One AI Assistant Overview

Introduction

One AI Assistant is a core part of the One Model platform that gives users a faster, more intuitive way to explore, understand, and use workforce data. It supports multiple use cases, including creating charts, uncovering insights, navigating storyboards, performing research, and retrieving trusted answers–all through a flexible and intuitive interface.

Each user’s experience is shaped by configuration. Organizations decide which capabilities to enable, what data the Assistant can access, and how much functionality to provide for each user group. All interactions respect role-based data permissions.

This article provides a high-level overview of what the Assistant can do, how it works, and how to manage it.

Video Overview

One AI Assistant Capabilities

From guided answers to open-ended analysis, One AI Assistant offers streamlined ways to get value from your workforce data. Its four core capabilities each support a different way to access information, explore trends, or make decisions depending on the user’s question, skill level, and goals.

Answers

Answers is the most structured and governed way to deliver information through One AI Assistant. Admins configure specific questions, choose an existing visual to return, and organize content by topic. Users can browse all available questions, see questions by topic, or ask their own question and be matched to the closest configured entry.

Answers include four parts designed to help users quickly understand and trust what they’re seeing:

1. An AI generated written answer based on the chart and question designed to help users interpret the visual (can be permissioned separately)
2. A visualization (chart, table, value, etc.) so users can understand further
3. A link to a relevant storyboard for additional context and deeper exploration
4. A list of related questions users can ask next

This setup is ideal for users who don't have the time or context to verify accuracy on their own. It guarantees consistency—everyone sees the same answer, based on the same chart, with no need to fact-check or interpret.

Check out the user guide to learn more: One AI Assistant Answers

Visualizations

Visualizations let users create custom charts, tables, or values by describing what they want to see in the prompt bar. It’s a flexible way to explore data without needing to build visuals manually or understand the underlying model.

To support accuracy and consistency, the Assistant first checks for any configured Answers. If nothing matches, it interprets the prompt and builds a visual using the appropriate metrics, dimensions, filters, and time period. 

Users can view exactly how the visual was built in the query panel and make adjustments if needed. Even when the result isn't perfect, it provides a clear starting point for further refinement or deeper analysis.

Check out the user guide to learn more: One AI Assistant Visualizations

Analyze

Analyze enables users to ask natural language questions about any chart or table in the assistant and get clear, contextual responses that simplify data interpretation. Analyze is available for both Visualizations and Answers and is powered by a secure large language model (LLM). The LLM is provided with both the user’s request along with the data displayed in the chart or table, enabling responses that are intelligent and grounded in the data. Think of it as securely pasting your data into ChatGPT and asking questions about it.

Analyze is built directly into the Assistant for in-flow analysis. Because conversations are threaded, users can ask follow-up questions that retain the full context of the discussion. Responses may include rich formatting such as lists, icons, and tables. As with all One AI Assistant capabilities, Analyze is permission-based and secure. Chart data is sent to the OpenAI LLM when using Analyze, so organizations should confirm alignment with their corporate AI policies prior to enabling this feature.

Optional web search capability is also available for Analyze. Web search enhances Analyze with complete up-to-date information and sources cited with hyperlinks.

Check out the user guide to learn more: One AI Assistant Analyze

Chat

Chat is a conversational AI feature built directly into One AI Assistant. It enables natural, back-and-forth dialogue with the assistant, whether you’re looking up HR concepts or brainstorming ideas. For example, you might ask about SHRM-recognized predictors of voluntary separation, get a concise answer, and then follow up with clarifying questions — all while staying in the same thread.

Designed for ease of use, Chat requires no configuration. You simply switch to Chat mode and start asking questions. Responses can include formatting like lists, tables, and rich text that makes the information provided clear.

As with Analyze, web search capability is available for Chat as a permissioned setting. Web search magnifies the power of Chat with complete up-to-date information and sources cited with hyperlinks. Enabling web search also makes the One Model Help Center available to Chat as a tool for answering questions about the One Model platform. This capability can also be permissioned separately from full chat web access.

