# From reactive systems to proactive intelligence — Jessie Pahng — session 2026-08-28T02:30:00.000Z → 2026-08-28T03:00:00.000Z _469 transcript lines · 84 slides_ ## Transcript Thank you. We're right on time, Peter. So won't have time for questions. But thank you for that. That was fantastic. Thank you. There was a cartoon that I saw yesterday, the day before, where an autonomous car was had been pulled over by an autonomous police car, and the police person, like the officer was standing next to the driver of the or the driver of the, passenger car saying your car know why my car pulled you over? There's another quote from sort of years ago that a machine can never be held responsible for making a bad decision and so we should not allow machines to make decisions without humans, overseeing that choice. And I think what Peter articulated there very very nicely, was the importance of our role in that decision making process. Alright. We good? Yes? Yes. Awesome. Alright. Our next speaker Jesse, is gonna talk to us about how we shift from designing for reaction towards designing proactivity in our systems. Please join me in welcoming Jesse to the stage. Thank you. Is my oh, I can hear myself. Thank you. Just a quick question. I hear a lot of people streaming like from United States Yeah. I don't know how many are you about to offend The United Yeah. Yeah. I'm There may be a consequences. I wanna say hi first. I traveled a little bit of distance, to come here and I've been really expecting, I didn't know what to expect but, I've been enjoying very much and you guys are so nice. I So a few things I wanna talk about and share with you today, and actually, listening to what Peter had to say, it seems my talk is has a little bit of connection to that as well. My talk will totally support what Iainapita shared with us. I spent my career solving one problem. Making complex technology easier for people to use. So in recent years, I've been working on enterprise platform across cloud and data infrastructure, security, compliance, data intelligence, and air powered observability. And, over the years, across all these platforms, and I'm sure you we've all noticed is technology has become more capable and sophisticated vastly, but the user experience hasn't necessarily become simpler. So let me show you what the complexity can feel like. An alert comes in, something changes, and performance drops all of a sudden 40%. And the dashboard lights up like a Christmas tree, and we start looking through all the signals. And years ago, what a company had done is that, oh, there's a lot of signals. We've got to help the users. And what do we do? Design more dashboards. And we trace the problem of cluster systems to figure out really what happened and why. So we eventually find the answer, what we might have taken hours getting there, So let me show you what the com what the complexity can look like for the user. Right? Users are trying to really figure out mapping their project and really just going into the timeline and then look at all different logs, metrics, and try to correlate and really figure out, okay. So who owns this one? How important is it for me? Does it affect my data? Do I need to connect and collaborate with other cross teams? Right? So that's what really the takes a long time for the user to figure out in the technologies have been there, and it takes just a millisecond to bring all this data but it takes a long time for people to really understand what is going on because we still have to connect the dots ourselves. So what if the system could help us connect those dots? So the evolution that's been going on very recently, and it's rapidly increased and expediting, is now AI can help prioritize what matters, bring together all the context, and explain what might have happened, and guide us on what to investigate next. So we can solve the problem faster. Right? And that's incredibly powerful, and this is actually happening now So as you can see and it, actually this is really not a critique as as to whether it's a good interface or not. But you can, this is also mocked, you know, using quality just to make it clear. But there's this all like a trend over time, and there is all the data on the table underneath of it, And as you can see, you've, tried to trace the problem over time. Anything that you hover over, the rows on the in the table with the highlight as well, you click and you can drill down into, learning more about who owns it and what happened and why and etcetera. Right? So I there's been evolution. There's been, new companies like popping up probably about maybe nineteen years ago in The United States. Really focusing on mapping the data because data quality is a big problem for, larger corporations, So the metrics that are coming out right now is actually AI is making the context all together and it's helping people and