GenAI Augmented Structured Content

Digital Transformation with
GenAI Augmented Structured Content

The biopharma industry operates in a highly regulated environment with constantly evolving guidelines. To navigate this landscape, leveraging advanced technologies is essential for streamlining content creation and ensuring compliance.

Generative AI (GenAI) is proving to be a transformative tool, revolutionizing content generation, regulatory information management, and submission processes. However, the effectiveness and accuracy of GenAI hinge on the quality and structure of the underlying content and data.

Maximizing GenAI Efficiency through Structured Content

GenAI has the potential to revolutionize regulatory content generation and authoring in the biopharma industry. However, its true value is realized only when it operates on high-quality, structured content. In biopharma, where precision and accuracy are critical, the absence of structured content can result in significant inaccuracies and require additional effort by authors to review and edit AI-generated content, impacting efficiency and regulatory compliance, and potentially jeopardizing patient safety.

Improving GenAI Outputs with Prompt Specificity

In practice, both high data quality and prompt specificity are crucial for unlocking the full potential of GenAI. Specific prompts guide AI models to generate precise, contextually relevant, and actionable insights, ensuring regulatory compliance. By prioritizing data quality and prompt specificity, organizations can drive better outcomes and create significant value.

The Role of Structured Content in Improving Prompt Specificity

Structured content offers a robust framework for configuring component-level prompts, ensuring segmentation, detailed context, precision, consistency, and compliance. By breaking information into distinct components, structured content enables the creation of detailed prompts for each segment.

The InteliNotion Solution: GenAI-Assisted Structured Authoring

InteliNotion seamlessly integrates embedded GenAI capabilities into our core Content Platform. Our solution provides intuitive prompt configurability and management directly within our structured models and related templates.

The following diagram illustrates the InteliNotion solution flow for
GenAI-assisted Structured Content Authoring:

Component Prompt Configurations

The InteliNotion solution for GenAI embodies our vision of empowering clients to configure, manage, and govern component-level prompts within our clients’ models.

The following screenshot showcases the initial configurability of component-level prompts within the InteliNotion Info Model:

The Prompt Library, shown in the screenshot below, supports prompt management and governance, and allows prompts to be reused across multiple models and templates:

GenAI-Assisted Authoring

Once the prompts have been configured into the Info model, when the author generates the document using the template and associated Info model, the platform will generate the document, execute the component-level AI prompts embedding any contextual information into the prompts, and auto-insert the generated content into the related components. Further refinements can then be performed by using the InteliNotion (IN) Content Companion App, which is built into the MS Word interface.

The following screenshot illustrates the IN Content Companion icon in the InteliNotion Word Ribbon interface:

When editing a document, the IN Content Companion offers Authors and Reviewers a comprehensive “Prompt View” feature, enabling them to:

View and edit prompts as needed.
Save revised prompts as new versions.
Pose questions related to document or component content, to further refine previously AI-generated content.

This feature empowers users to refine and customize prompts, ensuring AI-generated content meets their specific needs.

The IN Content Companion App in the MS Word Task Pane:

Authors are provided with right-click context menus from within Word to request AI Services:

The following are some examples of component-based GenAI use cases:
Writing a clinical protocol Study Design component using publicly available information or proprietary information from previously written protocols.
Writing a 2-paragraph summary of data contained in an in-text demographics table in a clinical study report results section.
Writing a protocol synopsis component by summarizing the content in one or more source components from the body of the protocol.
Summarizing the content from one or more protocol components into a methodology/front end component of a clinical study report, if the content is not suitable for as is reuse from protocol to clinical study report.
Changing from present to past tense of any component reused from the protocol into a clinical study report methodology section.
Enhancing AI Capabilities through LLM and RAG

The core InteliNotion platform features a fully integrated cutting-edge GenAI capability, combining a curated large language model (LLM) with advanced Retrieval Augmented Generation (RAG) leveraging both public and client-specific data to unlock the full potential of GenAI.

Model Flexibility and Adaptability

Our GenAI delivery model keeps clients ahead of the curve with:

Adaptive LLM updates and reconfiguration through API based integration
Advanced RAG modeling for efficient content structuring and training
Flexible APIs for tailored integration with our customers’ own models and knowledge sources

Our collaborative approach ensures a deep understanding of client needs, delivering precise and effective AI solutions.