tcworld China 2026 Program

Expand All +

  • May 21


  • As AI reshapes the landscape of technical writing, the issue of “factual hallucinations” in large language models (LLMs)—such as fabricated content, misattribution, and over-editing—has become a key barrier to their scalable application in high-accuracy scenarios.

    This presentation proposes a new role paradigm for technical writers evolving into “Model Context Engineers.” Rather than simply writing text, this role involves systematically constructing, optimizing, and managing the trusted context that models rely on for generation.

    This presentation provides an in-depth analysis of the underlying causes of hallucinations in technical documentation generation and defines the competency model and methodology for this new role. It introduces a three-tiered “Knowledge-Generation-Validation” anti-hallucination framework, detailing how to systematically build, optimize, and manage the input context for models, along with a feedback mechanism to create a closed-loop approach for mitigating hallucinations.

    AI, Automation & the Future of Content
    Software Documentation

  • In 2023, the data storage field launched the intelligent Q&A application, Storage AI Assistant Xiao Hai 1.0. By 2024, through the construction of an auto-updating data foundation, a next-generation Q&A technical framework, and Data Flywheel solutions, the team achieved fully automated corpus governance and reached an 85% accuracy rate for storage-specific user knowledge queries.

    In 2025, the focus shifted toward integrating user research with actual operational workflows. By conducting precision operations across products, content, and user segments based on the user journey, the project achieved an 88% coverage rate among core target users and a 25% increase in user activity.

    lntormation Development, Information Journey & Content Operations

  • Technical documentation is undergoing a seismic shift from static publishing to dynamic, intelligent assembly. While Generative AI has promised to revolutionize support, many implementations fail because they lack awareness of the user’s specific environment, role, or system state. This session explores how the Model Context Protocol (MCP) and context-aware design principles are bridging this gap, enabling a new generation of AI agents that do not just summarize text but actively resolve user problems based on real-time system data.

    The speaker examines the limitations of current Retrieval-Augmented Generation (RAG) approaches and introduces the concept of the Context Gap. Attendees discover how to transition from writing flat documentation to architecting dynamic content systems that integrate with live user context. The presentation details practical strategies for structuring metadata and taxonomy, ensuring that AI agents can retrieve and assemble the correct information for a specific user's configuration.

    Participants leave with a clear understanding of the emerging technical requirements for AI-ready content. The session provides a roadmap for evolving from traditional technical writing to content architecture, equipping professionals to lead their organizations in building adaptive, personalized, and system-integrated information experiences.

    AI, Automation & the Future of Content

  • Technical communication is evolving faster than ever. AI-driven workflows, immersive user experiences, and globally connected teams are redefining the boundaries of our profession every single day. But which future skills truly determine who will thrive in this dynamic field? And how do developments in Germany compare to global trends?

    In this article, we take a look beyond the obvious — exploring the skills, mindsets, and technologies that will shape the future of technical communication. Ready to break some boundaries?

    Education and Career Development

  • When addressing the dissemination challenges of complex technical concepts, traditional video formats often face two limitations: either being confined to dry abstract theories or reduced to fragmented technical demonstrations. This presentation advocates treating science communication video creation as a "design process for complex cognitive problems," with its core lying in establishing "dual pillars": first, transforming nonlinear knowledge systems into "structured narratives" that align with cognitive principles; second, integrating diverse media technologies into "systematic multimodal expressions" that serve narrative objectives.
    UX, UI & Product Content

  • In response to the digital transformation trend, technical documentation management urgently requires upgrades, with common pain points including low governance efficiency, compliance challenges in global expansion, and subpar user experience. This presentation highlights Inovance Technology's practical solutions, detailing actionable approaches to address these pain points through digital means, offering reusable insights for technical documentation professionals.
    lntormation Development, Information Journey & Content Operations

  • Against the backdrop of internationalization, products intended for overseas markets commonly face three major challenges: long and complex support paths, high learning costs, and significant language barriers. As a critical component of the product, documentation encounters similar issues. User research shows that overseas users rely more heavily on documentation than domestic users, and the quality of documentation directly influences customer satisfaction with both the product and the brand.

    Therefore, overseas documentation must go beyond accuracy and basic usability by improving readability and translatability, while establishing solid multilingual support. High-quality documentation experiences can better meet overseas user needs, support products in international markets, and enhance overall brand satisfaction.

    In this presentation, we will demonstrate how information designers at Inovance break through global business challenges using a complete, practice-proven methodology—from user research to closed-loop validation. The practice includes differentiated design based on BUTP analysis, concept development, implementation, usability testing, and the establishment of a long-term feedback and iteration mechanism. This provides peers with a validated pathway for improving documentation quality, evolving from “ensuring accuracy” to “optimizing user experience.”

    lntormation Development, Information Journey & Content Operations

  • In multi-agent application development, traditional approaches that rely on text files (such as .md or .txt) to aggregate skills, commands, and interaction logic are often constrained by model limitations in quantization and parsing. This can lead to character loss or execution errors.