company understand the root cause and do the analysis of that. And identify, all the anomalies. So that is very helpful. Right? You know, if there's some information is missing and there's conflict, AI can bubble that up. But now that's creating even more problem because enterprise companies are doing this really fast right now. So the technologies are not fully integrated. So think about having wrapper. Right? Wrapping on one side, wrapper on one side. Let's say, like that kind of like a check bot lookalike right panel like sliding out, you can also enter information. So is that really integrated? Probably not because this is rapidly happening. What that means is that users are not trusting what they're looking at. And users not trusting because when there is a very unique incident that's a complex, then what they're doing is that they are copying what they're seeing and they can confirm. So there's a huge trust issue. And also, AI can automate but then, the information that coming out is pretty generalized. So users are not really trusting, what AI is giving them either. So does it really save time? Yes and no? Not really. Does it solve problem? One side? But that may be creating problem on the other side. So not by having this evolution through, the older industry in enterprise platform arena, How does a system really know what matters to the user? Systems have their own logic. There are assets, rules, policies, events, incidents, and relationships between them. So think about use cases such as, you connect the pipe and migrate all the data, all those assets, you apply the rules. But if those assets buy violate policies, they will trigger events. And altogether, it will create incidents and all those thoughts and relationship will show in the lineage. So that deductive structure and if that reasoning is what how the systems are built in the back end. Right? So But that's not how people think. So if something happens that we are thinking, what just happened? What's affected? Is it important? Do I need to coordinate with other teams who owns this? Do I need to fix it? What should I do? Did I fix it? So the mental model between systems and human are vastly different Systems are built that way because and again, it's for the hardware and it's a limitation about the hardware what software can do. And also debugging also needs a specific very linear structure. Right? But still there is a gap between what systems are made to do and how human think and that gap creates complexity, for the user. So that's why we have been doing user research, usability testing, to understand how people think so we can make the experience more intuitive, even when the technology underneath is complex. And that used to take time. But very valuable But now, AIs is dramatically compressing the cycle. Designers can explore faster. Engineers can build faster. Teams can ship faster, and I really love that. So probably everybody, also experienced this. Right? We wanted to see something really quick that we use AI to show us. Super fast. And I go, I like that. Mhmm. Yeah. That looks pretty nice. And I keep exploring. But there is another side to the speed. So I gave two AI tools the same prompt. Combine observability and lineage. To make the experience more intuitive. I thought, this look good? Very fast, but looks so polished. And I was very impressed. But was my assumption right? Does putting everything together make the experience more intuitive. Or more complex. AI can make an idea look really polished and convincing very quickly. And it doesn't always challenge the direction we give it either. Right? So if our assumption is wrong, we can go in the wrong direction. Very far, very quickly. Polished doesn't mean right. So I think about it this way. AI can analyze large quantity of data identify patterns, and synthesize information It also helps us move really fast, and explore tons of ideas. But we still have to decide actually what makes sense to the user. So the question is, what if if we are wrong, then what happens? In a large enterprise platform, one workflow One simple workflow can affect navigation, permission, terminology, other products, in thousands of users. Something can work really well in one place but create problems. Somewhere else. So if something is easy to undo, explore quickly. But if consequences are high, slow down, and validate. Why? Because enterprise companies are constantly adding new capabilities and scaling their systems. We are integrating platforms, adding products, and introducing new AI capabilities and agents all very very quickly. And each one brings each one logic workflows, assumptions, and altogether they can create a fragmented experience. That's why understanding how people think becomes even more important. Because we need to bring all these pieces together. Into an experience that makes sense to the user. The technology