Markdown source

Transcript: 500 people vibe-coded for 30 days. I was one of them. - Sanja Grbic, Automattic

Source Video

Local Cache

Transcript

Hi there. Welcome to my talk. My name is Hi there. Welcome to my talk. My name is Sanja and today I'm going to share with Sanja and today I'm going to share with Sanja and today I'm going to share with you an experiment we did at our company you an experiment we did at our company you an experiment we did at our company that's somewhat unusual and very that's somewhat unusual and very that's somewhat unusual and very exciting. exciting. exciting. It was a one-month initiative called It was a one-month initiative called It was a one-month initiative called radical speed month where two-person radical speed month where two-person radical speed month where two-person teams were given full autonomy to build teams were given full autonomy to build teams were given full autonomy to build and ship projects. I built three and ship projects. I built three and ship projects. I built three projects during this time. I will walk projects during this time. I will walk projects during this time. I will walk you through them and we'll talk about you through them and we'll talk about you through them and we'll talk about the outcomes and learnings for myself as the outcomes and learnings for myself as the outcomes and learnings for myself as a designer as well as the system-wide a designer as well as the system-wide a designer as well as the system-wide impact this experiment had. impact this experiment had. impact this experiment had. I'll tell you a little bit about I'll tell you a little bit about I'll tell you a little bit about Automattic first. We're the company Automattic first. We're the company Automattic first. We're the company behind several products in the WordPress behind several products in the WordPress behind several products in the WordPress ecosystem such as wordpress.com, ecosystem such as wordpress.com, ecosystem such as wordpress.com, Jetpack, WooCommerce, as well as many Jetpack, WooCommerce, as well as many Jetpack, WooCommerce, as well as many other brands like Tumblr, Beeper, and other brands like Tumblr, Beeper, and other brands like Tumblr, Beeper, and many more. many more. many more. We are around 1,400 people and we're We are around 1,400 people and we're We are around 1,400 people and we're fully distributed which is fully distributed which is fully distributed which is pretty interesting for also what what pretty interesting for also what what pretty interesting for also what what I'm about to show you. We're fully I'm about to show you. We're fully I'm about to show you. We're fully distributed distributed and asynchronous distributed distributed and asynchronous distributed distributed and asynchronous which means that most of our work, our which means that most of our work, our which means that most of our work, our thoughts, our concepts from the past thoughts, our concepts from the past thoughts, our concepts from the past couple of decades are very well couple of decades are very well couple of decades are very well documented. documented. documented. I'm a product designer and I've spent I'm a product designer and I've spent I'm a product designer and I've spent over a decade building software and over a decade building software and over a decade building software and watching how teams build software. I've watching how teams build software. I've watching how teams build software. I've worked for I've been at Automattic for 5 worked for I've been at Automattic for 5 worked for I've been at Automattic for 5 years now years now years now on the Jetpack design team and in the on the Jetpack design team and in the on the Jetpack design team and in the past I worked for several companies of past I worked for several companies of past I worked for several companies of different sizes, different different sizes, different different sizes, different types of products, and different team types of products, and different team types of products, and different team organiza- configurations. So after all organiza- configurations. So after all organiza- configurations. So after all these years these years these years I've not only accumulated experience in I've not only accumulated experience in I've not only accumulated experience in designing products, I also have a lot of designing products, I also have a lot of designing products, I also have a lot of insight into team dynamics and insight into team dynamics and insight into team dynamics and organizational structures within product organizational structures within product organizational structures within product teams. teams. teams. Over the years the the designer role has Over the years the the designer role has Over the years the the designer role has morphed and evolved a lot. We we had We morphed and evolved a lot. We we had We morphed and evolved a lot. We we had We still have all of these different types still have all of these different types still have all of these different types of of of of roles like web designers or UX of roles like web designers or UX of roles like web designers or UX designers or interaction or product designers or interaction or product designers or interaction or product designers. We've also used many designers. We've also used many designers. We've also used many different tools from the Adobe suite to different tools from the Adobe suite to different tools from the Adobe suite to Sketch to Figma Sketch to Figma Sketch to Figma and many many others in addition to and many many others in addition to and many many others in addition to those. And AI is a new tool. those. And AI is a new tool. those. And AI is a new tool. It is definitely not built just for It is definitely not built just for It is definitely not built just for designers. It's versatile so it can be designers. It's versatile so it can be designers. It's versatile so it can be used by many other used by many other used by many other um many different roles, but the um many different roles, but the um many different roles, but the expectation is is the same for everyone. expectation is is the same for everyone. expectation is is the same for everyone. It's that it will bring a speed. It's that it will bring a speed. It's that it will bring a speed. And of course, this is why companies are And of course, this is why companies are And of course, this is why companies are rushing to put it to use. But no matter rushing to put it to use. But no matter rushing to put it to