    In this presentation, I will present a recently explored writing engineering approach: storing agent skills, commands, and interaction logic in structured databases, and driving agent interactions through database queries and operations. This approach enables a low-cost, highly stable execution environment. It ensures skill integrity and traceability, improves model robustness in complex task execution, and provides a scalable, engineering-oriented path for large-scale agent-based writing applications.

    AI, Automation & the Future of Content
    Software Documentation

  • 1. Establishing an AI-driven knowledge flywheel system: Connecting the full lifecycle of user insights, knowledge creation, knowledge accumulation, and scenario-based application to address broken links in traditional knowledge management.

    2. Standardizing the knowledge flywheel process: Defining standardized workflows for knowledge demand management, classification, and grading to ensure systematic accumulation of knowledge assets.

    3. Developing an AI-assisted tool platform: Leveraging AI-powered intelligent search to overcome timeliness limitations in knowledge management and enable automated circulation of knowledge assets.

    4. Scenario-based closed-loop management: Building a repeatable knowledge management model through cross-department collaboration and scenario-driven operations.

    lntormation Development, Information Journey & Content Operations
    Software Documentation

  • May 22


  • This presentation focuses on lifecycle-based management of technical documentation, covering the complete workflow from concept analysis and content planning to authoring, multi-round reviews, testing and validation, and final release. Drawing on real-world content domain development scenarios, the presentation systematically explores how AI can be applied at each stage, along with practical insights into implementation.

    The presentation also defines a structured human-AI collaboration model: AI takes on repetitive and rule-based tasks, allowing human experts to concentrate on value-based decision-making, ensuring technical accuracy, and improving user experience. Through practical case studies, the presentation demonstrates how AI can improve both the efficiency and quality of documentation production, supporting the evolution of technical communication toward more intelligent, standardized, and efficient practices.

    AI, Automation & the Future of Content

  • 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.
    AI, Automation & the Future of Content

  • 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.

    AI, Automation & the Future of Content

  • 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."

    AI, Automation & the Future of Content

  • 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.

    AI, Automation & the Future of Content

  • Human-factor errors are among the most common causes of accidents in technical and industrial environments. Unclear documentation often plays a key role. This workshop explores how Simplified Technical English (ASD-STE100) can help reduce misinterpretation and support safer, more reliable task execution. Through a mix of theory and hands-on exercises, participants will learn how to identify linguistic risk factors in safety instructions and procedures, and how to rewrite them for clarity, compliance, and usability. Using real examples, the session highlights how applying STE writing rules not only improves readability and translation consistency but also supports human performance and operational safety. By the end of the workshop, participants will understand how clear language can actively mitigate human-factor risks and enhance safety communication in maintenance, operations, and training contexts.
    lntormation Development, Information Journey & Content Operations

  • The presentation will demonstrate how to establish an end-to-end digital validation process through deep integration of CMS (Content Management System) and OA (Office Automation) systems. Key components include business requirement analysis, system architecture design, test environment consistency verification, and process deviation management. It will also showcase the development of a standardized validation solution database, bilingual translation of core functionalities, and the final quality review approval for deployment.
    Regulation, Standards & Compliance for Exported Products

  • AI is dramatically expanding the external world: more information, faster analysis, more options. Yet a counterintuitive outcome is emerging: why is decision-making becoming harder — and scarier — with AI?

    When AI can present multiple “seemingly reasonable” answers at once, traditional decision-making approaches that rely on external analysis, data, and models begin to break down. External systems can no longer make the real trade-offs for us. This signals a critical shift: the rise of AI is moving decision-making from “looking outward for answers” back to “looking inward for judgment.” In other words, AI is not the adversary of decision-making — it is finally returning the ultimate responsibility of choice back to the human. When AI optimizes the external dimension to its limit, it pushes us to evolve our decision-making role: from being analysts of external information and environments to becoming Chief Decision Officers aligned with our inner values, purpose, and meaning.

    What does a Chief Decision Officer do? When options approach infinity and efficiency is high, what truly determines outcomes is no longer how much information we possess, but clarity on:
    What are you choosing for?
    Which direction are you willing to pay the price for?
    Behind your hesitation — is it rational weighing, or internal avoidance?

    This topic focuses on the real bottlenecks decision-makers face in the AI era, exploring why decision difficulty is shifting from the technical level to the human level — cognition, psychology, and identity — and introduces the perspective of Purpose-Driven Decision-Making. It helps audiences understand: when AI perfects the external dimension, what truly cannot be avoided is the upgrade of human internal decision-making capability. Decision-making must return to a “whole person” to complete the final judgment. It is not just about external information — it is about integrated human judgment in complex environments.

    What the audience will take away is not more tools or models, but a clearer decision-making lens: how to make the critical trade-offs that only a “human” can make — even with AI’s support.

    Education and Career Development

  • The rise of generative AI is fundamentally redefining the boundaries and value of content strategy. While the traditional "plan → create → distribute → manage" content loop remains a useful framework, its core has undergone profound changes: shifting from "document creation" to building an "intelligent content ecosystem" and moving from serving "human readers" to accommodating both "machine understanding and invocation." This isn't merely an addition to existing content strategies; it represents a paradigm-level transformation.

