Episode 6 of Components Live—recorded in Valencia as part of this 11-part series—features Patrick Bosek and Noz Urbina exploring why graph databases are having a moment—and what that means for structured content and AI.

They begin by contrasting graph databases with traditional relational databases. Where relational systems rely on tables, rows, and predefined schemas, graphs model entities and the relationships between them in a more flexible, self-describing way. The result is a structure that more closely mirrors how humans think—through connections, associations, and context.

To make this tangible, Patrick and Noz use familiar examples: how we recall people through shared connections, the classic “Six Degrees of Kevin Bacon,” and complex product or parts relationships in engineering systems. In each case, graph models excel because they support many-to-many relationships and open-ended exploration—without forcing edge cases into rigid table structures.

This flexibility unlocks something powerful: discovery.

Graphs allow systems to traverse relationships, uncover patterns, and even support inference in ways that are difficult or inefficient with traditional databases. That capability becomes especially important in AI-driven environments, where understanding context and connections is key to delivering accurate answers.

They also highlight an important technical advantage: graph query patterns tend to be closer to natural language. That makes them a strong fit for large language models, which can more reliably generate and execute graph-style queries compared to more rigid SQL-based approaches. The result? More accurate and intuitive question-answering experiences, as supported by emerging research and real-world implementations.

The conversation then zooms out to look at the bigger picture—particularly how Google has evolved its search experience. What was once a list of blue links has increasingly become a dynamic, relationship-driven interface powered by underlying graph structures. It’s a shift that signals a move “beyond the page,” where information is assembled and delivered based on meaning, not just documents.

For technical communicators and content teams, the implication is clear: the future of content isn’t just about managing information—it’s about modeling relationships. And graph-based approaches may be a key part of making content truly AI-ready.

Episode 5 of Components Live—part of the 11-part Valencia series—features Patrick Bosek and Noz Urbina taking on a debate that refuses to die: structured vs. unstructured content for AI.

But instead of picking sides, they challenge the premise.

Patrick and Noz argue that most discussions miss a more important question—what do we actually mean by “structure,” and where does it create value in a system? The answer, as they explore, is highly contextual.

They walk through scenarios where structure clearly improves outcomes. One standout example: tabular data. In large tables, LLMs can struggle to maintain column relationships as they process deeper rows. Without repeated metadata, meaning can break down. In these cases, structure—and even strategically reinforcing it—can significantly improve how AI interprets the data.

On the flip side, they share examples where rigid structure can get in the way. For content like glossaries, converting highly structured, DITA-style entries into clean, natural-language sentences actually produced better results for AI consumption. It’s a reminder that large language models are fundamentally optimized for human language—not strict schemas.

This leads to a more nuanced takeaway: it’s not about choosing structured or unstructured—it’s about knowing when and how to use each.

The conversation reinforces a key principle from earlier episodes: keep content structured upstream. By doing so, teams retain flexibility. Deterministic systems can pull exact values from structured sources (like tables), while transformation layers—using tools like XSLT—make it possible to experiment with different ways of “dosing” content for AI, adapting quickly as models and use cases evolve.

Finally, Patrick and Noz caution against a common trap: storing content only in delivery formats like Markdown, PDF, or HTML. These formats are endpoints, not sources of truth. As channels continue to shift—from websites to AI agents and beyond—structured content ensures that information can be repurposed, recombined, and delivered wherever it’s needed next.

This episode brings the series back to a central theme: structure isn’t about rigidity—it’s about optionality. And in an AI-driven world, that flexibility is what makes content future-ready.

Episode 4 of Components Live—recorded on-site at La Botifarra in Valencia—continues the 11-part series with Patrick Bosek and Noz Urbina diving into one of the most important (and often misunderstood) topics in AI: context.

Rather than treating “structured vs. unstructured content” as a binary debate, Patrick and Noz reframe it as part of a broader challenge—how to effectively navigate and deliver the right context to AI systems at the right time. In this episode, they break down how context operates across different layers of AI, starting with the distinction between training and fine-tuning (post-training) versus how large language models are configured and used at question time.

From there, they unpack one of the most talked-about approaches in enterprise AI today: Retrieval-Augmented Generation (RAG). Instead of expecting an AI model to “know” everything, RAG works by retrieving relevant content from source systems and injecting it into the model’s context window—the limited working memory available during a given interaction.

That limitation is key.

Patrick and Noz explain the concept of the context window as a kind of short-term memory for AI systems—one that can become strained as more information is added, sometimes leading to degraded recall or accuracy, especially in the middle of long inputs. This makes upstream retrieval and selection incredibly important.

