In a recent blog, “Top Ways to Get Your Content and Data Ready for AI,” Sara Mae O’Brien-Scott and Zach Wahl gave an approach for ensuring your organization is ready to undertake an AI Initiative. While the previous blog provided a broad view of AI-readiness for all types of Knowledge Assets collectively, this blog will leverage the same approach, zeroing in on actionable steps to ensure your content is ready for AI. Content, also known as unstructured information, is pervasive in every organization. In fact, for many organizations it comprises 80% to 90% of the total information held within the organization. Within that corpus of content, there is a massive amount of value, but there also tends to be chaos. We’ve found that most organizations should only be actively maintaining 15-20% of their unstructured information, with the rest being duplicate, near-duplicate, outdated, or completely incorrect. Without taking steps to clean it up, contextualize it, and ensure it is properly accessible to the right people, your AI initiatives will flounder. The steps we detail below will enable you to implement Enterprise AI at your organization, minimizing the pitfalls and struggles many organizations have encountered while trying to implement AI.

1) Understand What You Mean by “Content” (Knowledge Asset Definition) 

In a previous blog, we discussed the many types of knowledge assets organizations possess, how they can be connected, and the collective value they offer. Identifying content, or unstructured information, as one of the types of knowledge assets to be included in your organization’s AI solutions will be a foregone conclusion for most. However, that alone is insufficient to manage scope and understand what needs to be done to ensure your content is AI-ready. There are many types of content, held in varied repositories, with much likely sprawling on existing file drives and old document management systems. 

Before embarking on an AI initiative, it is essential to focus on the content that addresses your highest priority use cases and will yield the greatest value, recognizing that more layers can be added iteratively over time. To maximize AI effectiveness, it is critical to ensure the content feeding AI models aligns with real user needs and AI use cases. Misaligned content can lead to hallucinations, inaccurate responses, or poor user experiences. The following actions help define content and prepare it for AI:

• Identify the types of content that are critical for priority AI use cases.
• Work with Content Governance Groups to identify content owners for future inclusion in AI testing. 
• Map end-to-end user journeys to determine where AI interacts with users and the content touchpoints that need to be referenced by AI applications.
• Inventory priority content across enterprise-wide source systems, breaking knowledge asset silos and system silos.
• Flag where different assets serve the same intent to flag potential overlap or duplication, helping AI applications ingest only relevant content and minimize noise during AI model training.

What content means can vary significantly across organizations. For example, in a manufacturing company, content can take the form of operational procedures and inventory reports, while in a healthcare organization, it can include clinical case documentation and electronic health records. Understanding what content truly represents in an organization and identifying where it resides, often across siloed repositories, are the first steps toward enabling AI solutions to deliver complete and context-rich information to end users.

2) Ensure Quality (Content Cleanup)

Your AI Model is only as good as what’s going into it. ‘Garbage in, garbage out’, ‘steady foundation’, ‘steady house’, there are any number of ways to describe that if the content going into an AI model lacks quality, the outputs will too. Strong AI starts with strong content. Below, we have detailed both manual and automated actions that can be taken to improve the quality of your content, thereby improving your AI outcomes. 

Content Quality

Content created without regard for quality is common in the everyday workflow. While this content might serve business-as-usual processes, it can be detrimental to AI initiatives. Therefore, it’s crucial to address content quality issues within your repositories. Steps you can take to improve content quality and accelerate content AI readiness include:

• Automate content cleanup processes by leveraging a combination of human-led and system-driven approaches, such as auto-tagging content for update, archival, or removal.
• Scan and index content using automated processes to detect potential duplication by comparing titles, file size, metadata, and semantic similarity.
• Apply similarity analysis to define business rules for deleting, archiving or modifying duplicate or near-duplicate content.
• Flag content that has low-use or no-use, using analytics.
• Combine analytics and content age to determine a retention cut-off (such as removing any content older than 2 years).
• Leverage semantic tools like Named Entity Recognition (NER) and Natural Language Processing (NLP) to apply expert knowledge and determine the accuracy of content.
• Use NLP to detect overly complex sentence structure and enterprise specific jargon that may reduce clarity or discoverability.

Content Restructuring

In the blog, “Improve Enterprise AI with Semantic Content Management” we note that content in an organization exists on a continuum of structure depending on many factors. The same is true for the amount of content restructuring that may or may not need to happen to enable your AI use case. We recently saw with a client that introducing even just basic structure to a document improved AI outcomes by almost 200%. However, this step requires clear goals and prioritization. Oftentimes this part of ensuring your content is AI-ready happens iteratively as the model is applied and you can determine what level of restructuring needs to occur to best improve AI outcomes. Restructuring content to prepare it for AI involves activities such as:

• Apply tags, such as heading structures, to unstructured content to improve AI outcomes and enhance the end-user experience.
• Use an AI-assisted check to validate that heading structures and tags are being used appropriately and are machine readable, so that content can be ingested smoothly by AI systems.
• Simplify and restructure content that has been identified as overly complex and could result in hallucinations or unsatisfactory responses generated by the AI model.
• Focus on reformatting longer, text-heavy content to achieve a more linear, time-based, or topic-based flow and improve AI effectiveness. 
• Develop repeatable structures that can be applied automatically to content during creation or retroactively to provide AI with relevant content in a consumable format. 

