For how to implement the extension, see `ConfigAccess.get_banned_urls()` in the [SDK Reference](https://developers.fd.agenticstar.tm.softbank.jp/en/docs/marketplace/basic/develop/reference/sdk-ref.md).

## Master Data

### Organizations

Manage organization information.

### Job Types

Manage the job-type master.

### Announcements

Create and manage announcements shown to end users. You can set a title and body (Markdown), priority, and enabled / disabled state.

### Email Provider Settings

Configure the email provider used to send notification emails.

#### Basic Settings

Toggle the email feature on or off.

#### SMTP Settings

| Setting            | Description                   | Notes                               |
| ------------------ | ----------------------------- | ----------------------------------- |
| **Host**           | SMTP server hostname          | Required (e.g., `smtp.example.com`) |
| **Port**           | SMTP server port              | Required (1–65535, default: 587)    |
| **Encryption**     | Encryption for the connection | None / SSL / TLS (TLS recommended)  |
| **Authentication** | Authentication method         | None / LOGIN / PLAIN / CRAM-MD5     |
| **Username**       | SMTP authentication username  | Required                            |
| **Password**       | SMTP authentication password  | Required                            |
| **From Address**   | Sender email address          | Required                            |

## Log Management

### Audit Logs

Review the history of operations performed in the admin console — who changed what and when.

### LLM Audit Logs

Review the history of LLM usage. Token consumption and request content can be traced.

### Reports

Review user reports.

### Access Logs

Review access history to the application.

## System Management

### Notification Settings

Configure whether notification emails are sent to end users. Task-completion mail, follow-up mail, and Weekly mail can be toggled individually.

## Version Management

Check the platform's current version and upgrade to the latest available version. Versions must be upgraded one at a time, in order.
