KEYNOTE - Ronald Ashri (OpenDialog.ai): Designing Software that Acts: Agents beyond LLMs

While LLMs have renewed interest in autonomous software agents, current implementations often overlook decades of foundational research. The end result is that we keep re-discovering the same problems while we could be leaping ahead. The aim of this talk to to bridge this gap by examining how established agent theories and architectures can enhance today's LLM-driven applications.

Olaf Stelter (Mercedes-Benz AG): How AI could leverage the DevPortal customer journey

AI solutions might improve the customer facing parts of a developer portal, but could also be used for background optimization. This talk shows examples and ideas we work on for Mercedes-Benz Data.

Roy Derks (IBM): Effectively use AI Agents to Maintain Your Docs

This session explores how to integrate AI agents into your workflows to ensure consistency, automate updates, and reduce manual effort. Learn best practices for handling diverse data sources and see real examples of how I'm using AI to keep my developer-focused documentation accurate and up to date.

David Karlsson (kapa.ai): Docs accessibility, for robots

Ever wonder if the writing tips you've been using all along work just as well for AI? Spoiler: They do. In this talk, we'll take a behind-the-scenes look at how AI systems consume your docs and how clear technical writing can streamline that process.

Michael Iantosca (Avalara): Graph-Driven RAG AI Powered by DITA

Can generative AI benefit from structured content? What role play knowledge graphs in this? And what does all of that have to do with DITA? After they discovered the shortcomings of vector-based RAG, there is a buzz in the industry around knowledge graph-driven retrieval-augmented generation (Graph RAG). This session will put the question of whether and how DITA fits into that equation.

Jorge de Antonio, Anna Tsolakou (Amadeus): How LLMs are changing the way we build API specifications

In this session, we’ll share our journey of developing a chatbot powered by Large Language Models (LLMs) capable of customizing API specifications.

Walter Heck (Helixiora): Smarter Search: How RAG Pipelines Help Navigate Complex Documentation

In this session, we’ll dive into:
    •    How RAG pipelines work and why they’re a game-changer for documentation search
    •    Challenges of crawling technical documentation, from handling different formats (PDFs, wikis, APIs) to keeping content up-to-date and makign sense out of not-so-great documentation
    •    Lessons learned from implementing RAG in Lorelai, including indexing strategies, hallucination mitigation, and user-friendly search experiences

Tammy Lee (Culture Creates): Discoverability Is an Act of Agency: Rethinking Metadata as Cultural Infrastructure

We talk a lot about discoverability but we rarely talk about the infrastructure underneath it. This presentation will share a perspective from outside the traditional tech world, grounded in the cultural sector. I’ll outline how I see metadata as the hidden layer that shapes visibility and meaning online, why it matters, what we need to get right, and what to avoid if we want digital infrastructure that serves the public good.

Anthony Lusardi (liblab): Annotating API Specs with AI

This talk will present practical steps and tools to simplify and enhance the OpenAPI spec writing experience, resulting in more complete and accurate documentation.

KEYNOTE- Zdenek Nemec (Superface): APIs at the Verge of AI

There are new API consumers on the block: the AI agents. What does this mean for APIs and businesses? Will APIs stay as we know them? What about the API documentation and SDKs? Will there still be engineers manually developing and integrating APIs? 

Pooja Vijay Kumar, Aman Talwar (Autodesk): Specs Are Docs Now: Designing OpenAPI for Agentic Interfaces

I’ll share what it means to treat OpenAPI like user-facing documentation—from syntax choices to semantic intent—and how doing so unlocks new affordances for agentic AI.

Jessie Mongeon (Dfinity): Leveraging AI for Efficient Technical Documentation and Routine Maintenance

We’ll explore how AI can be used for managing technical documentation and streamlining routine maintenance tasks. Listeners will learn how to leverage AI to create and automate documentation workflows.

Stefan Mesquita (Deutsche Bank): From APIs to AI: How to Build an AI-Ready API Ecosystem

We’ll explore how to design an API ecosystem that supports AI-driven applications while ensuring performance, governance, and cost efficiency. We’ll cover best practices for structuring APIs to optimize data ingestion, enable AI agents to integrate seamlessly, and manage resource usage effectively. Attendees will gain insights into key design considerations that make APIs a strong foundation for AI—whether for training models or deploying intelligent agents.

Manny Silva (Skyflow): Self-Healing Docs: How Agents are Redefining the Docs Pipeline

You'll learn how embedding self-healing capabilities into your docs-as-code or CMS pipelines can dramatically reduce manual maintenance, enhance accuracy, and free technical writers to focus on creative, high-value tasks. We’ll share real-world case studies and practical strategies for implementing documentation systems that continuously verify and repair content, ensuring your API documentation and developer portals stay reliable and resilient to rapid product changes.

Selvaraaju Mururegsan (kovai.co): Producing AI-friendly content: Emerging best practices

We will cover some emerging best practices to write GenAI-friendly content. We will also discuss some learnings from interacting with some customers in Chatbot implementation with respect to content restructuring.

Elmer Thomas (Twilio): The Robots are coming for your job, and that's okay.

I’ll share how we decided which agents to build and how we made them more accessible to less-technical Twilions outside of our team. I’ll share some practical ways you can use agents in your own work to simplify your workflows and streamline your authoring process. Once we’ve covered the basics, we can share some ideas we have for taking these agents, and our docs, to the next level.

James Higginbotham (LaunchAny): AI-Assisted API Design and Documentation

AI promises to change how we work. Let's explore how to approach your API design and documentation efforts by leveraging AI assistance to guide us throughout the API delivery lifecycle. We will explore what is required to design and document an API effectively, how to leverage AI to accelerate the process, and keep our APIs prepared for both human and machine consumption.

Tom Johnson (Google): API quick reference diagrams: boosting comprehension for both human and machine users

As we turn to AI for more advanced documentation authoring, augmenting AI chats with API reference content improves the accuracy of the AI’s responses. Grounding your AI with your API reference basically uploads this intelligence into your AI chat sessions, giving your AI the right knowledge and context to address nearly any documentation scenario. Ultimately, these quick reference diagrams serve a dual role: improving the developer’s understanding of the API while also enhancing the reliability of the AI responses.

David Hou (MongoDB): Teaching Old Docs New Tricks: Practical AI applications for documentation teams

This session provides a pragmatic approach towards leveraging LLMs and AI tools in documentation teams. Though models have improved dramatically, they still complement rather than replace subject matter expertise. Though LLMs are now part of our audience, they reaffirm documentation best practices rather than redefine how we should write docs. This talk will discuss some of these misconceptions and explore practical ways that writers can use AI to drive productivity.