In brief, cleaning up and restructuring content assets improves machine readability of content and therefore allows the AI model to generate stronger and more accurate outputs. To prioritize assets that need cleanup and restructuring, focus on activities and resources that will yield the highest return on investment for your AI solution. However, it is important to recognize that this may vary significantly across organizations, industries, and AI use cases. For example, an organization with a truly cross-functional use case, such as enterprise search, may prioritize deduplication of content to ensure information from different business areas doesn’t conflict when providing AI-generated responses. On the other hand, an organization with a more function-specific use case, such as streamlining legal contract review, may prioritize more hands-on content restructuring to improve AI comprehension.

3) Fill Gaps (Tacit Knowledge Capture)

Even with high-quality content, knowledge gaps that exist in your full enterprise ecosystem can cause AI errors and introduce the risk of unreliable outcomes. Considering your AI use case, the questions you want to answer, the discovery you’ve completed in previous steps, and the actions detailed below you can start to identify and fill gaps that may exist. 

Content Coverage 

Even with the best content strategy, it is not uncommon for different types of content to “fall through the cracks” and be unavailable or inaccessible for any number of reasons. Many organizations “don’t know what they don’t know”, so it can be difficult to begin this process. However, it is crucial to be aware of these content gaps, particularly when using LLMs to avoid hallucinations. Actions you may take to ensure content coverage and accelerate your journey toward content AI readiness include: 

• Leverage systems analytics to assess user search behavior and uncover content gaps. This may include unused content areas of a repository, abandoned search queries, or searches that returned no results. 
• Identify content gaps by using taxonomy analytics to identify missing categories or underrepresented terms and as a result, determine what content should be included.
• Leverage SMEs and other end users during AI testing to evaluate AI-generated responses and identify areas where content may be missing. 
• Use AI governance to ensure the model is transparent and can communicate with the user when it is not able to find a satisfactory answer.

Fill the Gap

Once missing content has been identified from information sources feeding the AI model, the real challenge is to fill in those gaps to prevent “hallucinations” and avoid user frustration that may be generated by incomplete or inaccurate answers. This may include creating new assets, locating assets, or other techniques identified which together can move the organization from AI to Knowledge Intelligence. Steps you may take to remediate the gaps and help your organization’s content be AI ready include:

• Use link detection to uncover relationships across the content, identify knowledge that may exist elsewhere, and increase the likelihood of surfacing the right content. This can also inform later semantic tagging activities.
• Identify, by analyzing content repositories, sources where content identified as “missing” could possibly exist.
• Apply content transformation practices to “missing” content identified during the content repository analysis to ensure machine readability.
• Conduct knowledge capture and transfer activities such as SME interviews, communities of practice, and collaborative tools to document tacit knowledge in the form of guides, processes, or playbooks. 
• Institutionalize content that exists in private spaces that aren’t currently included in the repositories accessed by AI.
• Create draft content using generative AI, making sure to include a human-in-the-loop step for accuracy. 
• Acquire external content when gaps aren’t organization specific. Consider purchasing or licensing third-party content, such as research reports, marketing intelligence, and stock images.

By evaluating the content coverage for a particular use case, you can start to predict how well (or poorly) your AI model may perform. When critical content mostly exists in people’s heads, rather than in documented, accessible format, the organization is exposed to significant risk. For example, an organization deploying a customer-facing AI chatbot to help with case deflection in customer service centers, gaps in content can lead to potentially false or misleading responses. If the chatbot tries to answer questions it wasn’t trained for, it could result in out-of-policy exceptions, financial loss, decrease in customer trust, or lower retention due to inaccurate, outdated, or non-existent information. This example highlights why it is so important to identify and fill knowledge gaps to ensure your content is ready for AI. 

4) Add Structure and Context (Semantic Components)

Once you have identified the relevant content for an AI solution, ensured its quality for AI, and addressed major content gaps for your AI use cases, the next step in getting content ready for AI involves adding structure and context to content by leveraging semantic components. Taxonomy and metadata models provide the foundational structure needed to categorize unstructured content and provide meaningful context. Business glossaries ensure alignment by defining terms for shared understanding, while ontology models provide contextual connections needed for AI systems to process content. The semantic maturity of all of these models is critical to achieve successful AI applications. 

Semantic Maturity of Taxonomy and Business Glossaries

Some organizations struggle with the state of their taxonomies when starting AI-driven projects. Organizations must actively design and manage taxonomies and business glossaries to properly support AI-driven applications and use cases. This is not only essential for short-term implementation of the AI solution, but most importantly for long-term success. Standardization and centralization of these models help balance organization-wide needs and domain-specific needs. Properly structured and annotated taxonomies are instrumental in preparing content for AI. Taking the following actions will ensure that you have the Semantic Maturity of Taxonomies and Business Glossaries needed to achieve AI ready content:

• Balance taxonomies across business areas to ensure organization-wide standardization, enabling smooth implementation of AI use cases and seamless integration of AI applications. 
• Design hierarchical taxonomy structures with the depth and breadth needed to support AI use cases.
• Refine concepts and alternative terms (synonyms and acronyms) in the taxonomy to more adequately describe and apply to priority AI content.
• Align taxonomies with usability standards, such as ANSI/NISO Z39.19, and interoperability/machine readability standards, such as SKOS, so that taxonomies are both human and machine readable.
• Incorporate definitions and usage notes from an organizational business glossary into the taxonomy to enrich meaning and improve semantic clarity.
• Store and manage taxonomies in a centralized Taxonomy Management System (TMS) to support scalable AI readiness.

