# Feature Flags

The **Settings > Configuration > Feature Flags** configurations control optional and experimental platform capabilities for your tenant. These are tenant-level settings that apply to all bots you create in this Aisera tenant.

## Channels

### Enable Search for Email Channel

| **Type**    | Checkbox |
| ----------- | -------- |
| **Default** | Disabled |

Controls whether Aisera performs a knowledge base search as a fallback when an inbound email does not match an intent or skill. When enabled, Aisera searches the knowledge base using the email content and replies with the closest matching article. When disabled, unmatched emails are marked unresolved without a search attempt. Enable this when your knowledge base is broad enough to cover unstructured email inquiries and you want Aisera to attempt a best-effort answer before marking a request unresolved.

See also: [create ticket to SOR on KB Serving over Email](/aisera-platform/tenant-setup/aisera-platform-configuration/tenant-configuration-settings/conversation.md#create-ticket-to-sor-on-kb-serving-over-email)

### Enable AI Chat Channel

| **Type**    | Checkbox |
| ----------- | -------- |
| **Default** | Disabled |

Controls whether AI Chat appears as a channel type option when creating channels manually. When disabled, the option is hidden and no new AI Chat channels can be created.

### Disable gRPC for Channels

| **Type**    | Checkbox |
| ----------- | -------- |
| **Default** | Disabled |

Forces channel communication to use REST instead of Google Remote Procedure Call (gRPC). By default, all channels communicate with the conversation service over gRPC.

### Disable User based queuing for Channels message delivery

| **Type**    | Checkbox |
| ----------- | -------- |
| **Default** | Disabled |

No description available.

## Workflow and Hyperflow

### Enable Skill Preamble

| **Type**    | Checkbox |
| ----------- | -------- |
| **Default** | Disabled |

Controls whether Aisera displays an introductory message at the start of a skill before collecting slot inputs. When enabled, Aisera reads from the **Messages** field in the skill's workflow definition, selects the best-matching variant based on which slot values are already known, and displays it once per skill session.

To configure preamble messages:

1. Open **AI Automation** and select **AI Workflow Studio**.
2. Open the workflow you want to configure.
3. Click the pencil icon in the top right corner of the **Workflow Details** page.
4. Navigate to **General** > **Messages**.
5. Add the introductory message you want displayed when the skill begins.

For example:

{% code overflow="wrap" %}

```
I can help you reset your password. I'll need to ask a few quick questions to verify your identity first.
```

{% endcode %}

{% hint style="warning" %}
The **Messages** field is also used for skill recommendations and skill disambiguation. The disambiguation path reads from this field regardless of whether Enable Skill Preamble is enabled. Write messages that work appropriately in all three contexts. 
{% endhint %}

### Enable Hyperflow V1

| **Type**    | Checkbox |
| ----------- | -------- |
| **Default** | Enabled  |

Controls which processing path Hyperflow uses for non-streaming LLM requests. Disable this only if directed to by Aisera Support.

{% hint style="info" %}
This flag is scheduled for removal in a future release.
{% endhint %}

### Enable Streaming Hyperflow V1

| **Type**    | Checkbox |
| ----------- | -------- |
| **Default** | Enabled  |

Controls which processing path Hyperflow uses for streaming LLM requests. This is the streaming counterpart to Enable Hyperflow V1. Both flags should be set to the same value. Disable this only if directed to by Aisera Support.

{% hint style="info" %}
This flag is scheduled for removal in a future release.
{% endhint %}

### Enable Streaming Flow Response

| **Type**    | Checkbox |
| ----------- | -------- |
| **Default** | Disabled |

Controls whether workflow execution sends responses to the user incrementally as each node completes, rather than waiting for the entire workflow to finish. Enable this for longer workflows where intermediate outputs are meaningful, such as flows that produce status updates across multiple steps. This setting applies to standard workflows only, requires a streaming-capable channel, and has no effect on Hyperflow.

See also:[ Enable streaming for Hyperflow and its executed workflow response outputs](#enable-streaming-for-hyperflow-and-its-executed-workflow-response-outputs).

### Enable streaming for Hyperflow and its executed workflow response outputs.

| **Type**    | Checkbox |
| ----------- | -------- |
| **Default** | Disabled |

Controls whether Hyperflow delivers responses progressively as they are generated, including intermediate status updates and output from any sub-workflows it invokes. When disabled, all output is held until execution completes and intermediate status messages are silently dropped. Enable this for complex Hyperflows where showing users progress while they wait is beneficial. Requires a streaming-capable channel.

