Designing for Generative AI

Intro

[internal_only]

Generative AI is the talk of the town. But what does it mean for the design of business applications? With this article, we want to give you an overview of where SAP’s generative AI strategy stands today, our approach to developing guidelines, patterns, and best practices, and how everyone can contribute.

SAP’s Generative AI Strategy

Generative AI and other emerging AI capabilities will have a significant impact on global businesses and society in the upcoming years. SAP has responded to the opportunities and risks of this huge technological innovation with a clear strategy for SAP Business AI. We’ve made it a priority to add business value by embedding relevant, reliable, and responsible AI across our entire portfolio. To dive deeper, see SAP’s Generative AI Strategy on the Artificial Intelligence at SAP page (Work Zone).

In September 2023, SAP also announced Joule, SAP’s generative AI-based copilot. Joule will be embedded throughout SAP’s cloud enterprise portfolio to deliver proactive and contextualized insights that span our entire solution portfolio and also integrate third-party sources. For questions about Joule, please refer to the SAP-internal FAQ document.

We envision this to transform the user experience of SAP solutions massively – so that you can define the desired business outcomes, and SAP systems generate insights and optimizations by connecting the relevant business knowledge and process data. We believe that generative AI can make businesses around the world more productive, more efficient and more resilient and has the potential to delight SAP’s end users in a totally new dimension so that they can achieve more and focus on what matters most.

Furthermore, we believe that … humans continue to play a key role in the decision and reasoning processes of enterprises. Therefore, we intentionally design our AI solutions to keep humans in the loop to carefully review and approve AI-generated information.

– Rahul Lodhe, Senior Director SAP Artificial Intelligence, 07/2023 in AIM
Check out interesting demos from product teams across SAP!
Open the Demos page in the AI workspace on Work Zone.

All guidelines for generative AI are based on our findings so far and provide initial ground rules for you to start with. The guidelines will evolve iteratively based on research, input from the community, and feedback from stakeholders.

We need you, fellow UX designers, to collaborate, exchange insights, and contribute to these evolving design guidelines. Together, we can stay at the forefront of this dynamic field and ensure that we deliver a unified AI experience for our customers and users across SAP’s portfolio.

Coming soon: Generative AI Design Patterns
For more details about upcoming patterns, check out the AI Patterns Backlog and join the AI Patterns Community.

[/internal_only][external_only]

Generative AI and other emerging AI capabilities will have a significant impact on global businesses and society in the upcoming years. SAP has responded to the opportunities and risks of this huge technological innovation with a clear strategy for SAP Business AI. We’ve made it a priority to add business value by embedding relevant, reliable, and responsible AI across our entire portfolio.

In September 2023, SAP also announced Joule, SAP’s generative AI-based co-pilot. Joule will be embedded throughout SAP’s cloud enterprise portfolio to deliver proactive and contextualized insights that span our entire solution portfolio and also integrate third-party sources.

We envision this to transform the user experience of SAP solutions massively – so that you can define the desired business outcomes, and SAP systems generate insights and optimizations by connecting the relevant business knowledge and process data. We believe that generative AI can make businesses around the world more productive, more efficient and more resilient and has the potential to delight SAP’s end users in a totally new dimension so that they can achieve more and focus on what matters most.

Furthermore, we believe that … humans continue to play a key role in the decision and reasoning processes of enterprises. Therefore, we intentionally design our AI solutions to keep humans in the loop to carefully review and approve AI-generated information.

– Rahul Lodhe, Senior Director SAP Artificial Intelligence, 07/2023 in AIM

We are releasing this early version of our generative AI design guidelines to share our discoveries early on with our broader SAP and UX community. The design guidelines in this section will evolve iteratively based on research, input from the community, and feedback from stakeholders.

Coming soon:

  • Designing Safety into Generative AI
  • Designing Sustainable Generative AI Experiences
  • Designing Effective AI Prompts

[/external_only][internal_only]

Design Guidelines for Generative AI

The UI and interaction design is a crucial element of SAP’s generative AI offering. How well we guide and empower users, surface the right information at the right time, and explain our AI results will ultimately determine whether or not users trust and embrace the capabilities of generative AI.