can and will become more complex underneath But user experience shouldn't. So the question is, how do we use AI to move faster without losing what matters? I think about it in three parts. First, the foundation. So this is our understanding about the user and the problem. And this shouldn't change every time we use AI. Then we give a constraints and requirements to work within, then AI can explore very quickly. Ask AI to challenge the thinking. What assumptions do we make? And ask AI to tell you what it does know and most importantly, was still needs to be validated. And, we can actually put this whole framework directly into the prompt. So, designers if you want one thing, you can take back to your team tomorrow, take this, Good prompt isn't about writing more, It's about making the right thing explicit. Give the AI specific context that it needs for the task. That helps the AI to stay focused, more faster, and actually use a few tokens. Yeah. I know, token anxiety is a real And, try, you know, work with engineering or design technologies to work with design engineers. So that you guys can connect the systems altogether In that way, you can only reference to that specific context right, to make the AI faster. So it doesn't read everything, it doesn't get confused, it helps you to move faster, But, this is still doesn't guarantee a correct design. But it gives us much better starting point for x exploration. AI makes the designers faster. And leaders who should be able to move fast with them. Set a clear framework stay close to what's going on, Give designers more ownership help them make good decisions, and get involved where you matter most. Resolving conflicts, influencing partners, making major decisions, and reviewing critical end to end experiences That allows your team to move faster without lowering the quality bar. And that's how design quality scales with execution speed. We started with a simple gap Systems are built around how technology works, People experience them through how they think. Complexity comes from that gap. And air is not going to make that gap disappear but it can help us bridge it faster. I can analyze huge quantity of data, identify patterns, synthesize information, that's all very helpful. But we still have to understand the user Define what good looks like and evaluate whether what we are creating actually makes the experience better. AI gives us leverage. Design give it direction, As our platforms grow, we have an opportunity to make the experience more cohesive, more intuitive, and easier to use. Rather than simply adding more complexity. Scale the experience not the complexity. And keep the experience human. Thank you. Thank you, Jesse. Thank you. If you want to come this way. Yes. So bring your laptop. Do does anyone have questions for Jesse while we I checked online and there were none online, so we clear there. You might get an early mark. Awesome. Thank you, Jesse. I might have answered all the questions. Already. Yeah, yeah, yeah, it was it was good. Thank you. Thanks. Okay. Yes. Sorry. Say that again. Post that in the chat. So that you can see it. 14782 refers to. Does that number mean anything to anybody? No reason why it really should. But that's the number of, gambling ads after after these new reforms have come through, that's the number of gambling ads children will be able to see per year. 14782 only. Woo hoo. Beautiful thing, three per hour between 5AM and 08:30PM day in, day out, ends up with 14,782 ads. The beautiful part about technology is that we can target those ads to the user, so those will be almost 15,000 highly targeted ads geared towards the individual with no age limit. So if they're in front of a TV, they get access to the ads. And I love our democracy. I really do. It's a beautiful thing. Jesse was going to offend the Americans, and didn't. Oh, you did? I don't know why. But anyway, I'm gonna say that because I will do by the end of the day. But anyway, we've we've touched on a topic around forcing people to do unnecessary I is going to delve into, in detail framework around how we can actually quantify that extra load Please join me from the University of Newcastle in welcoming Ben and Cordelia to the stage. Come on up. Okay. Thank you for the the good introduction there. So I I might just start with I I guess this is a metaphor or a mechanism to explain some of what we're talking about today. So this is probably a familiar scene to to most of you. So you're, you know, you're on your way home from work. What's Friday today? Maybe you're on the way home from a conference. It's a it's been a busy day, a busy week, and there's a bit there's a bit going on. There's a bit happening in the scene. So you might there there's headlights everywhere. You know, there's really bright things that are darting back and forth. Again, been a long day and just wanting to get home. So