To make this more tangible, they compare it to how ChatGPT uses web search: it doesn’t read the entire internet on demand—it retrieves and prioritizes a subset of relevant sources. Enterprise AI systems operate the same way, except instead of the open web, they rely on internal documentation, knowledge bases, and structured content systems.

The takeaway? Success with AI isn’t just about the model—it’s about “context engineering.” By improving how content is retrieved, structured, and delivered into the context window, organizations can significantly increase the factual accuracy of AI-generated responses—often moving from roughly 70% reliability into the high 80s or beyond.

This episode sharpens the focus of the series, showing that the future of AI in technical communication isn’t just about generating content—it’s about designing the systems that ensure AI has the right information to begin with.

Episode 3 of Components Live—part of the 11-part series recorded live in Valencia—finds Patrick Bosek and Noz Urbina tackling a fast-evolving question: what does content reuse look like in a world increasingly driven by AI search?

The conversation opens by reframing reuse in two distinct contexts. On one hand, there’s reuse for drafting—helping teams create content more efficiently. On the other, there’s backend reuse—structuring content in ways that power downstream delivery across channels, interfaces, and now, AI systems. As Patrick and Noz explore, that second layer is becoming significantly more important as AI reshapes how users find and consume information.

From there, they dive into the emerging world of AI search optimization—often referred to as GEO (Generative Engine Optimization) or AEO (Answer Engine Optimization). It’s a space that’s still taking shape, with even the terminology up for debate. But one thing is clear: the rules are shifting.

Noz highlights a key tension with traditional SEO thinking. For years, duplicated content was something to avoid. But in an AI-driven landscape, consistent repetition of the same message across multiple touchpoints may actually act as a signal—helping AI systems recognize patterns and increasing the likelihood that your content is surfaced as the “best” answer.

The episode also draws an important distinction between optimizing for public AI systems—like Google—and designing content for private, customer-facing AI agents powered by your own backend. These are fundamentally different challenges, with different levels of control, risk, and opportunity.

Finally, Patrick and Noz discuss Google’s rapid evolution toward a chat-first experience, including recent moments where the Google app routes searches directly into conversational responses powered by Gemini—sometimes without showing traditional web results at all. It’s a signal of where search is heading, and a wake-up call for content teams still optimizing for a list of blue links.

This episode pushes the series further into the practical implications of AI on content strategy, challenging long-held assumptions and offering a fresh lens on how reuse can drive visibility, consistency, and impact in an AI-first world.

Episode 2 of Components Live continues the 11-part in-person series recorded in Valencia, where Patrick Bosek and Noz Urbina dig deeper into one of the most foundational (and often overlooked) challenges in content operations: defining truth.

At the center of this conversation is the idea of a “context graph”—and how it connects to systems of truth in an AI-driven environment. Patrick and Noz explore a deceptively simple but critical question: What is the right answer, and where should it live? As they point out, determining that answer is often unglamorous, messy work—but it’s essential to making AI outputs reliable.

They break down the real-world consequences of getting this wrong. Technical communicators have long resisted maintaining multiple conflicting versions of the same content—and for good reason. Duplicate or inconsistent information doesn’t just create editorial headaches; it drives up translation costs, increases support tickets, leads to field errors, frustrates customers, and ultimately erodes brand trust.

From there, the discussion turns to a timely debate: is content reuse dead—or more important than ever?

With AI now playing a larger role in drafting and content generation, there’s a risk that reuse discipline could weaken, leading to even more content drift. Noz advocates for a more proactive approach: applying AI across the entire content lifecycle—from planning and strategy to product design and requirements—so reuse is defined early and embedded into the system. In this model, AI doesn’t just help authors write; it actively surfaces relevant, reusable content at the right moment.

At the same time, Patrick raises a practical counterpoint: reuse isn’t always easy to standardize, especially across organizations with complex or inconsistent information architectures. This is where “human-in-the-loop” systems remain essential—ensuring that automation supports, rather than overrides, sound content decisions.

This episode builds on the themes introduced in Episode 1, pushing further into how teams can balance AI innovation with the discipline required to maintain accuracy, consistency, and trust at scale.

This episode kicks off a special 11-part season of Components Live, recorded in person in Valencia in early February 2026. Across the series, Patrick Bosek (Heretto) and Noz Urbina (Urbina Consulting; OmnichannelX and Truth Collapse podcasts) sit down together to explore one big theme from every angle: how AI is reshaping structured content, content operations, and the role of technical communication.