Our Approach

The content for the generative AI design guidelines is rooted in real use cases. All of our design concepts are being co-created and continuously improved in collaboration with SAP product teams and generative AI power users.

Creating best practices for user experiences fueled by generative AI will require extensive human-centered research and design to make it valuable and enjoyable for users. Getting started is the hard part – especially for a completely unique interaction model that’s still in its infancy. With this in mind, we’re taking the following approach to creating guidelines and patterns:

  • Talk to users to understand their needs
  • Develop an informed hypothesis
  • Learn, iterate, and improve as we go
In short: Strive for excellence through continuous improvement.

Guideline Scope

The generative AI design guidelines primarily focus on crafting the front-end user interface of our AI-enabled solutions. They provide a vital framework for designing a cohesive, intuitive, engaging, and trustworthy user experience across SAP products.

These guidelines, however, do not cover the design and development of foundational AI models, which demands a separate set of technical expertise.

Design is a team sport. In the table below you can see the current role of the AI Design Team in shaping SAP’s generative AI experiences (as of June 2023). This will also form the basis for our evolving guidelines.

Generative AI Design
AI Design Team Focus
Provide best practices for designing experiences with generative AI
Primary
Identify and design user-friendly interaction patterns together with product teams across SAP
Primary
Build foundational AI models and LLMs
N/A
Handle data quality and bias
N/A
Ensure data privacy and security
N/A
Create accessible, context-aware prompt patterns
Shared
Develop reliable and trustworthy AI systems
Shared
Adapt to evolving user needs and expectations
Primary
Comply with legal and ethical standards
N/A
N/A: Areas that fall outside the AI Design team’s current domain expertise and require specialized technical know-how. For all questions related to these topics, please make use of the central guidance and resources on the Artificial Intelligence at SAP page.

What to Expect

The goal of these guidelines is to enable designers to confidently create and innovate on generative AI experiences that are valuable, inclusive, and trustworthy for all SAP customers. To do this, we’re focusing on four main areas:

  1. Educating designers about generative AI: We’re creating a space where designers can learn quickly about generative AI and its endless possibilities.
  2. Showing off the best generative AI use cases: We’re creating and maintaining a library of the most mature UX designs for generative AI coming from SAP and beyond.
  3. Collaborating with product teams: As new generative AI projects are started, we’re rolling up our sleeves to work closely with SAP product teams to create UX guidance and patterns that everyone can benefit from.
  4. Keeping designers in the know: To make sure our designers are always one step ahead, we’re committed to keeping everyone updated on the latest innovations and disruptions in the world of generative AI.
Get your Jedi skills ready and join the force!

We’re excited and ready to see these new guidelines expand and evolve and we want to hear from YOU!

If you or your team are dabbling in generative AI, we want to know what you’re up to, what you’re learning, and how we can help share your insights with others. We’re all in this together, after all.

So, don’t be shy – share your feedback and needs with the AI Design Team and let’s make these generative AI design guidelines even better. We’re excited to journey with you into this new frontier of user experience design!

[/internal_only]


Design Guidelines for Generative AI

The UI and interaction design is a crucial element of SAP’s generative AI offering. How well we guide and empower users, surface the right information at the right time, and explain our AI results will ultimately determine whether or not users trust and embrace the capabilities of generative AI.

Our Approach

The content for the generative AI design guidelines is rooted in real use cases. All of our design concepts are being co-created and continuously improved in collaboration with SAP product teams and generative AI power users.

Creating best practices for user experiences fueled by generative AI will require extensive human-centered research and design to make it valuable and enjoyable for users. Getting started is the hard part – especially for a completely unique interaction model that’s still in its infancy. With this in mind, we’re taking the following approach to creating guidelines and patterns:

  • Talk to users to understand their needs
  • Develop an informed hypothesis
  • Learn, iterate, and improve as we go

The UI and interaction design is a crucial element of SAP’s generative AI offering. How well we guide and empower users, surface the right information at the right time, and explain our AI results will ultimately determine whether or not users trust and embrace the capabilities of generative AI.

Get Started!

Check out our first set of guidelines generative AI.

Find explanations for key generative AI terms in our AI design glossary and check out helpful AI design resources.

[internal_only]

Partner with us or share your feedback.

[/internal_only]

[external_only]

Contact the SAP AI Design Team.

[/external_only]