use. But no matter what role uses AI, what role uses AI, what role uses AI, um this um this um this velocity is going to look very different velocity is going to look very different velocity is going to look very different in small teams like one to three people in small teams like one to three people in small teams like one to three people that are building new products. Let's that are building new products. Let's that are building new products. Let's say a zero to one product versus large say a zero to one product versus large say a zero to one product versus large organizations that might have built organizations that might have built organizations that might have built entire entire product ecosystems, that entire entire product ecosystems, that entire entire product ecosystems, that have software that's anywhere between 5 have software that's anywhere between 5 have software that's anywhere between 5 and 20 years old and that have uh more and 20 years old and that have uh more and 20 years old and that have uh more than a thousand or even thousands of than a thousand or even thousands of than a thousand or even thousands of people. Before I dive into the experiment, I Before I dive into the experiment, I will tell you a little bit about what will tell you a little bit about what will tell you a little bit about what preceded it in terms of how we use AI at preceded it in terms of how we use AI at preceded it in terms of how we use AI at Automattic. We were encouraged to use Automattic. We were encouraged to use Automattic. We were encouraged to use it, to learn it, and to experiment with it, to learn it, and to experiment with it, to learn it, and to experiment with AI from the very beginning. AI from the very beginning. AI from the very beginning. At first, we had access to tools and At first, we had access to tools and At first, we had access to tools and courses. courses. courses. Then the AI enablement Then the AI enablement Then the AI enablement was initiated where every single was initiated where every single was initiated where every single employee goes through a two-week course employee goes through a two-week course employee goes through a two-week course designed specifically for their role. designed specifically for their role. designed specifically for their role. This is completely immersive with This is completely immersive with This is completely immersive with lectures and and focused hands-on time. lectures and and focused hands-on time. lectures and and focused hands-on time. Very very helpful. Very very helpful. Very very helpful. And over time as AI coding tools got And over time as AI coding tools got And over time as AI coding tools got better, everyone was encouraged to get better, everyone was encouraged to get better, everyone was encouraged to get comfortable with contributing in code. comfortable with contributing in code. comfortable with contributing in code. And we can thank our systems and And we can thank our systems and And we can thank our systems and operations team for setting up fantastic operations team for setting up fantastic operations team for setting up fantastic security and processes as well as security and processes as well as security and processes as well as documentation that's good enough that a documentation that's good enough that a documentation that's good enough that a non-engineer such as myself can spin up non-engineer such as myself can spin up non-engineer such as myself can spin up a working development environment. And a working development environment. And a working development environment. And last but not least, an incredibly last but not least, an incredibly last but not least, an incredibly helpful tool that I that I use every day helpful tool that I that I use every day helpful tool that I that I use every day for research and planning is context AC. for research and planning is context AC. for research and planning is context AC. It's an MCP server that gives AI tools It's an MCP server that gives AI tools It's an MCP server that gives AI tools access to all of the knowledge and data access to all of the knowledge and data access to all of the knowledge and data that we have documented over the years that we have documented over the years that we have documented over the years that I previously mentioned. that I previously mentioned. that I previously mentioned. So back to the experiment. About 2 So back to the experiment. About 2 So back to the experiment. About 2 months ago, we kicked off this project. months ago, we kicked off this project. months ago, we kicked off this project. The instructions were to pause the The instructions were to pause the The instructions were to pause the roadmap work for 30 days, pair with a roadmap work for 30 days, pair with a roadmap work for 30 days, pair with a partner, and ship something real. We partner, and ship something real. We partner, and ship something real. We were welcome to use AI, though it wasn't were welcome to use AI, though it wasn't were welcome to use AI, though it wasn't a requirement. And of course, um a requirement. And of course, um a requirement. And of course, um we couldn't all do this at once. We had we couldn't all do this at once. We had we couldn't all do this at once. We had to do this in in stages, and we had to do this in in stages, and we had to do this in in stages, and we had about a third of the company about a third of the company about a third of the company participating in the first round. That's participating in the first round. That's participating in the first round. That's around 500 people around 500 people around 500 people that started around 794 projects in that started around 794 projects in that started around 794 projects in these 30 days. One lucky circumstance these 30 days. One lucky circumstance these 30 days. One lucky circumstance for me was that during this month, I was for me was that during this month, I was for me was that during this month, I was also participating in this 2-week also participating in this 2-week also participating in this 2-week in-person AI enablement course. So AI in-person AI enablement course. So AI in-person AI enablement course. So AI tools played a huge role in what I was tools played a huge role in what I was tools played a huge role in what I was able to deliver. able to deliver. able to deliver. Um and Um and Um and that's why I was building not one but that's why I was building not one but that's why I was building not one but three different projects. three different