As Founding Product Designer in an engineer-led startup, I championed user-centered design by transforming passive live captioning into an interactive AI second-screen ecosystem, solving cognitive overload for trilingual government summit attendees.
AI
B2B + SAAS + START UP
FOUNDING PRODUCT DESIGNER
UX + STRATEGY
2023
CPII AI Meeting Assistant
Designing Real-Time AI Transcription for High-Stakes Multilingual Events
Adopted by Hong Kong’s largest broadcaster
with 3.4M+ listeners.
Featured • 2025 Policy Address
CPII Meeting Assistant enhanced the Hong Kong government’s 2025 Policy Address broadcast.
AI model for navigating the chaos of trilingual “code-mixing”
Hong Kong’s linguistic landscape is one of the most complex in the world. Professionals weave Cantonese, English, and Mandarin into single sentences—a 'code-mixing' challenge that breaks standard AI models. The CPII Meeting Assistant is engineered to bridge this gap. Designed specifically for this multilingual reality, it ensures accuracy where it matters most: at critical government summits and high-level ceremonial events.
CONTEXT
Journalists & Broadcasters
Professionals covering high-stakes government policy addresses who need to capture precise quotes in real-time without errors.
The Public
Viewers of major ceremonial events (e.g., Government Policy Address) who struggle to follow complex, trilingual speeches in real-time.
Workflow Fragmentation in Live Journalism
PROBLEM + REQUIREMENTS
The core problems we set out to solve was workflow fragmentation: the fractured experience of journalists juggling recorders, notepads, and translation apps while trying to stay present in a fast-moving event. Stop to transcribe a quote, and you miss the next sentence. Switch to translate, and you lose your place entirely.
We wanted to create a space where capturing, understanding, and synthesizing could happen simultaneously, without breaking flow.
Input
Live code-mixed audio (Cantonese/English/Mandarin)
Processing
Live Stream: real-time transcription + translation
Context: rolling AI summaries for instant catch-up
Chat: bounded chatbot for fact-checking
Output
Synthesis: automated post-event report, note
When I first joined, the product focused on providing real-time transcription and translation as live subtitles during events. However, AI latency and hardware constraints limited scalability. Through contextual inquiries and user interviews, I helped pivot our strategy from generic subtitles to solving a critical workflow problem for journalists covering multilingual events.
Product Evolution
Early product: event subtitles
The product focused on live subtitles during events when I first joined the early project.
Post-event summary
Pivoted product direction to target journalists, introducing post-event summary.
The event workspace
Integrate capturing and synthesizing into a scalable and adaptive workspace.
The “Stream-to-Synthesis” Mental Model
The mental model of the CPII Meeting Assistant was built around the journalist’s cognitive workflow during and after event: transforming a chaotic live stream into structured intelligence:
Augmented Input: Transforming fleeting audio into navigable, real-time text.
Active Processing: Empowering users to interrogate the data via Chat capture context without losing the live thread.
Structured Output: Crystallizing fragmented insights into verified reports and audio clips.
By grounding the design in this Input → Processing → Output flow, we gave users a stable anchor within the high-velocity environment, keeping complex AI interactions digestible and intuitive.
SOLUTION
To eliminate the "tool -switching fatigue" of live reporting, I designed a Dynamic Panel System where consumption and verification coexist. The interface anchors the Live Feed as the persistent core, while the Intelligence Layer (Chat & Summary) scales fluidly alongside it. This allows journalists to interrogate data and fact-check in real-time without ever obscuring the context of the stage.
Standard
The default layout with a balanced view of capturing inputs and synthesizing.
Transcription & Translation
Optimized for concentrating on the event content with the real-time navigable text.
Input + Note
Ideal for synthesizing and documenting the real-time summary onto notes.
Dynamic Panel Structure • During Event
Dynamic Panel Structure • After Event
Post-event, the platform transitions from Capture to Analysis mode. In this state, the Bounded AI Chat becomes a verification engine for journalists to interrogate specific details, while the automated Meeting Report handles the heavy lifting of structural synthesis.
Standard
The default layout with a balanced view of inputs and synthesizing.
Processing through Chat
Optimized for referencing transcription and synthesizing the event content.
Notes & Meeting Report
Automated post-event synthesis via AI Meeting Reports, consolidating insights from the live transcription and chat.
Output Panel
The transformation space where raw event inputs become outputs. Users can take notes, organize insights, and package their synthesis into shareable work.
Chat Panel
The chat panel remains central to the post-meeting experience, while shrinking during live events to serve as a lightweight tool for quickly checking event content.
Input Panel
This is the real-time transcription and translation of the event that serves as the foundation of the user experience, providing the information source for both the chat panel and post-meeting report.
