May 22

Large Language Models are meanwhile a standard-tool in technical documentation. But still, hallucinations occur and the content provided by the model is not fully reliable. This talk addresses, how and why hallucinations are generated by language models and what users can do, to reduce the amount of unreliable information.

Besides a good prompt, the design of context for the model becomes vital to achieve the results the user expects. No matter whether LLMs are used for research or generation of new content, the proper setting of the context will improve the quality of the model answers. Understanding how inputs lead to hallucinations and how the user input can be design to reduce the amount of false information improves the efficiency when using language models in the daily work-flow.

Living and working in Shanghai fundamentally changed how I understand content. I saw firsthand how documentation, UX copy, terminology, and compliance break down when content is created for one market and simply exported to another.

In this session, I’ll share practical lessons from designing and managing content across cultures and how those experiences shape the way I approach AI, automation, and content operations today. We’ll look at why global content succeeds when it’s treated as a system, not a set of documents, and how UX thinking, governance, and structured content make localization and compliance easier not harder.

Attendees will leave with clear, actionable ways to design content that scales globally, supports AI enabled workflows, and still works for real users in real markets.”

Despite the rapid iteration of high-tech products driven by LLMs, the methods for creating, maintaining, and consuming the accompanying documentation have struggled to keep pace. Traditional methods may improve efficiency to some extent, but when dealing with complex products, documentation professionals still need to deeply understand product technical details and vast documentation structures to accurately locate and modify content, leading to significant bottlenecks in documentation maintenance.

To address this challenge, we have developed an AI-powered multi-agent solution for technical documentation, leveraging the powerful text generation capabilities of LLMs, semantic search technologies through embedded models, and agents with proactive thinking and execution abilities. This solution addresses pain points in document synchronization, review, proofreading, and operational maintenance, pushing these processes toward automation and intelligence. As a result, documentation transitions from a passive, static asset to an “active” resource capable of self-reviewing and continuously evolving.

This presentation will introduce ZTE’s exploration and practice of integrating AI agents in documentation delivery. It will discuss how to build an AI agent system based on large language models, facilitating the transition of technical documentation from static knowledge to dynamic services. The presentation will focus on application scenarios such as intelligent Q&A, scenario-based content delivery, and automated knowledge maintenance. It demonstrates how the concept of “knowledge as a service” significantly improves document retrieval efficiency and operational support, providing practical insights for the industry’s shift toward intelligent documentation delivery.