you have the radio playing. So, no, that that's a nice thing to do. It can be a bit boring driving home. It's a bit monotonous. You've been you've been that way a bunch of times, so it's, you know, it's nice to have some some music playing. The headlights are still there. You know, you're steering, operating the pedals, hopefully, if you're driving correctly, but there there's a bit going on. It starts to rain. So it does that annoying thing where you're just trying to get somewhere. And inevitably, you know, it starts pouring down. So you have the rain coming down. It's pretty heavy. So the the wipers are doing the whole wiping thing. The headlights are still darting back and forth, cars coming through across streets. The radio's still going, and hopefully, still doing the steering and pedaling things that you can actually make your way home. The GPS is speaking. So you you're a like today. So you're not you're you're taking a bit of a different route maybe and you're not not quite sure how to get back. So the GPS is going. It's it's doing that thing where it pauses and stops the music when it's saying, okay, we'll turn right here, go left there. So on and so forth. Still raining. The rain hasn't really stopped. The wipers are still going. Headlights are still there, and you're hopefully still steering and pedaling. So Traffic's pretty heavy, so everyone it was a very popular conference. Everyone was trying to get home at the same time. But it's still raining. The headlights thing's still happening. The radio's still playing, and the GPS is still nattering away. And then a message arrives. It's that thing when you're on your way home on a Friday, and it's your it's your boss telling you you forgot you forgot to thing. It's a report or a spreadsheet or something that you that you haven't quite finished up. So you sort of glance over to the the the information panel on your on your car. And, yeah, you sort of see what the message is. Pause is the music. It pauses the GPS. But it's still raining. The headlights are still there, so on and so forth. So this leads to a question. So you you need to concentrate on your driving. So what what would you do in this scenario to allow you to better concentrate on on your driving? Any ideas? The radio? Okay. So let me get this clicker working. Here we go. So you turn off the radio. Surprise to to these folk over here. So you make the world quieter, but that that doesn't really make sense in some ways doesn't it? So it's it's a fascinating phenomenon that we we choose to turn off the radio. So in that scene, we had what do we have? The traffic, the rain, the steering pedally thing, so on and so forth. There was there was a lot going on, but but as humans, we choose to remove something from working memory. So there's lots of things we could choose to remove. We can't we can't really stop the rain or the traffic I guess we could stop steering, or manipulating the pedals. That that that would be bad. The radio seems pretty easy. So switching off the radio is is maybe the no brainer in that scenario. But this is this is something that we all innately do, and I think something that most of us or folks who drive experience all the time. You know, there's sort of a wild thing happening. And you'll switch down the radio. And that's that's us intuitively reducing the number of items in work memory, and that's what Cordelia and I are talking about today, this idea of cognitive load theory, which relates to working memory, and how we we as good designers hopefully design around that and make experiences that conform to the ideals cognitive load. So this is the concept of the ideal or the idea that the brain has limits. And that interfaces compete for cognition. And so this is where ## Slides ### 00:00:38 # Proactive Intelligence ### How to move faster with AI without losing sight of how users think Joeske Pahng [Dark background with light, sparkling particles] ### 00:00:58 # Proactive Intelligence ## How to move faster with AI without losing sight of how users think Jessie Pahang ### 00:01:19 # Proactive Intelligence How to move faster with AI without losing sight of how users think Jessie Pahng ### 00:01:24 # Proactive Intelligence How to move faster with AI without losing sight of how users think Jessie Pahng ### 00:01:45 # From Reactive Systems to Proactive Intelligence How to move faster with AI without losing sight of how users think Jessie Pahng [Abstract background with blue and white dots forming a wave pattern] ### 00:02:06 # From Reactive Systems to Proactive Intelligence How to move faster with AI without losing sight of how users think Jessie Pahng [Abstract background with glowing particles and lines on a dark blue field] ### 00:02:26 # From Reactive Systems to Proactive Intelligence How to move faster with AI without losing sight of how users think Jessie Pahng [Abstract background with