    This session explores the construction of an Intelligent Content Ecosystem, where knowledge continuously gains value through human-AI collaboration. It highlights the value leap for content teams—transitioning from information communicators to strategic decision-support partners. For practitioners, mastering this new logic means evolving from executors into architects of enterprise knowledge infrastructure.

    Content Strategy and Governance

  • Ecodesign aims to make products more resource-efficient and reduce their environmental impact. Legal requirements for ecodesign have been established in the European single market for two decades. However, European Regulation 2024/1781 on ecodesign for sustainable products has significantly expanded the framework for ecodesign, introducing comprehensive information requirements and the so-called ‘digital product passport’. How will the Regulation be applicable on a product-specific basis, and what challenges will this pose for products and those responsible for technical communication?
    Regulation, Standards & Compliance for Exported Products

  • With the rise of AI, can technical writing naturally achieve 10x or even 100x efficiency gains? The answer is no—multiple challenges still constrain the effective use of AI. Today, technical documentation management in large enterprises commonly faces three major pain points: misalignment between R&D and documentation leading to version chaos, where operations teams often use old manuals to operate new equipment; static documents that fail to meet the needs of different roles, resulting in low information retrieval efficiency; and high collaboration costs across the full lifecycle, with repetitive work accounting for over 60%, trapping technical writers in low-efficiency internal competition.

    Based on real-world projects, this session presents a human–AI collaborative practice that builds a documentation development model centered on intelligent information blocks. The approach achieves a 60% reduction in business process complexity and supports a flatter organizational structure, offering a benchmark “living documentation” practice that intelligently bridges the gap from content to action.

    AI, Automation & the Future of Content

  • Engineering teams struggle to balance documentation quality with development velocity. Manual documentation processes create bottlenecks, while outdated content leads to knowledge gaps and increased support burden. This presentation explores a practical approach: developing an AI agent that integrates directly into existing engineering workflows.

    The speaker shares firsthand experience building and deploying an AI agent that operates within the software development lifecycle. The presentation covers the complete development journey from concept to production-ready system, demonstrating how an AI agent connects with version control, responds to code changes, and produces consistent output without disrupting established team processes.

    Attendees learn the technical foundations of agent development including API integration with large language models, event-driven architecture design, and CI/CD pipeline automation using GitHub Actions. The talk addresses critical implementation challenges such as authentication handling, error recovery, output quality control, and managing edge cases.

    The presentation emphasizes practical integration patterns that allow a documentation AI agent to complement rather than complicate engineering workflows. The speaker discusses how to identify appropriate automation opportunities, set realistic expectations, and measure agent effectiveness.

    Participants gain actionable knowledge for evaluating, building, and deploying AI agents within their own engineering organizations.

    AI, Automation & the Future of Content

  • In fast-paced, iterative product development, content designers are often limited to "copy polishing" after interfaces are finalized. However, high-quality content experiences are driven not only by precise wording, but by clear logic and well-designed interactions.

    As key contributors to user experience, conducting DUX (Design & User Experience) evaluations before development begins is an effective way to optimize interaction flows and reduce users' cognitive load. This approach improves product usability while significantly reducing the need for extensive downstream documentation.

    This 90-minute hands-on workshop guides participants through a systematic analysis of product interfaces. We will explore how to transcend surface-level editing to reach the core of interaction logic, learning to use content strategy as a driver for design decisions. Through professional assessment frameworks, we help teams transform complex products into intuitive, seamless experiences.

    Target Audience
    •Content Designers: Break free from the "final polishing" role and move toward strategy
    •Information Architects: Focus on optimizing interaction logic and user cognitive paths
    •Technical Writers: Integrate UX thinking and explore career expansion from documentation to experience
    •Product Managers: Introduce early content evaluation to reduce trial-and-error costs and enhance product experience

    Workshop Objectives
    •Redefine roles: Enable content designers to become core contributors to early-stage experience design
    •Master early evaluation methods: Learn and apply the DUX evaluation framework to identify design pain points
    •Content-driven design: Explore how content strategy can serve as a strong lever in design decision-making
    •Improve product quality: Create more intuitive and user-friendly products through systematic analysis

    90-Minute Hands-on Practice
    Participants will work through a simulated product interface and learn to:
    •Apply heuristic evaluations to identify common usability issues
    •Validate from the user perspective by simulating real usage scenarios to uncover interaction barriers
    •Apply accessibility principles to ensure inclusive and accessible design
    Together, we will explore how to move beyond simple text optimization, uncover the deeper value of content in interaction design, and learn how to translate complex interactions into smooth and efficient user experiences.

    Expected Outcomes
    •Gain a practical, content-driven UX evaluation toolkit
    •Develop a deeper understanding of product interaction logic
    •Independently or collaboratively conduct DUX evaluations and provide forward-looking design recommendations
    •Effectively reduce later-stage iteration costs and documentation maintenance effort

    UX, UI & Product Content