See also: [Enable Streaming Flow Response](#enable-streaming-flow-response)

## AI and knowledge

### Enable Fuzzy Intent Match

| **Type**    | Checkbox |
| ----------- | -------- |
| **Default** | Disabled |

When enabled, Aisera presents a "Did you mean?" confirmation prompt when the intent model identifies a probable but uncertain match for a user's request, rather than immediately falling back to exception handling. If the user confirms, the matched skill executes. If the user declines, the bot falls back to its configured exception handling response. Enable this when users frequently phrase requests in ways the bot doesn't recognize but close matches exist, reducing dead-end conversations.

{% hint style="info" %}
This setting only triggers a prompt when the intent model returns a fuzzy match. Enabling the flag has no effect if the model is not producing fuzzy match data for ambiguous inputs in your deployment. 
{% endhint %}

### Enable Knowledge To Flow Creation with LLM

| **Type**    | Checkbox |
| ----------- | -------- |
| **Default** | Disabled |

Controls whether converting a knowledge base article into a bot workflow uses an LLM or a rule-based structural parser. When disabled, the system mechanically maps the article's headings and sections into flow nodes. When enabled, the LLM interprets the article's meaning to produce a more contextually structured flow. Enable this when you want the platform to generate the workflow for you based on the article's content. Aisera always creates generated flows as drafts. Review them before publishing.

{% hint style="warning" %}
If LLM generation fails for any article, the entire flow creation fails with no fallback to rule-based generation. If a draft flow already exists for the selected articles, Aisera blocks flow creation until the existing draft is resolved.
{% endhint %}

### Enable ConvAI RAG Tenant Level Index

| **Type**    | Checkbox |
| ----------- | -------- |
| **Default** | Disabled |

No description available.

## Analytics and testing

### Enable Analytics V2 (Beta)

| **Type**    | Checkbox |
| ----------- | -------- |
| **Default** | Disabled |

Routes analytics queries to a dedicated analytics database instead of the primary database. The analytics database must be provisioned by Aisera before this setting has any effect. Contact Aisera Support if you are interested in enabling Analytics V2 for your tenant.

### Enable Event Studio (Beta)

| **Type**    | Checkbox |
| ----------- | -------- |
| **Default** | Disabled |

Makes the **Event Studio** and **Data Types** sections visible in the admin navigation. Event Studio lets you create event triggers that automatically execute bot workflows in response to external webhooks, scheduled connector events, or internal platform events. Data Types provides a schema editor for defining custom data structures used to map event payload fields to workflow inputs. Enable this when you need to automate workflows based on events from connected systems.

### Enable Test Suite

| **Type**    | Checkbox |
| ----------- | -------- |
| **Default** | Disabled |

Makes the **Test Suites** section visible under **AI Workbench** for app admins. Test suites let you create and run automated conversational validation tests against a bot, with results displayed as a match rate percentage and execution history tracked over time. Enable this when your team needs a repeatable way to validate bot behavior, such as before deploying changes, after retraining, or during ongoing quality monitoring.

{% hint style="info" %}
Both this flag and the app role are required to access Test Suites. Enabling the flag alone does not grant access to standard users.
{% endhint %}

## Session and user management

### Enable Session Manager V2

| **Type**    | Checkbox |
| ----------- | -------- |
| **Default** | Disabled |

Switches conversation session storage from a single shared object to individual entries, with each conversation stored separately alongside its own session variables. This reduces overhead when accessing or updating individual sessions and enables automatic auditing of sessions that started but never cleanly terminated, such as those interrupted by a channel disconnect.

### User Preference

| **Type**    | Checkbox |
| ----------- | -------- |
| **Default** | Disabled |

When enabled, Aisera tracks each user's interactions, including feedback, knowledge base article clicks, and action selections, and uses that history to personalize future responses. When multiple responses or intents are equally valid for a query, the bot prioritizes what the user has previously found helpful and automatically selects intents they have engaged with before, skipping disambiguation. In multilingual deployments, the bot also tracks each user's preferred language and prompts them to confirm or update it when a different language is detected. Enable this in deployments with diverse content options where personalizing responses for returning users is a priority.

### Enable Tenant level Permission and override access attribute permission for Bot

| **Type**    | Checkbox |
| ----------- | -------- |
| **Default** | Disabled |

No description available.

## Integrations

### Automation Anywhere Product Integration

| **Type**    | Checkbox |
| ----------- | -------- |
| **Default** | Disabled |

Enables communication between the Aisera platform and Automation Anywhere. Enable this if your organization uses both products and needs them to interact.

## Deprecated configurations

### Enable Advanced SMS Channel

| **Type**    | Checkbox |
| ----------- | -------- |
| **Default** | Disabled |

This configuration is deprecated and has no effect.

### Enable Next Gen

| **Type**    | Checkbox |
| ----------- | -------- |
| **Default** | Disabled |

This configuration is deprecated and has no effect.


---

# Agent Instructions: Querying This Documentation

If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://docs.aisera.com/aisera-platform/tenant-setup/aisera-platform-configuration/tenant-configuration-settings/feature-flags.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.