swirling blue and white dots on a dark field] ### 00:02:47 # From Reactive Systems to Proactive Intelligence How to move faster with AI without losing sight of how users think Jessie Pahng [Abstract background with glowing particles on a dark blue field] ### 00:03:08 # From Reactive Systems to Proactive Intelligence How to move faster with AI without losing sight of how users think Jessie Pahng [Abstract background of scattered light points on a dark blue field] ### 00:03:26 # From Reactive Systems to Proactive Intelligence How to move faster with AI without losing sight of how users think Jessie Pahng [Abstract background with glowing blue dots and lines] ### 00:03:27 # From Reactive Systems to Proactive Intelligence How to move faster with AI without losing sight of how users think Jessie Pahng [Abstract background with blue and white light particles] ### 00:04:15 ### -40% drop Monitor complex dashboard Manually trace problems [Line graph showing a significant drop from positive to negative values] [Dashboard with multiple small charts: a bar chart showing positive and negative values, a line graph, and a single bar chart] [Diagram showing a dotted, winding path connecting several red pin markers, illustrating manual tracing] ### 00:04:39 ### Interface example: Datadog Live Search / Traces [Screenshot of the Datadog Live Search and Traces interface, displaying a search bar with filters and a table of service traces including timestamps, service names, resources, durations, HTTP methods, and status codes.] ### 00:05:02 ### Interface example: Datadog Live Search / Traces [Screenshot of the Datadog Live Search / Traces interface, displaying graphs for requests, errors, and latency, alongside a detailed filtering sidebar] ### 00:05:25 # Datadog Live Search / Traces Interface [Screenshot of a Datadog interface showing live search for traces, with bar charts for requests and errors, a line graph for latency, and a detailed table of individual traces with filtering options.] ### 00:05:56 ### Severe Latency and Timeouts on Primary Checkout API [Screenshot of a monitoring dashboard showing a graph of incidents by function and a detailed view of an alert for severe latency and timeouts on a primary checkout API, including an API response time graph.] ### 00:06:18 ### Severe Latency and Timeouts on Primary Checkout API [Line graph showing incidents by function over time] [Line graph showing API response time over time, with a red line indicating a threshold] [List of alerts with status, severity, and condition] ### 00:06:41 ### Severe Latency and Timeouts on Primary Checkout API [Screenshot of a monitoring dashboard showing a line graph of incidents by function, a list of active incidents, and a detailed pop-up window for a "Severe Latency and Timeouts" incident, including a line graph of API response time with a critical spike and recommended actions.] ### 00:07:04 # Severe Latency and Timeouts on Primary Checkout API [Screenshot of an application monitoring dashboard with a line graph of incidents by function and a detailed alert pop-up for "Severe Latency and Timeouts on Primary Checkout API" showing an API response time graph.] ### 00:07:26 ### Severe Latency and Timeouts on Primary Checkout API [Screenshot of an application dashboard displaying a list of alerts and a detailed panel for a specific alert titled "Severe Latency and Timeouts on Primary Checkout API", which includes two line graphs showing "Incidents by function" and "API response time over time".] ### 00:07:50 ### Severe Latency and Timeouts on Primary Checkout API [Screenshot of a software dashboard showing an alert list and a detailed alert view] [Line graph titled "Incidents by function"] [Line graph titled "API response time over time" showing a performance drop] ### 00:08:12 ### Severe Latency and Timeouts on Primary Checkout API [Screenshot of a monitoring dashboard showing incident alerts and API response time graphs] ### 00:08:27 ### Screenshot of a monitoring dashboard Severe Latency and Timeouts on Primary Checkout API [Line graph showing incidents by function over time] [Table of alerts with status, severity, and condition] [Line graph showing API response time over time, highlighting a period of high latency] ### 00:08:48 ### Severe Latency and Timeouts on Primary Checkout API [Screenshot of a monitoring dashboard displaying incident alerts, a graph of incidents by function, and a detailed view of an API latency alert with a response time graph] ### 00:09:11 Systems are structured around implementation logic. ### 00:09:25 Systems are structured around implementation logic. ### 00:09:46 Systems are structured around implementation logic. ### 00:10:07 Systems are structured around implementation logic. ### 00:10:26 Systems are structured around implementation logic. ### 00:10:47 Systems are structured around implementation logic. ### 00:11:09 Systems are