Semantic Maturity of Metadata 

Before content can effectively support AI-driven applications, organizations must also establish metadata practices to ensure that content has been sufficiently described and annotated. This involves not only establishing shared or enterprise-wide coordinated metadata models, but more importantly, applying complete and consistent metadata to that content. The following actions will ensure that the Semantic Maturity of your Metadata model meets the standards required for content to be AI ready:

• Structure metadata models to meet the requirements of AI use cases, helping derive meaningful insights from tagged content.
• Design metadata models that accurately represent different knowledge asset types (types of content) associated with priority AI use cases.
• Apply metadata models consistently across all content source systems to enhance findability and discoverability of content in AI applications. 
• Document and regularly update metadata models.
• Store and manage metadata models in a centralized semantic repository to ensure interoperability and scalable reuse across AI solutions.

Semantic Maturity of Ontology

Just as with taxonomies, metadata, and business glossaries, developing semantically rich and precise ontologies is essential to achieve successful AI applications and to enable Knowledge Intelligence (KI) or explainable AI. Ontologies must be sufficiently expressive to support semantic enrichment, traceability, and AI-driven reasoning. They must be designed to accurately represent key entities, their properties, and relationships in ways that enable consistent tagging, retrieval, and interpretation across systems and AI use cases. By taking the following actions, your ontology model will achieve the level of semantic maturity needed for content to be AI ready:

• Ensure ontologies accurately describe the knowledge domain for the in-scope content.
• Define key entities, their attributes, and relationships in a way that supports AI-driven classification, recommendation, and reasoning.
• Design modular and extensible ontologies for reuse across domains, applications, and future AI use cases.
• Align ontologies with organizational taxonomies to support semantic interoperability across business areas and content source systems.
• Annotate ontologies with rich metadata for human and machine readability.
• Adhere to ontology standards such as OWL, RDF, or SHACL for interoperability with AI tools.
• Store ontologies in a central ontology management system for machine readability and interoperability with other semantic models.

Preparing content for AI is not just about organizing information, it’s about making it discoverable, valuable, and usable. Investing in semantic models and ensuring a consistent content structure lays the foundation for AI to generate meaningful insights. For example, if an organization wants to deliver highly personalized recommendations that connect users to specific content, building customized taxonomies, metadata models, business glossaries, and ontologies not only maximizes the impact of current AI initiatives, but also future-proofs content for emerging AI-driven use cases.

5) Semantic Model Application (Content Tagging)

Designing structured semantic models is just one part of preparing content for AI. Equally important is the consistent application of complete, high-quality metadata to organization-wide content. Metadata enrichment of unstructured content, especially across silo repositories, is critical for enabling AI-powered systems to reliably discover, interpret, and utilize that content. The following actions to enhance the application of content tags will help you achieve content AI readiness:

• Tag unstructured content with high-quality metadata to enhance interpretability in AI systems.
• Ensure each piece of relevant content for the AI solution is sufficiently annotated, or in other words, it is labeled with enough metadata to describe its meaning and context. 
• Promote consistent annotation of content across business areas and systems using tags derived from a centralized and standardized taxonomy. 
• Leverage mechanisms, like auto-tagging, to enhance the speed and coverage of content tagging. 
• Include a human-in-the-loop step in the auto-tagging process to improve accuracy of content tagging.

Consistent content tagging provides an added layer of meaning and context that AI can use to deliver more complete and accurate answers. For example, an organization managing thousands of unstructured content assets across disparate repositories and aiming to deliver personalized content experiences to end users, can more effectively tag content by leveraging a centralized taxonomy and an auto-tagging approach. As a result, AI systems can more reliably surface relevant content, extract meaningful insights, and generate personalized recommendations.

6) Address Access and Security (Unified Entitlements)

As Joe Hilger mentioned in his blog about unified entitlements, “successful semantic solutions and knowledge management initiatives help the right people see the right information at the right time.” But to achieve this, access permissions must be in place so that only authorized individuals have visibility into the appropriate content. Unfortunately, many organizations still maintain content in old repositories that don’t have the right features or processes to secure it, creating a significant risk for organizations pursuing AI initiatives. Therefore, now more than ever, it is important to properly secure content by defining and applying entitlements, preventing access to highly sensitive content by unauthorized people and as a result, maintaining trust across the organization. The actions outlined below to enhance Unified Entitlements will accelerate your journey toward content AI readiness:

• Define an enterprise-wide entitlement framework to apply security rules consistently across content assets, regardless of the source system.
• Automate security by enforcing privileges across all systems and types of content assets using a unified entitlements solution.
• Leverage AI governance processes to ensure that content creators, managers, and owners are aware of entitlements for content they handle and needs to be consumed by AI applications.

Entitlements are important because they ensure that content remains consistent, trustworthy, and reusable for AI systems. For example, if an organization developing a Generative AI solution stores documents and web content about products and clients across multiple SharePoint sites, content management systems, and webpages, inconsistent application of entitlements may represent a legal or compliance risk, potentially exposing outdated, or even worse, highly sensitive content to the wrong people. On the other hand, the correct definition and application of access permissions through a unified entitlements solution plays a key role in mitigating that risk, enabling operational integrity and scalability, not only for the intended Generative AI solution, but also for future AI initiatives.

7) Maintain Quality While Iteratively Improving (Governance)

Effective governance for AI solutions can be very complex because it requires coordination across systems and groups, not just within them, especially among content governance, semantic governance, and AI governance groups. This coordination is essential to ensure content remains up to date and accessible for users and AI solutions, and that semantic models are current and centrally accessible. 

