Reference for Generative AI Controller
Summarize
Summary of Reference for Generative AI Controller
The Generative AI Controller enables users to leverage artificial intelligence to enhance content generation, summarization, sentiment analysis, and brainstorming capabilities within the ServiceNow platform. This reference provides key information about flow actions, tables, and properties associated with the Generative AI Controller.
Show less
Key Features
- Generate Content: Quickly create bodies of text, such as knowledge base articles, from user interactions.
- Summarize: Condense large text bodies or complex exchanges for smoother information transfer, particularly during agent handoffs.
- Sentiment Analysis: Assess user sentiment from input text to improve overall customer experience.
- Generic Prompt: Utilize generative AI for brainstorming and generating ideas on various topics.
Tables Installed
- OneExtend Capability: Contains capabilities including Summarize, Record Summarization, Generate Content, and Generic Prompt.
- OneExtend Capability Definition: Configures input and output variables for Flow Designer subflows.
- OneExtend Builder Config: Links capabilities and providers to builder components in Flow Designer and Virtual Agent Designer.
- OneExtend Usage: Tracks each usage of a capability within Flow Designer or Virtual Agent Designer topics.
Properties
- Default Provider: Specifies the default AI provider when no default is defined.
- AI Search Failure Message: Custom message when AI fails to provide an answer.
- Log Prompt: Determines if generative AI API calls are logged.
- Moderation Message: Message displayed if content is flagged by moderation tools.
- Token Buffer: Checks the token count before executing a OneExtend capability.
These properties enable fine-tuning of the Generative AI Controller's functionality, ensuring it meets specific organizational needs while adhering to data and usage policies set by various AI providers.
Reference topics provide information about Generative AI Controller flow actions, tables, and properties.
Flow actions
Action |
Description |
|---|---|
Generate Content |
Generate content with an artificial intelligence model to create bodies of text quickly, such as generating knowledge base articles from interactions, cases, or incidents. |
Summarize |
Summarize large bodies of text or complicated exchanges to make the transfer of information easier, such as during handoffs between virtual and live agents. |
Sentiment Analysis |
Analyze user sentiment based on text that has been input in interactions and forms to improve customer experiences. |
Generic Prompt |
Use Generative AI to generate ideas and brainstorm on any topic, such as ideas for increasing engagement. |
Tables installed
| Name | Table | Description |
|---|---|---|
| OneExtend Capability | sys_one_extend_capability | Generative AI Controller capabilities that include Summarize, Record Summarization, Generate Content, and Generic Prompt. |
| OneExtend Capability Definition | sys_one_extend_capability_definition | Attribute configuration for input and output variables for Flow Designer subflows. |
| OneExtend Capability Definition Attribute | sys_one_extend_definition_attribute | Input and output variables for Flow Designer subflows. Variable names can't be changed if the capability is active and used on the instance. You can check whether a capability is used by going to the OneExtend Usages table. |
| OneExtend Builder Config | sys_one_extend_builder_config | Determines which capability and provider is related to each builder component for Flow Designer and Virtual Agent Designer. |
| OneExtend Builder Capability | sys_one_extend_builder_capability | Definitions for a capacity and its provider for builder components. |
| OneExtend Usage | sys_one_extend_usage | Each usage of a capability in a Flow Designer or Virtual Agent Designer topic, as well as any scripts such as business rules or UI actions. |
Properties
| Property | Description |
|---|---|
| com.sn.generative.ai.provider | Default provider when capability definition has no default. Type: choice list No default value |
| com.sn.generative.ai.ais.message | Message that is displayed when AI Search fails to find an answer to a query. Type: string Default value: No answer found. |
| com.sn.generative.ai.log_prompt | Prompt that determines whether generative AI API calls are logged. Type: true | false Default value: true |
| com.sn.generative.ai.moderation.message | Message that is displayed if the OpenAI or Azure OpenAI moderation tools identify the content that goes against their terms of service. Type: string Default value: The response cannot be displayed as it’s deemed inappropriate by OpenAI. |
| com.glide.one.extend.token.buffer | Buffer that checks the request for the number of tokens before a OneExtend capability is executed. The maximum allowed request tokens are calculated based on the maximum tokens that are permitted by the AI provider's API minus
the response token and buffer value that is specified in this system property. Type: integer Default value: 250 |
External links
| Provider | Data policy | Usage policy |
|---|---|---|
| OpenAI | API data usage policies | Usage policies |
| Microsoft Azure OpenAI | Data, privacy, and security for Azure OpenAI Service | Code of conduct for Azure OpenAI Service |
| Google Cloud | Google Cloud Platform Terms of Service | Google Cloud Platform Terms of Service |
| Aleph Alpha | Data privacy | Terms and Conditions |