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
-
•
Designers often face a 'blank page' problem when thrown into complex enterprise domains without full context or research.
-
•
Edgy is a simplified open-source enterprise modeling language designed to bridge between customer tasks, enterprise architecture, and organization.
-
•
Enterprise systems contain hidden complexity and 'dark matter' like legacy systems, politics, and siloed teams that designers must navigate.
-
•
AI like GPT-4 can augment designers by generating initial task maps and models using curated enterprise repositories as context.
-
•
Using AI as a 'jester' can provoke conversation by providing wrong or unexpected models to stimulate stakeholder feedback.
-
•
The 'cyborg' mode combines AI output with domain-specific research and context to improve relevance and accuracy.
-
•
The 'matrix' mode uses AI to transform knowledge between different enterprise perspectives, e.g., from product portfolio to organizational capability maps.
-
•
AI is powerful at understanding raw data quickly, enabling knowledge transformation and diagram creation but is not yet perfect at layout or accuracy.
-
•
Feeding AI with relevant, enterprise-specific context is crucial to improve output quality and reduce reliance on generic internet knowledge.
-
•
The output of AI-assisted enterprise design is best seen as a collaborative starting point that helps overcome inertia and supports cross-disciplinary teamwork.
Notable Quotes
"We are facing the blank page and we have to come up with something else than a blank page before the meeting."
"Design starts from the customer, from the user. Let’s go back to that experience we are designing for."
"Enterprises are complex sociotechnical systems with a lot of hidden dark matter behind the scenes."
"AI is augmentation, not automation. It can make us more efficient but won’t replace us yet."
"We use our repository as context to the AI so it doesn’t just lean on its general internet knowledge."
"Sometimes AI’s wrong outputs are interesting because they provoke discussion and surface assumptions."
"There are three AI modes: the jester to provoke, the cyborg to integrate context, and the matrix to transform perspectives."
"AI is very good at understanding raw data and transforming it into diagrams or structured knowledge."
"The brand is basically the reflection of the enterprise identity in people’s experiences."
"Feeding the AI with relevant context vastly increases the quality of the models it produces."
Or choose a question:
More Videos
"Can you show me your process, not just your portfolio? That shows me your real design thinking."
Adam Cutler Karen Pascoe Ian Swinson Susan WorthmanDiscussion
June 8, 2016
"UX directors often feel like this poor person in the middle here getting pulled in all these directions."
Peter MerholzThe Trials and Tribulations of Directors of UX (Videoconference)
July 13, 2023
"Nobody knows who’s supposed to decide what around digital, and that’s the problem."
Lisa WelchmanCleaning Up Our Mess: Digital Governance for Designers
June 14, 2018
"Policy change is the backbone of effective climate strategies in urban areas."
Vincent BrathwaiteOpener: Past, Present, and Future—Closing the Racial Divide in Design Teams
October 22, 2020
"The squad model flopped for us after six months but created culture triads that stuck around."
Brenna FallonLearning Over Outcomes
October 24, 2019
"We are all experiencing a spatial collapse, a disruption of our mental models of how we navigate physical and virtual spaces."
Tricia WangSpatial Collapse: Designing for Emergent Culture
January 8, 2024
"Creating hypotheses from pain points with measurable success criteria helped prioritize which to pursue."
Edgar Anzaldua MorenoUsing Research to Determine Unique Value Proposition
March 11, 2021
"Service lines bridge the gaps between product lines through information flows to provide the right knowledge at the right time."
Designing Systems at Scale
November 7, 2018
"Decades worth of agricultural data had to be thrown out because they lacked control groups and statistical rigor."
Erin WeigelGet Your Whole Team Testing to Design for Impact
July 24, 2024