AI Governance for Content Readiness 

Content Governance 

Not all organizations have supporting organizational structures with defined roles and processes to create, manage, and govern content that is aligned with cross-organizational AI initiatives. The existence of an AI Governance for Content Readiness Group ensures coordination with the traditional Content Governance Groups and provides guidance to content owners of the source systems on how to get content AI ready to support priority AI use cases. By taking the following actions, the AI Governance for Content Readiness Group will help ensure that you have the content governance practices required to achieve AI-ready content:

• Define how content should be captured and managed in a way that is consistent, predictable, and interoperable for AI use cases.
• Incorporate in your AI solution roadmap a step, delivered through the Content Governance Groups, to guide content owners of the source systems on what is required to get content AI ready for inclusion in AI models.
• Provide guidance to the Content Governance Group on how to train and communicate with system owners and asset owners on how to prepare content for AI.
• Take the technical and strategic steps necessary to connect content source systems to AI systems for effective content ingestion and interpretation.
• Coordinate with the Content Governance Group to develop and adopt content governance processes that address content gaps identified through the detection of bias, hallucinations, or misalignment, or unanswered questions during AI testing.
• Automate AI governance processes leveraging AI to identify content gaps, auto-tag content, or identify new taxonomy terms for the AI solution.

Semantic Models Governance

Similar to the importance of coordinating with the content governance groups, coordinating with semantic models governance groups is key for AI readiness. This involves establishing roles and responsibilities for the creation, ownership, management, and accountability of semantic models (taxonomy, metadata, business glossary, and ontology models) in relation to AI initiatives. This also involves providing clear guidance for managing changes in the models and communicating updates to those involved in AI initiatives. By taking the following actions, the AI Governance for Content Readiness Group will help ensure that your organization has the semantic governance practices required to achieve AI-ready content: 

• Develop governance structures that support the development and evolution of semantic models in alignment with both existing and emerging AI initiatives.
• Align governance roles (e.g. taxonomists, ontologists, semantic engineers, and AI engineers) with organizational needs for developing and maintaining semantic models that support enterprise-wide AI solutions.
• Ensure that the systems used to manage taxonomies, metadata, and ontologies support enforcing permissions for accessing and updating the semantic models.
• Work with the Semantic Models Governance Groups to develop processes that help remediate gaps in the semantic models uncovered during AI testing. This includes providing guidance on the recommended steps for making changes, suggested decision-makers, and implementation approaches.
• Work with the Semantic Models Governance Groups to establish metrics and processes to monitor, tune, refine, and evolve semantic models throughout their lifecycle and stay up to date with AI efforts.
• Coordinate with the Semantic Models Governance Groups to develop and adopt processes that address semantic model gaps identified through the detection of bias, hallucinations, or misalignment, or unanswered questions during AI solution testing.

For example, imagine an organization is developing business taxonomies and ontologies that represent skills, job roles, industries, and topics to support an Employee 360 View solution. It is essential to have a governance model in place with clearly defined roles, responsibilities, and processes to manage and evolve these semantic models as the AI solutions team ingests content from diverse business areas and detects gaps during AI testing. Therefore, coordination between the AI Governance for Content Readiness Group and the Semantic Models Governance Groups helps ensure that concepts, definitions, entities, properties, and relationships remain current and accurately reflect the knowledge domain for both today’s needs and future AI use cases.  

Conclusion

Unstructured content remains as one of the most common knowledge assets in organizations. Getting that content ready to be ingested by AI applications is a balancing act. By cleaning it up, filling in gaps, applying rich semantic models to add structure and context, securing it with unified entitlements, and leveraging AI governance, organizations will be better positioned to succeed in their own AI journey. We hope after reading this blog you have a better understanding of the actions you can take to ensure your organization’s content is AI ready. If you want to learn how our experts can help you achieve Content AI Readiness, contact us at info@enterprise-knowledge.com. 

The post How to Ensure Your Content is AI Ready appeared first on Enterprise Knowledge.

Taylor Swift’s strategy of repurposing content, while unique for a singer, is very common from a business perspective. 94% of marketers repurpose content, indicating that reusing content is not a new concept… and yet, are you exploring the multi-facet reuse of your content? 

Since July 2020, Taylor Swift has released five original studio albums, four studio album re-recordings (“Taylor’s Version” produced before Taylor was able to buy back her original catalog of recordings), presentation variants, deluxe editions, and live albums totaling 36 albums to date, with 20 million+ units sold. Swift has had a stratospheric few years of breaking records—including becoming the first musician ranked as a Forbes billionaire primarily from songs and performances— partially due to her intelligent “content” reuse. What can we learn from this? Read on to find out.

Results

Before delving into the ways you can reuse content, what results can you expect when you put in the foundational work to enable intelligent reuse?

Broaden Your Target Audience

Statistically speaking, if you increase the amount of content you produce, you are more likely to reach a wider audience. With the development of the Eras Tour (where each era represents one of her 11 studio albums, spanning several different genres), many Taylor Swift fans began to classify themselves by their preferred “era”, or the album that made them a fan of Swift. With each album and re-recording, she’s endeared more fans to her, based on their preferred genre. 

The same can be said for reusing and repurposing content. By using Structured Content Management and effective content reuse, you decrease the overhead associated with creating and managing content. This effectively enables more systematic ways to reuse content and frees up time for content producers to create new and interesting types of content. This results in both an increase in content and the opportunity to broaden your audience. Moreover, content reuse frees up content producers’ and content marketers’ time, paving the way for two vital capabilities: personalization and experimentation.