projects. three different projects. And when Radico Speedman started, And when Radico Speedman started, And when Radico Speedman started, uh uh uh I I had some knowledge of GitHub. I I I had some knowledge of GitHub. I I I had some knowledge of GitHub. I would review PRs. I had played around would review PRs. I had played around would review PRs. I had played around with cloud code. with cloud code. with cloud code. But I had never until then actually But I had never until then actually But I had never until then actually built and shipped something in code. And built and shipped something in code. And built and shipped something in code. And I mean I mean I mean at work. Like I've done a small hobby at work. Like I've done a small hobby at work. Like I've done a small hobby project here and there, but that's project here and there, but that's project here and there, but that's completely that was a completely completely that was a completely completely that was a completely different experience. Uh I'm going to different experience. Uh I'm going to different experience. Uh I'm going to share my personal journey of how my share my personal journey of how my share my personal journey of how my skills and process and collaboration skills and process and collaboration skills and process and collaboration style shifted over the over the course style shifted over the over the course style shifted over the over the course of the 30 days. of the 30 days. of the 30 days. And this will also give us insights into And this will also give us insights into And this will also give us insights into how this change can be promoted and how this change can be promoted and how this change can be promoted and implemented at the organizational level implemented at the organizational level implemented at the organizational level for large companies. for large companies. for large companies. So this is the story of the first So this is the story of the first So this is the story of the first project I worked on and my first project I worked on and my first project I worked on and my first contributions in code. As I mentioned at contributions in code. As I mentioned at contributions in code. As I mentioned at the time uh Radical Speed Month was the time uh Radical Speed Month was the time uh Radical Speed Month was starting, I was at the in-person A&E starting, I was at the in-person A&E starting, I was at the in-person A&E enablement training. And over there we enablement training. And over there we enablement training. And over there we did an as as part of the program we did did an as as part of the program we did did an as as part of the program we did an exercise where as a group of four we an exercise where as a group of four we an exercise where as a group of four we had uh had uh had uh 2 hours to build something together. 2 hours to build something together. 2 hours to build something together. We were two designers that aren't super We were two designers that aren't super We were two designers that aren't super comfortable in code, an engineer, and a comfortable in code, an engineer, and a comfortable in code, an engineer, and a product lead. And we decided to build product lead. And we decided to build product lead. And we decided to build this board game session manager. We had this board game session manager. We had this board game session manager. We had a board game evening planned that night. a board game evening planned that night. a board game evening planned that night. Uh so we wanted to create an app that's Uh so we wanted to create an app that's Uh so we wanted to create an app that's that's used to create, view, and join, that's used to create, view, and join, that's used to create, view, and join, and manage board game event sessions. Um and manage board game event sessions. Um and manage board game event sessions. Um you can see what that looked like. This you can see what that looked like. This you can see what that looked like. This is what we built in in 2 hours. We built is what we built in in 2 hours. We built is what we built in in 2 hours. We built an app um an app um an app um where where where people can start and stop uh uh a people can start and stop uh uh a people can start and stop uh uh a session, uh session, uh session, uh see what games and spots are available, see what games and spots are available, see what games and spots are available, and even chat with each other. And on and even chat with each other. And on and even chat with each other. And on top of that we chose this 16-bit style top of that we chose this 16-bit style top of that we chose this 16-bit style um illustration of our actual office um illustration of our actual office um illustration of our actual office that uh people found especially that uh people found especially that uh people found especially appealing. appealing. appealing. The most interesting thing about this The most interesting thing about this The most interesting thing about this project isn't what we built. It was how project isn't what we built. It was how project isn't what we built. It was how we worked together and leveled up we worked together and leveled up we worked together and leveled up together. together. together. Uh at the very beginning we agreed that Uh at the very beginning we agreed that Uh at the very beginning we agreed that we all want to uh contribute, and we we all want to uh contribute, and we we all want to uh contribute, and we were very lucky that the engineer that were very lucky that the engineer that were very lucky that the engineer that was uh in our group was really really was uh in our group was really really was uh in our group was really really great at setting us up for success. So great at setting us up for success. So great at setting us up for success. So she set up the project in GitHub, helped she set up the project in GitHub, helped she set up the project in GitHub, helped us grap grasp some basic commands, and us grap grasp some basic commands, and us grap grasp some basic commands, and helped us understand how Git works. I helped us understand how Git works. I helped us understand how Git works. I worked with versioning in the past um worked with versioning in the past um worked with versioning in the past um for for for you know, in different situations, but you know, in different situations, but you know, in different situations, but and I thought I understood Git, but and I thought I understood Git, but and I thought I understood Git, but actually I didn't. I really needed actually