1. NetSuite Basics
  2. Artificial Intelligence (AI) in NetSuite
  3. What's New in NetSuite AI

What's New in NetSuite AI

NetSuite continues to add and enhance features that use artificial intelligence (AI) and machine learning (ML). Click the following links to see what's new with NetSuite AI and ML features since the last major release:

NetSuite AI Connector Service

You can connect your NetSuite account to an external AI client using the NetSuite AI Connector Service. You can use this integration to:

  • Invoke the tools from the AI client using natural language prompts

  • Build AI tools with the custom tool script type

  • Deploy these tools to your NetSuite account using SuiteCloud projects and SDF

To explore what’s possible with the NetSuite AI Connector Service and custom tools, install the MCP Sample Tools SuiteApp from the SuiteApp Marketplace.

For more information, see:

Text Enhance Translations

Text Enhance Translations is a new capability of Text Enhance that lets you translate content into supported languages. This feature helps you collaborate across multilingual global teams and communicate more clearly with customers.

With Text Enhance Translations, you can translate text into any supported language. The Translate to action is available in both the full and partial Text Enhance menus, so you can translate all the text in a field or only the part you select. Text Enhance Translations automatically detects the original language for you. For more information, see Text Enhance.

Text Enhance Translations is available by default for all accounts with Text Enhance. If you're a user with an Administrator role, you can manage settings, such as translation target languages. For more information, see Manage Text Enhance Translations Preferences.

Text Enhance Translations was recently upgraded to use generative AI through NetSuite. Generative AI provides context awareness when translating content. This change also lets users with a NetSuite Administrator role use Prompt Studio to customize translation prompts and Text Enhance actions.

N/machineTranslation

A new SuiteScript 2.1 module, N/machineTranslation, was added. This module lets you translate documents into other languages using SuiteScript. You can send a set of documents, and the module will request translations from the Oracle Cloud Infrastructure (OCI) Language service. After it returns the translated documents, you can use them in your scripts. See N/machineTranslation Module for more information or refer to Language in the Oracle Cloud Infrastructure Documentation.

Generative AI Availability Updates

Text Enhance, SuiteScript Generative AI APIs, and Prompt Studio are now available in more locations:

  • Brazil

  • Hong Kong

  • Mexico

  • Philippines

  • Singapore

Text Enhance is now available for more languages. If your account has Text Enhance, and your user preferences are set to one of these languages, you'll now see the Enhance Text button next to supported fields:

  • Portuguese (Brazilian)

  • Spanish

  • Spanish (Latin America)

See Generative AI Availability in NetSuite for more information.

SuiteScript Generative AI APIs

The N/llm module has the following new capabilities. See N/llm Module for more information.

  • Retrieval-augmented generation (RAG) support: You can give source documents to the large language model (LLM) when calling llm.generateText(options). The LLM uses information from the source documents to augment its response. The LLM also returns citations that identify which source documents it used. For an example of how to implement a RAG use case using the N/llm module, see Provide Source Documents When Calling the LLM.

  • Embedding support: The N/llm module's embed(options) method converts text to vector embeddings. Your SuiteScript applications can use vector embeddings for use cases such as semantic searches, recommender systems, text classification, or text clustering. For more information, see llm.embed(options) or refer to About the Embedding Models in Generative AI in the Oracle Cloud Infrastructure Documentation.

    Note:

    Embedding methods have their own monthly free usage quota, separate from generate methods. If you use both in a month, you'll see two rows for the month, labeled by usage type. For more information, see View SuiteScript AI Usage Limit and Usage.

  • Streaming support: With the N/llm module's generateTextStreamed(options) method or evaluatePromptStreamed(options) method, your code gets content as the LLM generates it, instead of waiting to receive it all at the same time. For more information, see llm.generateTextStreamed(options) and llm.evaluatePromptStreamed(options).

  • New aliases for N/llm methods: You can use the following aliases in your N/llm module code instead of the method names:

    • llm.chat(options) is an alias for llm.generateText(options).

    • llm.executePrompt(options) is an alias for llm.evaluatePrompt(options).

    • llm.chatStreamed(options) is an alias for llm.generateTextStreamed(options)

    • llm.executePromptStreamed(options) is an alias for llm.evaluatePromptStreamed(options).

    Promise versions are also available for these methods.

    When aliases are available for methods, you'll see them listed in the main table of the method's help topic. For an example, see llm.generateTextStreamed(options).

  • Safety modes: This feature lets you specify a safety mode when calling llm.generateText(options) or llm.generateTextStreamed(options), which is designed to help filter and moderate content generated by the LLM. These modes focus on filtering out content that could be considered hateful, abusive, threatening, or otherwise harmful. The default mode is STRICT mode, which aims to avoid sensitive topics entirely. You can also use CONTEXTUAL mode (which offers a less restrictive approach while still rejecting harmful or illegal suggestions) and OFF mode (which removes restrictions on generated content and should be used with caution). Safety modes are available only for Cohere models. For more information, see llm.SafetyMode.

  • JSON response formatting: This feature lets you specify a JSON schema when calling llm.generateText(options), and the response will contain keys and values as defined in your schema that are populated by the generated content. You can then parse the response as JSON content. Response formatting is available only for Cohere models. For more information, see the options.responseFormat parameter of llm.generateText(options).

  • Usage object: This object is included in the llm.Response object returned from llm.generateText(options) (using the Response.usage property) and represents the number of tokens used during a request to the LLM. This object is available only for Cohere models. For more information, see llm.Usage.

Text Enhance

  • You can use Text Enhance to generate job posting details on the Job Requisition page. The Generate action is in the Enhance Text menu for the Posting Details field on the Job Requisition page. For more information, see Job Requisitions.

  • There's a new Text Enhance preference on the AI Preferences page. The Enable Text Enhance for External Roles setting lets you control whether users with external roles can use Text Enhance. To enhance security, this setting is disabled by default. Only users with internal roles can use Text Enhance unless you enable the setting. When you enable the setting, users with external roles can use Text Enhance. Standard external roles in NetSuite include Customer Center, Employee Center, NetSuite Support Center, NetSuite Support Center (Basic), Online Form User, Partner Center, Shopper, and Vendor Center. For more information, see Manage Text Enhance Preferences.

Related Topics

General Notices