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."
Dig deeper—ask the Rosenbot:
More Videos
"If you think about it, the theme is you — the 613 people from around the planet bringing so much energy and diverse experience."
Bria Alexander Louis RosenfeldWelcome
September 8, 2022
"The reality is bringing to market quickly at scale is expensive and time-consuming."
Mike OrenWhy Pharmaceutical's Research Model Should Replace Design Thinking
March 28, 2023
"We should think of AI as our ancestor encountered fire: managed well it’s a force for good, deployed recklessly it will burn us."
Jodi ForlizziDesign and AI innovation
June 5, 2024
"Working in design ops in 2023 can be overwhelming, so connecting with peers in the community mixer is more important than ever."
Bria AlexanderOpening Remarks
October 3, 2023
"People remember how you made them feel more than what you said."
Michael WeirMixed Methods and Behavioural Science (Videoconference)
May 26, 2023
"We created one-pagers — lightweight, skimmable documents — to help people from all areas quickly understand research insights."
Molly FargotsteinMultipurpose Communication & UX Research Marketing (Videoconference)
September 12, 2019
"Emotions are not universal at all; emotions and behaviors are constructed by the culture and society where they come from."
Verónica Urzúa Jorge MontielThe B-side of the Research Impact
March 12, 2021
"He looked at me with a blank stare because we didn’t have a shared context."
Husani OakleyTheme Two Intro
June 6, 2023
"You can publish your design from Sketch directly into the cloud and get it running as a web app in minutes."
George Abraham Stefan IvanovDesign Systems To-Go: Reimagining Developer Handoff, and Introducing App Builder (Part 2)
October 1, 2021