In this opening episode, Patrick and Noz introduce their backgrounds, the origins of Components Live, and what listeners can expect from the rest of the season. From there, they dive straight into the current AI moment—and why, despite all the hype, it feels surprisingly familiar.

They unpack how AI has reignited long-standing pressures to eliminate specialized documentation and content teams, with approaches that resemble past trends like crowdsourced documentation and “just dump everything into a data lake.” The modern version? Throwing PDFs into an AI system and expecting magic.

But that’s only part of the story.

The conversation highlights a growing divide: while some organizations chase shortcuts, others are investing in structured content and rich context to properly “feed” AI systems—unlocking far more accurate, scalable, and valuable outcomes. This, they argue, is where technical communicators have a real opportunity to lead.

Patrick and Noz also challenge conventional thinking about the purpose of tech comm itself. Governance, structure, and single sources of truth aren’t the end goal—they’re only valuable if they consistently deliver meaningful answers that help users succeed and drive real business impact.

This episode sets the stage for the rest of the season, where each conversation builds on these ideas and explores what it really takes to operationalize content for an AI-driven future.

Patrick sits down with the industry experts that wrote the Content Operations book to talk about their chapters and how each one hopes to influence the structured content community. Whether you're just starting to explore content operations or ready to take yours to the next level, this podcast and this book is for you!

Get the book here

Kevin is an award-winning thought leader, digital industry enthusiast and author with more than 25 years of professional experience. He was a key contributor to creating MIT OpenCourseWare, grew one of the largest content strategy teams in the world at SapientNitro and has worked on digital strategy and content for dozens of global, Fortune 100 brands. In 2016 he launched AvenueCX with Rebecca Schneider. At AvenueCX he works with global brands to help them improve their brand, content, and customer experiences. He is an expert on content strategy for customer journey optimization, personalization, omnichannel, and enterprise content strategy. Kevin is author of Enterprise Content Strategy: A Project Guide and co-author of UX for Dummies. Kevin is also the chair of Content Strategy Alliance Best Practices initiative.

He started his career in the mid-1990s while a graduate student at Harvard University working for a Sabre Foundation, a non-profit book donation organization. His studies led him to Bosnia and Herzegovina, where he produced and significantly contributed to Nobel Laureate Physicians for Human Rights Watch website. He became a user experience lead at Sapient and later, a key architect of MITOpenCourseWare’s website where he contributed to publishing processes for an initiative that changed the face of global, online education. He went on to Molecular where he helped a global Fortune 10 brand redefine its external messaging and internal processes to support it. He built one of the of the strongest and largest content strategy teams in the world for SapientNitro. In June, 2015, Kevin left SapientNitro to focus on launching a company with Rebecca Schneider, AvenueCX. Kevin is committed to international human rights, especially those of refugees.

Connect with Kevin on LinkedIn

Visit his website

Patrick sits down with the industry experts that wrote the Content Operations book to talk about their chapters and how each one hopes to influence the structured content community. Whether you're just starting to explore content operations or ready to take yours to the next level, this podcast and this book is for you!

Get the book here

Kevin is an award-winning thought leader, digital industry enthusiast and author with more than 25 years of professional experience. He was a key contributor to creating MIT OpenCourseWare, grew one of the largest content strategy teams in the world at SapientNitro and has worked on digital strategy and content for dozens of global, Fortune 100 brands. In 2016 he launched AvenueCX with Rebecca Schneider. At AvenueCX he works with global brands to help them improve their brand, content, and customer experiences. He is an expert on content strategy for customer journey optimization, personalization, omnichannel, and enterprise content strategy. Kevin is author of Enterprise Content Strategy: A Project Guide and co-author of UX for Dummies. Kevin is also the chair of Content Strategy Alliance Best Practices initiative.

He started his career in the mid-1990s while a graduate student at Harvard University working for a Sabre Foundation, a non-profit book donation organization. His studies led him to Bosnia and Herzegovina, where he produced and significantly contributed to Nobel Laureate Physicians for Human Rights Watch website. He became a user experience lead at Sapient and later, a key architect of MITOpenCourseWare’s website where he contributed to publishing processes for an initiative that changed the face of global, online education. He went on to Molecular where he helped a global Fortune 10 brand redefine its external messaging and internal processes to support it. He built one of the of the strongest and largest content strategy teams in the world for SapientNitro. In June, 2015, Kevin left SapientNitro to focus on launching a company with Rebecca Schneider, AvenueCX. Kevin is committed to international human rights, especially those of refugees.

Connect with Kevin on LinkedIn

Visit his website