ConVEx 2026 • Featured Session
Tuesday, April 14, 2026
1:00 PM
Rob Hanna

The AI-Ready DITA Pipeline

Modeling, Metadata, and Machine Understanding

Learn how to evolve DITA models, taxonomies, metadata strategies, and Open Toolkit publishing streams to create cleaner, more structured, AI-ready content for retrieval, reasoning, and generation.

Why attend
Improve retrieval quality
See how content granularity and metadata affect retrieval accuracy and grounding.
Reduce hallucination risk
Learn how cleaner semantics and classification improve machine understanding.
Modernize your pipeline
Adapt your DITA and OT workflows for AI without abandoning core DITA principles.

Session overview

DITA for PDFs was never the end of the story

As generative AI becomes a core capability in enterprise knowledge delivery, the structure, semantics, and consistency of DITA content take on new importance. This session explores how the same discipline that powers great multichannel publishing can also supercharge AI retrieval, reasoning, and content generation.

What you’ll learn

Practical ways to make your DITA pipeline AI-ready

Granularity
Adjust topic and component structure to improve retrieval and contextual generation.
Semantic annotation
Use metadata and classification more intentionally to support machine understanding.
Taxonomy and metadata
Strengthen context, relationships, and classification structures for better AI behavior.
Open Toolkit outputs
Adapt publishing streams to produce cleaner corpora for RAG, fine-tuning, and agentic workflows.

Business impact

What an AI-ready DITA pipeline can improve

Accuracy
Improve retrieval precision and answer quality.
Hallucinations
Strengthen grounding and reduce ambiguity in AI output.
Reuse
Create cleaner, more valuable content assets across channels and systems.
AI readiness
Prepare your corpus for RAG, model tuning, and agentic workflows.

Who should attend

Built for teams managing structured content in an AI world

DITA teams
Information architects
Content strategists
CCMS leaders
Metadata and taxonomy specialists
Technical communication managers
Enterprise AI teams

Speaker

Rob Hanna

Precision Content

Rob Hanna has dedicated his professional life to improving outcomes for teams embarking on structured authoring projects. Over the past 30 years, he has worked with many large corporations on DITA and CCMS projects to bring their teams into structure and drive operational efficiencies.

He has taught metadata and taxonomies at the University of Toronto and private courses on structured authoring, DITA, and information architecture.

In 2013, Rob founded Precision Content in Toronto, Canada, to build a team of writers, developers, and information architects to continue his mission to raise the bar in technical communication.

Contact us

Want to keep the conversation going?

Interested in DITA, metadata, AI-ready content pipelines, structured intelligent content, or content transformation? Reach out and we’ll continue the conversation.