Check out the user guide to learn more: One AI Assistant Chat

Insights

Insights help users focus on what’s most important in a visualization without needing to export data or analyze it manually. Available as part of the Visualizations capability, insights are statistical observations that surface trends, comparisons, outliers, and other notable patterns automatically identified by One Model’s Insights Engine.

Each insight includes a Gen AI-generated recommendation to suggest what to analyze or consider next. Recommendations are permission-controlled and can be turned off. One AI Assistant also shows its work, allowing users to see how the insight was calculated and verify it if needed.

Check out the user guide to learn more: One AI Assistant Insights

Storyboard Navigation

Users can also ask the Assistant to find relevant storyboards by topic. It searches storyboard titles, descriptions, and page names to identify the best matches, then returns a list of direct links to the most relevant content.

This helps users find existing content without relying on search or manual navigation.

Check out the user guide to learn more: One AI Assistant Storyboard Navigation

How One AI Assistant Works

One AI Assistant combines context identification, configuration, vector search, and generative AI to deliver fast, relevant results based on your organization’s own data and content.

Configured Answers, metrics, dimensions, and Storyboard are transformed into embeddings, which are numeric representations of meaning. The system stores those embeddings in a secure vector database, allowing the Assistant to match user prompts to the right concepts, even if different terms or language are used.

When a user submits a prompt, One AI Assistant attempts to intelligently route it to the appropriate capability. This intelligent routing can be overridden by manually selecting a capability. Each capability then uses generative AI in various ways to generate the desired result. This might include using the embeddings to identify relevant matches and/or using generative AI to interpret the question, generate an answer, or provide a recommendation. The various capabilities are described later in this document in detail.

Mode Selection

One AI Assistant is designed to provide a seamless experience in AI Mode, where it automatically decides whether to return an Answer, a Visualization, or a Storyboard based on your prompt. This allows you to ask questions naturally without worrying about which feature to use.

Because results depend on your organization’s configuration and your own data permissions, AI Mode may not always route you exactly where you expect. In those cases, you can use Mode Selection to take control. Selecting a mode explicitly ensures the Assistant responds in the way you want, whether that’s generating a chart, retrieving a storyboard, or providing a curated answer.

Available modes are:

• AI Mode – The Assistant chooses the most appropriate feature based on your prompt

• Visualizations – Creates a chart, table, or value from your description

• Storyboards – Retrieves the most relevant storyboards based on your topic

• Answers – Returns a curated, preconfigured answer to a key question

• Analyze - Ask natural language questions about any chart or table

• Chat - Chat with an LLM right within the assistant

This balance of automation and control lets you work fluidly: rely on AI Mode for a unified experience, or switch modes when you want more precision.

Configuration and Permissioning

Admins can tailor One AI Assistant to their organization using a range of configuration options. These include setting general behavior, defining example prompts, configuring Answers, and determining which metrics, dimensions, and Storyboards the Assistant can access. The Assistant will not return results until this configuration is complete. All results returned by the Assistant respect each user’s role-based data access permissions.

Each of the Assistant’s core capabilities can be individually permissioned through One Model’s Application Access Roles. Specific features powered by generative AI, such as Insight recommendations and the text-based portion of Answers, can also be permissioned separately.

To learn more, review: One AI Assistant Configuration Guide

Use of Generative AI

One AI Assistant uses OpenAI large language models (LLMs) through One Model’s enterprise-grade OpenAI account. Your data is never used to train OpenAI models. The user’s prompt and associated embeddings are sent to OpenAI, and they may be stored for up to 30 days to monitor for abuse, in line with OpenAI’s API policy.

Generative AI supports several parts of the Assistant’s workflow. Each of these features can be permissioned separately by role, ensuring that only authorized users can access them:

• Context identification
• Embedding creation
• Recognition of metrics, dimensions, and time selections in prompts
• Generation of written Answers
• Ranking of Insights
• Generation of Insight recommendations

To learn more, review: One AI Assistant Generative AI Usage

Conclusion

One AI Assistant brings together structured answers, custom analysis, insights, and navigation to make workforce data easier to use and act on. Whether you're exploring trends, supporting decisions, or enabling others, the Assistant adapts to a range of users and use cases—always grounded in your organization’s configuration and data permissions.