Increase Customer Engagement with Personalization

In this day and age, most marketers use personalized content to reach their customers, but 74% say they struggle with scaling that personalization. While structured content alone can enable personalization of content in a more systematic way, when you combine structured content with the power of a knowledge graph, you also pave the way for effective personalization at scale. Using a combination of metadata applied to content components, data known about customers, and a knowledge graph, dynamic content can be created and scaled to reach more segments of customers. By giving customers relevant and personalized content for their needs, you are more likely to increase customer engagement and satisfaction.

Increase Conversion Rates with Experimentation

As a final highlighted benefit, deploying Structured Content Management enables your organization to run experiments on content, fail quickly, and adjust the content strategy as needed. While page variants and A/B testing can be deployed with traditional content management, it is not the same as being able to test an individual content component and run many different experiments quickly. This could be presentation experiments—does a CTA perform better on the side rail or above the fold embedded in the body content—but could also be which content performs best when presented in the “related content” section, an infographic or a blog? What ultimately comes from experimentation is an invaluable feedback loop that enables your organization to develop high-value, high-performing content that increases engagement metrics such as improving conversion rates.

Types of Reuse

Now that we’ve covered the benefits, let’s turn our attention to the types of reuse that are possible. Swift’s 36 record-shattering albums have three core reuse strategies: visual change, audience change, and assembly change. While there are certainly more than this, we’ll look at the same three methods in this blog: a new presentation, a new lens, and a new assembly. When it comes to your organization’s essential content, how can you reuse your content in the same ways without it becoming stale?

Change the Presentation of Content

Visually, many of the albums Swift has released in the last 5 years have thematic visual ties with the album art. Speak Now (Taylor’s Version) was released in three different shades and hues of purple: Orchid Marbled, Violet Marbled, and Lilac Marble. It’s not uncommon to see people create “Franken Variants,” where they’ve taken an LP from each version and put them together. The parallel to content strategy is the presentation changes made when employing multi-channel marketing. You may have written a long-form blog, but you’ll send it out in an email, on a social post, etc. Social posts can vary depending on the site, and many digital asset management systems (DAMs) support the ability to create automatic derivatives that fit the particular parameters of a social media channel (e.g. Instagram is 1080 x 1080 pixels, while LinkedIn is 1350 x 440 pixels) without creating an entirely new copy of this content. 

What are other ways you could create a new presentation of the content, though? When we design Content Models at EK, we emphasize decoupling content from presentation to enable this kind of reuse. When you create a model for a content type, the focus should be on what information is being communicated rather than how it is presented. An example of this could be a social proof component. Perhaps when writing up a use case of your product by a customer in long-form content, you have quotes from customers. Within the body of the long-form content it may have a particular styling, but you also reuse the quote on landing pages as social proof, and on these pages it uses more of a card style. If you decouple the customer quote from the styling needed in different channels, you can automatically populate the different styles without keeping multiple copies.

This not only saves time from creating all new components every time they are reused, but also decreases the risk of mistakes that can be introduced through manually copying the content. We saw this recently with a client who used social proof throughout their marketing website on many different pages, but through a content audit, it was discovered that one of the quotes was misattributed to another customer in an entirely different industry. The customer then had to go through the entire website (10,000 pages!) and scrub the quote. If they had already implemented Structured Content Management, they could have changed all instances with a single content update.

Update the Tone or Perspective of the Content

For Record Store Day in 2023, Swift released a version of her Folklore album that had only been seen in a Disney+ special, The Long Pond Studio Sessions (LPSS). This record was an acoustic version of the pandemic release Folklore, recorded at Aaron Dessner’s Long Pond Studios. While many may wonder why you would buy another version of an album you already have, many fans prefer the LPSS version because Swift sounds more raw than the studio version. While it is infamously difficult to get the right tone on the internet (e.g. if I don’t use exclamation points or emojis, I’m worried you’ll think I’m cold), tone of voice can still be incorporated in content and be consistent with your organization’s branding. In the same way, when you’re communicating information with a group of stakeholders, you may shift tone depending on the make-up of those stakeholders. You’ll communicate information differently to a group of executives compared to a group of individual contributors, or a group from IT vs. a group from HR. How can you use this with your customer-facing content? 

Perhaps your company writes a lot of thought leadership, and a customer can browse this thought leadership via an abstract or summary of the content. While you may have originally written the abstracts very technically, you may have since realized that your audience base is predominantly newer professionals who do not know all of your industry’s lingo. Using this insight into your customers, you could then update the abstracts to be more beginner-friendly to prompt more engagement with posts. While this could be a manual change, there’s also the possibility of using generative AI to adjust the tone or comprehension level of the abstracts to speed up rewriting and repurposing. Additionally, this paves the way for personalization by having variations of components tagged with different audiences. When a certain customer is identified as belonging to a certain group, content could be dynamically updated via a graph to be more appealing to the customer. This increases engagement and customer satisfaction. 

Use a New Assembly of Content

On many levels, music is an assembly. A song is an assembly of notes and phrases, an album is an assembly of songs that tell a story, a playlist is an assembly of songs curated in a chosen order to mimic an event or a feeling. One of the things Swift did during the Eras Tour was include a “Surprise Song” section in which she would play one song from her discography on guitar and one on piano. While at the beginning of the tour, she was playing single songs on each instrument, by the end of the tour, she was making “mashups” of songs where she would seamlessly mix multiple songs together for a new creation. I Hate It Here x the lakes, The Manuscript x Long Live, I Think He Knows x Gorgeous—over the course of several months, Swift created many new songs that were assemblies of parts of other songs.