structured around implementation logic. Users think about how their work gets done. The gap between **the system model** and **the user's mental model** is where **complexity lives**. ### 00:11:26 ### Before AI: Longer, sequential process - Research - Synthesize - Explore - Prototype - Build [Diagram showing a linear, sequential process with five steps: Research, Synthesize, Explore, Prototype, and Build] ### 00:11:29 ### Before AI: Longer, sequential process - Research - Synthesize - Explore - Prototype - Build [Diagram showing a linear, sequential process with five steps: Research, Synthesize, Explore, Prototype, and Build] ### 00:11:50 # AI reduces the cost of execution. [Diagram comparing two process flows: "Before AI" shows a longer, sequential process with distinct steps (Research, Synthesize, Explore, Prototype, Build). "With AI" shows a compressed and overlapping process for the same steps, resulting in "2x faster cycles."] ### 00:12:11 # AI reduces the cost of execution. - **Before AI**: Longer, sequential process - Research - Synthesize - Explore - Prototype - Build - **With AI**: Compressed and overlapping process - Research - Synthesize - Explore - Prototype - Build - **2x faster cycles** [Diagram comparing two process flows: one showing sequential, non-overlapping steps labeled "Before AI", and another showing overlapping steps labeled "With AI" resulting in "2x faster cycles"] ### 00:12:55 # Customer 360 [Screenshot of a data observability dashboard showing metrics for availability, response time, error rate, freshness, data quality, and volume; a data lineage diagram; a list of incidents under "What to work on"; and a bar chart of backlog by age.] ### 00:13:18 # It also reduces the cost of executing the wrong assumption. [Screenshot of a data observability dashboard showing metrics for "Customer 360", incident tracking, and event logs.] ### 00:13:24 # It also reduces the cost of executing the wrong assumption. [Screenshot of a data observability dashboard showing metrics for "Customer 360", incident tracking, and event logs.] ### 00:13:45 - AI for analytics ### 00:14:07 - AI for analytics - AI for start-up approach ### 00:14:26 - AI for analytics - AI for start-up approach - AI for scaling enterprise systems ### 00:14:46 - AI for analytics - AI for start-up approach - AI for scaling enterprise systems ### 00:15:07 Enterprise companies keep adding capabilities to move faster. ### 00:15:26 # Enterprise companies keep adding capabilities to move faster. What the enterprise looks like underneath [Illustration of three overlapping application windows displaying various UI components like charts, graphs, and data entry fields] ### 00:15:48 # Enterprise companies keep adding capabilities to move faster. What the enterprise looks like underneath What the user should experience [Three overlapping abstract web interface diagrams showing complex data and UI elements] [A simplified abstract web interface diagram showing a bar chart and a green checkmark] ### 00:16:09 ### Enterprise companies keep adding capabilities to move faster. [Three overlapping browser windows showing complex, detailed dashboards and data visualizations, labeled "What the enterprise looks like underneath"] [A single, clean browser window showing a simple bar chart with a green checkmark, labeled "What the user should experience"] ### 00:16:27 # Enterprise companies keep adding capabilities to move faster. [Illustration showing two complex application interfaces labeled "What the enterprise looks like underneath" contrasted with a single, simpler application interface with a bar chart and a green checkmark, labeled "What the user should experience"] ### 00:16:29 ### Enterprise companies keep adding capabilities to move faster. What the enterprise looks like underneath What the user should experience [Illustration showing three complex, overlapping browser windows with various charts and UI elements, contrasted with a single, clean browser window displaying a simple bar chart and a green checkmark.] ### 00:16:50 ### Designing with AI framework - **Foundation** - User mental model - Problem - Desired outcome - Experience principles - **Context + Task + Expectation** - Use case - Relevant context - Constraints - Expected outcome [Two columns of text, each with a heading and a bulleted list. The "Foundation" column has an icon of a person, and the "Context + Task + Expectation" column has an icon of curly braces.] ### 00:17:11 # Designing with AI framework ### Foundation - User mental model - Problem - Desired outcome - Experience principles ### Context + Task + Expectation - Use case - Relevant context - Constraints - Expected outcome ### Evaluate + Iterate - Explore alternatives - Challenge assumptions - Check against foundation - Validate critical assumptions ### 00:17:26 # Designing with AI framework ### Foundation - User mental model - Problem - Desired