ROLES
UX designer
Project driver
TEAM
Cansu Aksu, Developer
Akanksha Grag, UX design
Heather Tompson, Content design
Timo Gasda, Squad lead
Tim Aeling-Bohmert, UX research
Deliverables
Embedded Files
Design and define Generative AI chat experience
From mid 2024, I led the projects to define and re-design the design system guidelines/toolsets for generative AI chat experience. The goal is to serve all AWS genAI related interfaces, including Amazon Q, Amazon Bedrock, etc.
Generative AI chat is a conversation between a user and a generative AI assistant.
Generative AI revolutionised the technology landscape in 2023, making waves across the field with its widespread popularity. Amazon Web Services has embraced this momentum by introducing innovative services, products, and tools powered by generative AI.
As part of the core design system team, I crafted guidelines that empower this competitive journey for multiple products, with a focus on maintaining the highest standards through an established design system, and aligning with product strategy.
The challenge
How might we
create a consistent and scalable generative AI chat experience guidelines with toolsets
for AWS product builders?
Ahead yet Behind
The design system strives to stay ahead, yet often finds itself lagging behind product releases. Despite early involvement, published releases can drift out of alignment. Individual product team doesn't care consistency, scalability, and adaptability.
Then who cares?
We do.
Known yet Potential
Generative AI is evolving rapidly, becoming familiar and widely adopted in a short span of time. Yet, it remains a field rich with untapped opportunities for growth and exploration. The existing system needs to be transformative and scalable to support such dynamic nature.
But how to?
Data-driven.
Approach and process
Deep dive into the existing use cases,
to understand the problem, gaps, teams and product plan.
Flexible feature/API
The features and APIs are designed with delicated analysis, strong opinions, but also adaptable to different user needs or use cases.
Modular component
Independent, reusable units that can be combined to create more complex generative AI interfaces, enabling flexibility to support scenarios beyond chat and easier maintenance.
Pattern guidelines
A set of standardized UX design concepts and building blocks that ensure consistency, usability, and efficiency across a system or interface.
Example demo
A demonstration of a working & accessible generative AI chat that showcases how features, components, from generative AI chat design pattern functions in practice.
Delivery the highest bar but not with over-refinement.
Ownership is the key.
Generative AI chat bubble with transparent background
A set of standardized UX design concepts and building blocks that ensure consistency, usability, and efficiency across a system or interface.
Earn trust with stakeholders by keeping decision logs, extensive feature plans, and clear prioritisation.
Team alignment and consensus is critical.
Visual cues in chat bubbles preference study
A set of standardized UX design concepts and building blocks that ensure consistency, usability, and efficiency across a system or interface.
Deliverables
2 components,
1 holistic generative AI chat pattern,
1 chat demo, all within 6 months.
avatar
chat bubbles
generative AI chat pattern
generative AI chat demo
UX guidelines
Distinguish between message authors
It’s important to provide visual affordance that helps users distinguish between authors of messages involved in a conversation. Avatars in chat bubbles help distinguish between messages sent by the user and generative AI by offering a different visual representation for the author of each message.
Maintain the flow of a conversation
Conversations can be exchange of multiple messages between a user and generative AI. Use support prompts to display suggested prompts from generative AI. This will help keep the conversation going and make the conversation more engaging.
Earn trust with users
List the sources of content, or cite the sources inline of the generative AI response. This enhances credibility and allows users to verify the information. Allow users to provide feedback on generative AI responses and use the feedback to improve the responses produced by generative AI moving forward.
Provide transparency
Users may feel uncertain or lose confidence during a generative chat if they’re unaware of the system's processing status, especially when a generative AI response takes time or encounters an error. Display error and loading states to keep users informed about the generative AI's activity and help set clear expectations.
Set user expectations around generative AI usage
Communicate the overall role of AI and risks involved with its usage in accordance by referencing any AI policies that are relevant to your product.
Learning
Keep pushing.
The goal is to serve AWS genAI related interfaces, including Amazon Q, Amazon Bedrock, etc
serve for a better holistic generative AI chat experience.
Page updated
Google Sites
Report abuse