When talking about Structured Content Management, we frequently compare content components or modular content to Legos. By creating reusable “legos” of content, you enable many different assemblies of those legos. This could take many forms—marketing landing pages or generation of proposals—but one of the easiest examples to understand is learning content. Internal trainings are ubiquitous in many organizations and often a sore spot because they can be irrelevant to an employee’s position. For example, perhaps you have a training on harassment that employees are required to take, but because the course is packaged as a single unit rather than broken up by the lessons within, all employees end up learning about topics that are more relevant to people managers. This could mean that the employee “checks out” when consuming that lesson and is more likely to disengage from the rest of the training. By creating smaller blocks of content, you could then have a personalized assembly of topics tagged with individual contributors and a personalized assembly of topics tagged with people managers without having to create multiple copies of the same course. 

Conclusion

While certainly not the first (or the only! or the last!) artist to develop methods of reuse, love her or hate her, it’s clear that Taylor Swift is a mastermind when it comes to engaging and expanding her fanbase. You can use these same techniques with your organization to expand your customer base. When you employ a clear content strategy and leverage methodical content engineering and content operations, your organization’s content has the potential to develop into a true business asset. If this has sparked your interest and you’re ready to get serious about bringing your content to its highest potential, give us a call.

The post Content Mastermind (Taylor’s Version): What Taylor Swift Can Teach Us About The Benefits of Repurposing Content appeared first on Enterprise Knowledge.

The Content Management Continuum 

Before we jump in, we need to clarify that there are three major content management methods that exist on a continuum — File-Level Management, Page-Based Content Management, and Semantic Content Management. 

• File-Level Management results in final output of information in the form of a document or file; there is no codified structure that exists within the document, and it is meant to be consumed as a whole.
• Page-Based Content Management gives authors a blueprint or a template to construct a page of content. For example, a proposal probably includes fields for introduction, problem statement, company description, solution approach, and references. If end users are then looking for, “what solution did we propose to Company A?,” it’s much easier to open the published page and scan for the “Solution Approach” section rather than having to parse through the entire document. 
• With Semantic Content Management, you are managing smaller content components that can be reused across multiple documents, files, or assemblies. In our previous example of proposals, the “Solution Approach,” rather than being a section of a page, would be managed as a component enriched with metadata that could be reused for other proposals. While there are standard ways to enrich content and extract meaning in a more automated fashion which can improve all methods on the content management continuum, componentization can require both substantial technical and human investment to realize the return on investment (ROI). 

While an overall enterprise content strategy should exist, that does not mean that every piece of content is managed in the same way. A thorough and iterative content analysis should be performed to identify how different types of content should be managed. The strategies to prepare content for AI vary based upon where it sits on the continuum, however, here we’ll be primarily focused on the Semantic Content Management end of the continuum.

Why Structure Content?

If a driver is on the side of the road with an unknown light flashing on their dashboard, they’re not going to start at the beginning of the owner’s manual and read, “How to turn the car on.” They’re going to flip to the warning lights guide, determine which warning light it is that they’re seeing, and then flip to the appropriate section for that warning light. This example illustrates a fundamental need for all documentation and other types of technical writing. It’s rare that a consumer will read the manual cover to cover in one go – it’s meant to be consumed in smaller chunks that meet a need, and we facilitate that by structuring the content to easily meet those needs. Structuring content in this manner is the beginning of the continuum into semantic content management.

How Does Structured Content Improve AI and LLM Results?

While LLMs rely on a large amount of content (hence, large language models) and can make sense of unstructured text because of the amount of data they consume, when we structure documents, we facilitate even better understanding of the content by the machine. Perhaps even more crucial, once content is broken up, we’ve improved storage and made retrieval easier and more efficient. If all of an organization’s help documentation is written in the same structure, where the introduction indicates the main topic of the article and the body of the text is broken down into important pieces of information, the LLM model has a better indication of what may be useful for any given prompt and can hone in on the answer that the user is expecting. Furthermore, if structured documents are fed into a Generative AI (or GenAI) pipeline that has been designed to provide a summary based on the introduction of a document, then the unity in structure facilitates automated extraction, improving the efficiency and accuracy of the answers to given questions, as well as tailoring the response given to match the style from the ingested content. 

Why Componentize Content?

As described earlier, when using the Semantic Content Management method, you are managing smaller content components that have been broken up from larger documents, pages or files. This process of breaking content down is called componentization, but why would you take the time to do that? Componentization facilitates reuse, which at a high level:

1. Reduces the amount of copies that exist and the organizational burden to manage those copies 
2. Creates an explicit structure of relevancy that can be referenced by humans and computers alike
3. Decreases organizational risk by introducing a single source of truth 
4. Facilitates rapid personalization and experimentation to improve engagement
5. Easily transforms into a graph for semantically precise and contextualized retrieval of information

As explained above, content structure exists on a continuum from unstructured documents to dynamic content, and every organization has to decide what is right for them and for all of their pieces of content based on a well-thought-out content strategy. For our purposes in this blog, let’s assume that your content strategy demands at least some semantically managed, componentized content and discuss how componentization improves AI results. 

How Does Semantic Content Management Improve AI and LLM Results?

Why would you take the time to create components? First, on the human end, having a standard component for something as simple as an introduction or a footer improves content operations because you’re not having to hunt down the language used in other documents or running the risk of a copy/paste error. On the machine end, by indicating to the LLM that some particular component (e.g., the introduction or the footer) are the same “thing” across documents, we can simplify some of the automated workflows and extraction that occur while building the model. A standard component is important for consistency’s sake, but it also helps to indicate the component as something that’s perhaps not as relevant to the user, and that more time should be spent on the unique content. In the same way most search engines will not return “the” or “a” and indexes generally will not alphabetize using “the,” recognizing a standard introduction as one object decreases the machine load of having to intake the introduction every time. 