outcome - Experience principles ### Context + Task + Expectation - Use case - Relevant context - Constraints - Expected outcome ### Evaluate + Iterate - Explore alternatives - Challenge assumptions - Check against foundation - Validate critical assumptions ### 00:17:31 # Designing with AI framework ### Foundation - User mental model - Problem - Desired outcome - Experience principles ### Context + Task + Expectation - Use case - Relevant context - Constraints - Expected outcome ### Evaluate + Iterate - Explore alternatives - Challenge assumptions - Check against foundation - Validate critical assumptions ### 00:17:53 # Prompt structure ### Foundation - The user is: [Who] - They are trying to: [Goal] - The problem is: [Problem] - The desired outcome is: [Outcome] - Preserve these experience principles: [Principles] ### Context + Task + Expectation - The use case is: [Use case] - Relevant context: [Context] - Constraints: [Constraints] - Design System: Utilize existing [System Name] components, variants, and tokens - Constraints: [Constraints - e.g., platform, technical, accessibility] - Expected outcome: [Success Metric / outcome format] ### Explore - Generate 3 meaningfully different approaches. - Explain the reasoning and assumptions behind each. - Do not assume missing information is true. Flag what you don't know. ### Evaluate For each approach, tell me: - Does it support the user's mental model and goal? - What assumptions did you make? - What could create unnecessary complexity? - What should be validated with real users or data? ### 00:18:15 # Prompt structure ## Foundation - The user is: [Who] - They are trying to: [Goal] - The problem is: [Problem] - The desired outcome is: [Outcome] - Preserve these experience principles: [Principles] ## Context + Task + Expectation - The use case is: [Use case] - Relevant context: [Context] - Constraints: [Constraints] - Design System: Utilize existing [System Name] components, variants, and tokens - Constraints: [Constraints - e.g., platform, technical, accessibility] - Expected outcome: [Success Metric / outcome format] ## Explore - Generate 3 meaningfully different approaches. - Explain the reasoning and assumptions behind each. - Do not assume missing information is true. Flag what you don't know. ## Evaluate For each approach, tell me: - Does it support the user's mental model and goal? - What assumptions did you make? - What could create unnecessary complexity? - What should be validated with real users or data? ### 00:18:40 # Prompt structure ### Foundation - The user is: [Who] - They are trying to: [Goal] - The problem is: [Problem] - The desired outcome is: [Outcome] - Preserve these experience principles: [Principles] ### Context + Task + Expectation - The use case is: [Use case] - Relevant context: [Context] - Constraints: [Constraints] - Design System: Utilize existing [System Name] components, variants, and tokens - Constraints: [Constraints - e.g., platform, technical, accessibility] - Expected outcome: [Success Metric / outcome format] ### Explore - Generate 3 meaningfully different approaches. - Explain the reasoning and assumptions behind each. - Do not assume missing information is true. Flag what you don't know. ### Evaluate - For each approach, tell me: - Does it support the user's mental model and goal? - What assumptions did you make? - What could create unnecessary complexity? - What should be validated with real users or data? ### 00:19:04 [The slide is currently blank] ### 00:19:25 ### Without shared foundation - Every designer reconstructs context - → AI generates more - → Managers review more - → Engineering waits - → Design becomes the bottleneck ### With shared foundation - Validated knowledge is reusable - → AI receives targeted context - → Teams explore independently - → Manager review consequential decisions - → Quality scales with speed ### 00:19:27 ### Without shared foundation - Every designer reconstructs context - → AI generates more - → Managers review more - → Engineering waits - → Design becomes the bottleneck ### With shared foundation - Validated knowledge is reusable - → AI receives targeted context - → Teams explore independently - → Manager review consequential decisions - → Quality scales with speed ### 00:19:49 ### Without shared foundation - Every designer reconstructs context - → AI generates more - → Managers review more - → Engineering waits - → Design becomes the bottleneck ### With shared foundation - Validated knowledge is reusable - → AI receives targeted context - → Teams explore independently - → Manager review consequential decisions - → Quality scales with speed ### 00:20:10 ### Design quality has to scale with execution speed. - **Without shared foundation** - Every designer reconstructs context - → AI generates more - → Managers review more - → Engineering waits - → Design becomes the bottleneck - **With shared foundation** - Validated