Summary
This talk is a case presentation about using generative AI and graph languages to come up rapidly with complex enterprise designs. We are using a repository based enterprise architecture tool and EDGY, an open source visual language, to feed GPT4 with context-rich queries. The resulting maps and models are ... wrong. But they have proven to be inspiring or even triggering for conversations across a diverse stakeholder community, and shortcut our way to a set of correct and useful models that inform design decisions. Moreover they can highlight blind spots and interrelationships previously unknown and thereby enrich the design process with minimal effort. Takeaways Recognising blank page moments in complex challenges How to embed context and an ad hoc Training in an LLM prompt How to make generate a web of coherent maps such as Journey, JTBD, Organization, Process Maps that cover a complete design related to a given challenge How to use these maps and how not to use them when co-creating with others When to keep tackling the blank page yourself instead
Key Insights
-
•
Overcoming the blank page is a common challenge for designers and can be tackled using structured tools and AI.
-
•
User-centered design is crucial; starting from the customer's perspective helps in defining relevant tasks.
-
•
Understanding the complexity of enterprise environments is essential for effective design solutions.
-
•
AI should be viewed as an augmentation tool for designers, not a replacement.
-
•
Task mapping is key to transforming abstract ideas into actionable plans.
-
•
Collaboration between teams is necessary to break down silos in enterprises.
-
•
Using supportive design tools can help visualize complex systems and tasks more clearly.
-
•
Feedback loops from AI can encourage iterative improvement in design processes.
-
•
Structured graph language can clarify relationships within enterprise design.
-
•
Engaging with AI can produce surprising outcomes that inform and inspire further design efforts.
Notable Quotes
"We are often asked to come up with something useful very quickly, sometimes even before we do our research."
"Design starts from the customer, from the user; let’s go back to that experience we are designing for."
"Behind simple tasks, there’s often big complexity hiding; these are enterprise design challenges."
"If we don’t address the underlying systems, it can stifle our efforts."
"We have to deal with these complex social technical systems rather quickly."
"Enterprise design must navigate dark matter, which is often invisible in complex organizations."
"AI can augment our abilities, making us more efficient and not replace us."
"Every job or problem can be placed on a slider between AI and human capabilities."
"The wrong outcomes from AI can often lead to interesting discussions and insights."
"AI benefits from structured information; it thrives on context-driven data."
More Videos
"Creating a knowledge management system is crucial for tracking insights throughout the research process."
Christian RohrerResearch Operations at Scale
November 7, 2017
"When you collect information, we're doing in-depth interviews and recording what people say to understand their needs."
Kelly GotoEmotion Economy: Ethnography as Corporate Strategy
May 13, 2015
"The confidence gap can prevent qualified candidates from applying for positions that they could excel in."
Libby MaurerTreating Diversity & Inclusion in Hiring as a Design Problem
December 5, 2019
"What doesn't kill you will only make you stronger."
Maria GiudiceEmpowering change: Reigniting purpose, passion and impact in research
March 13, 2025
"We must shift from being rigid in our skillsets to having an open mindset for innovative applications."
Jemma Ahmed Robert Fabricant Sean McKay Llewyn Paine Kate Towsey Noah BondTheme Panel
March 11, 2025
"User experience is not just in the product; it's about the experience others have with your team."
Gretchen AndersonScaling the Human Center
June 8, 2017
"Human behavior is notoriously complex and needs to inform machine learning models."
Sohit KarolDesigning Delightful Listening Experiences: Mixed Methods Research in the Age of Machine Learning
March 31, 2020
"It was a painful but wonderful experience to evaluate our progress."
Benjamin RealMaturity Models: A Core Tool for Creating a DesignOps Strategy
October 1, 2021
"Throwing a bunch of smart people at a problem alone doesn’t typically result in a positive outcome."
Shawna Hein Kevin HoffmanCreate a Cohesive Civic Design Practice Across Agency, Vendors, and Contracts
November 17, 2022