What also is enabled by reusable components, however, is the ability to trace the network of information that can start to appear by the appearance of components across content assemblies. Perhaps you’ve written a help document about Feature A, but in using Feature A, the user also needs to use Feature B; rather than rewrite content about Feature B, you can reuse the components related to it. This then creates an explicit relationship between Feature A and Feature B and starts to facilitate the creation of a graph. When we start to model content in a semantic manner, we’re not creating models in a vacuum; they exist as part of a larger business ontology and knowledge model that work together to inform agile, dynamic, and scalable content. 

Using these reusable components also decreases the risk of conflicting information in the digital experience, thereby reducing the risk of hallucinations. If in one help document you have written, “Feature A is accessible by all roles,” but then in another document it says, “you can only access Feature A if you have admin permissions,” there is now conflicting information that the LLM has to resolve through generative AI. It may be successful in being able to pull context elsewhere or make an “educated guess,” but the more contradictory information the LLM is fed, the more likely it is to have hallucinations and provide inaccurate or inappropriate responses.   

The Human Element

We’ve all heard, “garbage in, garbage out.” The same adage can certainly be applied to AI, and generally if your organization is in the File Content Management end of the spectrum, it can be harder to maintain the content repository, thereby increasing the possibility of garbage existing that can then decrease the reliability of the model. It’s also important to note that it’s not just garbage that we have to be mindful of, but that an organization’s biases and quirks present in their content will also show up in LLM responses. In 2018 Safiya Noble wrote, “Algorithms of Oppression: How Search Engines Reinforce Racism.” If you’re on TikTok, you may be aware of the phrase, “I am responsible for my own algorithm,” a phrase commented when you’ve landed on one of the “weirder” videos that exist – the sum of the choices of what you’ve interacted with (and not interacted with!) brought you to the video you’re seeing now. Both of these concepts highlight the fact that AI and LLM output is highly contingent on their respective human input(s). It is not “random” or “neutral,” choices made by humans writing and constructing content influence how the LLM will respond. If your organization is operating in the Semantic Content Management sphere, you decrease the risk of “garbage” files that may exist, but you do have to be mindful of how content has been structured and who has authored the content. If your content components are missing style guides or proper governance, you run the risk of the model training on inconsistent content, thereby influencing the outputs. By doing a content audit you can circumvent this potential pitfall, and improve how your AI is being used. 

The Context Element

If you’ve ever bought concert tickets, you may be familiar with the importance of a map or the context in which the ticket exists. Section 114, Row A of a stadium may be a great seat within the context of a basketball game, but could be an “obstructed view” at a Taylor Swift concert. The same is true for working with Legos – one Lego can serve many different purposes in the different sets or assemblies that exist. The almost 10,000 piece Titanic Lego set reuses much of the same bricks that you see in less complicated sets, and yet if you were to consume only the bricks and not their assembly you wouldn’t know how versatile a brick could be. This highlights the fact that AI and LLM output is improved when it “knows” the full context of a chunk of content, rather than extrapolating the context based on general knowledge it has picked up through other content it has ingested. By consuming both the component and the larger content object, as well as the metadata that enriches these two content objects, the model improves its comprehension of the content. By investing in semantic content management, and providing the LLM with a basis of context that it can train with, you are much more likely to receive a usable output from your AI investment.

Conclusion

When it comes to content and AI, there is no one-size-fits-all. Depending on your organizational needs and goals, your content could fall anywhere on the content management continuum. What is important is developing a foundational content strategy to thoughtfully and methodically manage your content in a way that meets your needs. If you’re interested in AI, structured and componentized content may be what your organization needs to improve your ROI and develop scalable, long-term success.

Need help making your investment in AI worthwhile, or defining your action plan for improving your content for AI? Check out our AI-ready Content Accelerator or contact us, we’d love to help!

The post Improve Enterprise AI with Semantic Content Management appeared first on Enterprise Knowledge.

This presentation explored the basics of reusable learning content, including the types of reuse and the key benefits of reuse such as improved content maintenance efficiency, reduced organizational risk, and scalable differentiated instruction & personalization. After this primer on reuse, Crockett laid out the basic steps to start building reusable learning content alongside a real-life example and the technology stack needed to support dynamic content. Key objectives included: 

• Be able to explain the difference between reusable learning content and duplicate content; 
• Explore how a well-designed learning content model can reduce duplicate content and improve your team’s efficiency; and
• Identify key tasks and steps in creating a learning content model.

Participants learned how thoughtful content strategy for reusable learning content improves content operations efficiency. 

The post Improving Learning Content Efficiency with Reusable Learning Content appeared first on Enterprise Knowledge.

Interested in turning your content into a strategic business asset? Contact us today!

The post Dynamic Content appeared first on Enterprise Knowledge.

With the rise of ChatGPT and other generative AI tools in the last year, there’s a common misconception that you can “do” AI on any content with no preparation. If you want accurate and useful results and insights, however, it requires some upfront work. Understanding how AI interacts with your content and how your content strategy supports AI readiness will set you up for an effective AI implementation. 

How AI Interacts with Content

While AI can help in many phases of the content lifecycle, from planning and authoring to discovery, AI usually interacts with existing content in two key ways:

	1) Comprehension: AI must parse existing content to “understand” an organization’s vernacular or common language. This helps the AI model create statistical models, cluster content and concepts, and create a baseline for addressing future inputs.
	2) Search: AI often needs to quickly identify snippets of content related to text, chunking longer content into smaller components and searching these components for relevant material. These smaller snippets are often used to gain an understanding of new or updated material.

