Lina Dong’s
Product Design
Portfolio.

01 / AGENTIC WORKFLOWS

Designing Control for a Multi-Agent AI Workflow

Let AI configure key video-generation parameters while keeping users in control.

• Intent-driven configurationAI agents automatically configure key video-generation parameters based on user intent.
• Clear interaction statesEditable and locked states are visually differentiated, so users always know when they can intervene.
• Visible progressExplicit system states such as “Thinking…” make progress visible during long-running generation.
• A window for interventionA short adjustment window lets users override AI decisions without interrupting the generation flow.

02 / MULTI-AGENT COLLABORATION

Role-Based Multi-Agent Workflow

Turn waiting into observable progress.

• Specialized responsibilitiesSpecialized agents take ownership of planning, scriptwriting, storyboarding, animation, and editing.
• A conversational activity streamInstead of hiding long-running AI work behind a loading screen, intermediate outputs are surfaced through a conversational activity stream.
• A continuous sense of progressThis makes the generation process understandable and gives users a continuous sense of progress.

Autoflow redesign~30% → ~60%Video completion after the redesign

03 / PROACTIVE GUIDANCE

Capability Discovery Through Proactive Suggestions

Help users discover what they can create at the moment they need inspiration.

• Contextual starting pointsSurface contextual prompt starters as users explore the workspace, enabling one-click entry into creation flows.
• Discover through examplesUse example prompts to reveal what the product can create—including longer-form stories—without requiring users to understand the full feature set first.
• Lightweight guidanceOffer lightweight inspiration at the point of need, reducing onboarding friction without interrupting the main workflow.

04 / CREATION TEMPLATES

Capability Discovery Through Scenario Templates

Map common user intents to ready-to-use creation setups.

• Ready-to-use setupsScenario-based templates map common user intents to ready-to-use creation setups.
• Less prompt-writing effortThey reduce the effort of prompt writing while showing users the range of outcomes the product can generate.
• Different goals, one interaction modelDifferent templates encode different creation goals, enabling diverse outputs through a consistent interaction model.

06 / MULTIMODAL CREATION

Multimodal Input: One Creation Flow, Multiple Input Types

Bring different source materials into a unified generation workflow.

• Flexible input methodsSupport text, audio, video, files, links, and direct recording within the same creation flow.
• A unified workflowBring different input types into a unified generation workflow, reducing context switching between tools and modes.
• Start from the sourceLet users choose the input method that best matches their source material and storytelling intent.

08 / PRECISE IMAGE EDITING

Region-Based AI Image Editing

Combine AI capabilities with precise user control.

• Define the regionLet users paint a precise region to define what AI should modify while preserving the rest of the image.
• A consistent editing patternMap different editing intents to the appropriate AI capability within one consistent interaction pattern.
• Precise controlThis combines model capability with precise user control, reducing unintended changes to the image.

09 / INTERNATIONALIZATION

Right-to-Left (RTL) & Cultural Adaptation

Adapt the product to language conventions and cultural context.

• Right-to-left interactionAdapt navigation, alignment, and content flow for right-to-left languages.
• Language-aware outputValidate LLM-generated content against language-specific conventions rather than relying on direct translation alone.
• Cultural representationExtend character and visual presets to better reflect regional and cultural contexts.
• Sensitive visual generationIntroduce safeguards for culturally or religiously sensitive visual generation.

10 / INTERNATIONALIZATION

Multilingual Subtitle System

Maintain readability across writing systems and bilingual content.

• Language-specific typographyDefine language-specific typography and subtitle presets to maintain readability across different writing systems.
• Bilingual contentSupport bilingual subtitle layouts for multilingual content.
• Emphasis and readabilityProvide optional animation and word-level highlighting for emphasis and readability.
• A reusable asset libraryStructure subtitle assets as a reusable library, creating a scalable foundation for localization without interrupting the core workflow.

11 / INTERNATIONALIZATION

Voiceover & Background Music

Make localized audio options easy to discover and compare.

• Scannable voice presetsOrganize voice presets by language, accent, tone, and persona, making localized narration options easy to scan and compare.
• Connected audio controlsKeep voiceover and audio controls within the same creation environment to reduce context switching.
• Room to scaleDesign the asset model to scale across standard and premium options without changing the core interaction pattern.
• One audio workflowSupport audio preset selection within the same panel, enabling localized narration and soundtrack choices in one workflow.