knowledge is reusable - → AI receives targeted context - → Teams explore independently - → Manager review consequential decisions - → Quality scales with speed ### 00:20:55 [Blank slide] ### 00:22:27 attendees [QR code linking to https://aka.ms/react-conf-2023-attendees] ### 00:23:13 [Screenshot of a car's dashboard and infotainment system showing navigation and speed] ### 00:23:26 ### Car Dashboard UI [Screenshot of a car's infotainment system displaying navigation to Newcastle and a digital instrument cluster showing 67 km/h] ### 00:23:51 ### Screenshot of an in-car navigation and instrument display [Screenshot of a car's dashboard, showing the infotainment screen with a navigation map to Newcastle and the instrument cluster with a speed of 67 km/h] ### 00:24:15 ### Screenshot of an in-car navigation system [Screenshot of a car's infotainment system displaying a navigation map with a route to Newcastle, alongside a view of the car's speedometer showing 67 km/h] ### 00:24:42 [Screenshot of an in-car infotainment system displaying navigation and a car dashboard] ### 00:25:07 # Driving to UX Australia - **Road sign:** Pacific Hwy, North Sydney, Newcastle, A1, UX Australia - **Car navigation screen:** 2.1 km to Pacific Hwy, Newcastle; ETA 10:15, 24 min - **Car dashboard:** 15°C, 67 km/h [View from inside a car at night, driving in the rain, showing a wet windshield, city lights, a road sign, and the car's navigation system and dashboard.] ### 00:25:28 Headlights everywhere [View from inside a car at night, looking out at a wet road with many car headlights and city lights. A green road sign indicates "Pacific Hwy", "North ### 00:25:29 Headlights everywhere [Night-time view from inside a car on a wet road, showing city lights, a road sign for "Pacific Hwy" and "UX Australia", and the car' ### 00:25:54 Headlights everywhere Radio is playing [Image of driving a car at night in the rain, with city lights and traffic visible, and a road sign for "Pacific Hwy North Sydney Newcastle" and "UX Australia". The car's infotainment system shows a map for "Pacific Hwy Newcastle".] ### 00:26:16 It's raining Headlights everywhere Radio is playing [Blurred image from inside a car driving at night in the rain, showing the dashboard and a road with many car headlights] ### 00:26:28 It's raining Headlights everywhere Radio is playing [Blurred image from inside a car at night, showing a rainy road with many car headlights and reflections, and the car's dashboard.] ### 00:26:52 - It's raining - Headlights everywhere - GPS is speaking - Radio is playing [Blurred image from inside a car at night, looking out at a rainy city street with many car headlights and city lights] ### 00:27:16 - It's raining - Headlights everywhere - Traffic is heavy - GPS is speaking - Radio is playing [Blurred image from inside a car at night, showing a steering wheel, dashboard, and a rainy, traffic-filled road ahead with many headlights] ### 00:27:24 - It's raining - Headlights everywhere - Traffic is heavy - GPS is speaking - Radio is playing [Blurred image from inside a car at night, showing a steering wheel, dashboard, and a rainy, traffic-filled road ahead with many headlights] ### 00:27:48 - It's raining - Headlights everywhere - Traffic is heavy - A message arrives - GPS is speaking - Radio is playing [Blurred image from inside a car at night, looking out at heavy traffic with headlights, showing the steering wheel and dashboard] ### 00:28:09 ### You need to concentrate on driving, so what you would you do? - It's raining - Traffic is - GPS is speaking - Radio is playing [Blurred image from inside a car at night, showing the dashboard, a rainy road with traffic lights, and a road sign] ### 00:28:26 # Turn off the radio You make the world quieter [Blurred image of a car interior at night, showing a road, streetlights, and a car dashboard with text overlays like "It's raining", "Traffic", "GPS is speak", and "Radio is playing"] ### 00:28:47 # Turn off the radio You make the world quieter [Blurred image of a car interior at night, showing a dashboard and a road ahead, with faint text overlays like "It's raining", "Traffic", "GPS is speak", "Radio is playing"] ### 00:29:09 # Turn off the radio You make the world quieter [Blurred image of a car interior at night with a road scene through the windshield, showing text overlays like "It's raining", "Traffic", "GPS is speak", and "Radio is playing"] ### 00:29:25 # Turn off the radio You make the world quieter - It's raining - Traffic - GPS is speak... - Radio is playing [Blurred image from inside a car at ### 00:29:30 # Turn off the radio You make the world quieter - It's raining - Traffic - GPS is speak... - Radio is playing [Blurred image from inside a car at ### 00:29:55 # The Brain Has Limits Interfaces compete for cognition [Nighttime aerial view of multiple highways with car light trails, converging and diverging]