When AI examines existing content, it is trying to understand what it is about and how it relates to other concepts within the knowledge domain, and there are steps we can take to help. While this blog is mostly considering how large language models (LLMs) and retrieval augmented generation (RAG) AI interact with content, the steps listed below will prepare content for a variety of other types of AI for both insight and action.

Developing a Content Strategy

The best way to prepare content for AI is to develop a content strategy that addresses the relationships, the structure, the clean up, and the componentization of the content. One key preliminary activity will be to audit your content with the specific lens of AI-readiness, and to assess your organization’s content against the steps listed below.  

Model the Knowledge Domain

In most situations, AI creates internal models to group and cluster information to help the AI respond efficiently to new inputs. AI does a decent job of inferring the relationships between information, but organizations can significantly assist this process by defining an ontology. Ontologies enable organizations to define and relate organizational information, codifying how people, tools, content, topics, and other concepts are related. These models improve findability, support advanced search use cases, and form semantic layers that facilitate the integration of data from multiple sources into consumable formats and user-intuitive structures. 

Once created, an ontology can be used with content to:

• auto-tag content with related organizational information (topics, people, etc.);
• enable navigation through an organization’s knowledge domain by following relationships; and
• supply AI with curated models that explain how content connects with the organization’s information that can lead to key business insights. 

Modeling an organization’s knowledge domain with an ontology improves AI’s ability to utilize content more effectively and produce more accurate results.

Cleanup and Deduplicate the Content 

Today’s organizations have too much content and duplicated information. Content is often split between multiple systems due to limitations with legacy tools, user permissions, or the need to support new features and displays. While auditing all of an organization’s content may seem daunting, there are steps an organization can take to streamline the process. Organizations should focus on their NERDy content, identifying the new, essential, reliable, and dynamic content users need to perform their jobs. As part of this focus, organizations reduce content ROT (Redundant, Outdated, Trivial), improving user trust and experience with organizational information. 
As part of the cleaning effort, an organization may want to create a centralized authoring platform to maintain content in one place rather than siloed locations. This allows content to be managed in one place, reducing the effort to update content and enabling content reuse. Reusing content helps deduplicate content, removing the need to replicate and update content in multiple places. A content audit, analysis, and clean-up will organize content in an intuitive way for AI and reduce bias from repeated or incorrect information.

Add Structure and Standardization

Once your organization’s knowledge domain is defined, the next step is to create the content models and content types that support that ontology, this is often referred to as content engineering. 
Content types are the reusable templates that standardize the structure for a particular format of content such as articles, infographics, webinars, and product information, as well as the standard metadata that should be included with that content type (created date, author, department, related subjects, etc.).

If we think of Content Types as the cake pan in this analogy, a content model is the Cake Recipe. While the Content Type defines the structure of the content, the Content Model defines the meaning of that content. In the cake analogy, you may have a chocolate cake, a vanilla cake, and a carrot cake; theoretically, any of those recipes could be used in any of the pans. If the content type dictates how, the content model dictates what. In an organization this could look like a content model of a product that includes parts like the product title, the product value proposition, the product features, etc. This content model of a product could then be fit into many content types, such as a brochure, a web page, and an infographic. By creating content models and content types we give the AI model better insight into how the content is connected and the purpose it serves.

The structure of these templates provides AI with content in a consumable and semantically meaningful format where content sections and metadata are given to the AI model. A crucial part of content engineering  is the creation of a taxonomy to describe the content. Taxonomies should be user-centric, highlighting users’ terminology to talk about content. The terms within a taxonomy and the associated synonyms improve an AI’s capability to utilize the content. Additionally, content types and content models facilitate the consistent display of information and configuration of advanced search features, improving the user experience when looking for and viewing content.

Componentize the Content

Once the content is structured and cleaned, a common next step is to break up the content into smaller sections according to the content model. This process has many names, such as content deconstruction, content chunking, or the creation of content components. In content deconstruction, structured content is split into smaller semantically meaningful sections. Each section or component has a standalone purpose, even without the context of the original document. Content components are often managed in a component content management system (CCMS), providing the following benefits:

• Users (and AI) can quickly identify relevant sections of larger content.
• Authors can reuse content components across multiple documents.
• Content components can have associated metadata, enabling systems to personalize the content that users see based on their profiles.
• Dynamic content is possible.

Similar to the user benefits, content components provide AI with user-generated components of content as opposed to requiring the AI to perform statistical chunking. The content chunks allow an AI to identify relevant text inputs quickly and more accurately than if fed entire large documents.

Conclusion

Through effective content strategy, content audit, and content engineering, organizations can efficiently manage information and ensure that AI has correct, comprehensive content with semantically meaningful relationships. A well-defined content strategy provides a framework to curate old and new information, allowing organizations to continuously feed information into AI, keeping its internal models up-to-date. A well-structured content audit will ensure preparation time is spent on the areas that will make the most difference in AI-readiness such as structure, standardization, componentization, and relationships across content. Well-thought-out content engineering will enable content reuse and personalization at scale through machine readable structure. 

Are you seeking help defining a content strategy, auditing your content for AI-readiness, or training your AI to understand your domain? Contact us and let us know how we can help!

Special thank you to James Midkiff for his contributions to the first draft of this blog post!

The post How to Prepare Content for AI appeared first on Enterprise Knowledge.