I didn't. I really needed actually I didn't. I really needed someone to to tell me how it works and someone to to tell me how it works and someone to to tell me how it works and and what what are the best ways to to to and what what are the best ways to to to and what what are the best ways to to to set up a project. We were sitting set up a project. We were sitting set up a project. We were sitting together, we were testing out the app, together, we were testing out the app, together, we were testing out the app, and we were building it and we were building it and we were building it um together and dividing the work among um together and dividing the work among um together and dividing the work among us. So, we were committing code to this us. So, we were committing code to this us. So, we were committing code to this project. project. project. And since this wasn't this And since this wasn't this And since this wasn't this this app that we were building, it's not this app that we were building, it's not this app that we were building, it's not related to any of related to any of related to any of of our existing products, so there were of our existing products, so there were of our existing products, so there were no risks involved, and our focus was on no risks involved, and our focus was on no risks involved, and our focus was on learning, which was really really really learning, which was really really really learning, which was really really really great. We great. We great. We only used Cloud Code only used Cloud Code only used Cloud Code for this purpose, and outside of that, I for this purpose, and outside of that, I for this purpose, and outside of that, I think the only visual tool used was Nano think the only visual tool used was Nano think the only visual tool used was Nano Banana to to create um Banana to to create um Banana to to create um uh to create the office illustration. And the biggest insight, I think, for me And the biggest insight, I think, for me from this project was that from this project was that from this project was that if you're an engineer, the impact that if you're an engineer, the impact that if you're an engineer, the impact that you have when you enable others may be you have when you enable others may be you have when you enable others may be far greater than the impact of doing far greater than the impact of doing far greater than the impact of doing more engineering yourself. more engineering yourself. more engineering yourself. And for any this this is a great And for any this this is a great And for any this this is a great learning for any role. It can be learning for any role. It can be learning for any role. It can be um the same for engineering or design or um the same for engineering or design or um the same for engineering or design or product. Keep in mind that when you're product. Keep in mind that when you're product. Keep in mind that when you're working on a team with mixed abilities, working on a team with mixed abilities, working on a team with mixed abilities, and if you're stronger in a specific and if you're stronger in a specific and if you're stronger in a specific skill, make sure that you're helping and skill, make sure that you're helping and skill, make sure that you're helping and enabling each other up, because now with enabling each other up, because now with enabling each other up, because now with AI, we can all do a little bit um of the AI, we can all do a little bit um of the AI, we can all do a little bit um of the work that's outside of our domain. work that's outside of our domain. work that's outside of our domain. And this was the biggest learning for And this was the biggest learning for And this was the biggest learning for me, uh that engineers me, uh that engineers me, uh that engineers will need to become will need to become will need to become enablers and teachers. enablers and teachers. enablers and teachers. Moving on to the second project I worked Moving on to the second project I worked Moving on to the second project I worked on, this was my main focus for the on, this was my main focus for the on, this was my main focus for the radical speed month. I paired with an radical speed month. I paired with an radical speed month. I paired with an engineer and um engineer and um engineer and um a design operations person. And our a design operations person. And our a design operations person. And our goal, our main goal, we we worked on goal, our main goal, we we worked on goal, our main goal, we we worked on some design system projects together in some design system projects together in some design system projects together in the past. And here our main goal was to the past. And here our main goal was to the past. And here our main goal was to surface relevant and up-to-date design surface relevant and up-to-date design surface relevant and up-to-date design system information to humans and AI system information to humans and AI system information to humans and AI tools. tools. tools. And this um And this um And this um problem space is huge. Our design system problem space is huge. Our design system problem space is huge. Our design system uh uh that we use for our WordPress ecosystem that we use for our WordPress ecosystem that we use for our WordPress ecosystem products is open source. It serves many products is open source. It serves many products is open source. It serves many products internally and externally and products internally and externally and products internally and externally and is always in flux. is always in flux. is always in flux. So, the problem space was big. Uh we saw So, the problem space was big. Uh we saw So, the problem space was big. Uh we saw a lot of opportunities. So, we decided a lot of opportunities. So, we decided a lot of opportunities. So, we decided to divide and each person took on a to divide and each person took on a to divide and each person took on a problem to tackle. And what I proposed problem to tackle. And what I proposed problem to tackle. And what I proposed this design system status track tracker this design system status track tracker this design system status track tracker um um um the solution that I proposed raised the solution that I proposed raised the solution that I proposed raised questions with the engineer around questions with the engineer around questions with the engineer around performance, around maintenance, and if performance, around maintenance, and if performance, around maintenance, and if we would be able to to build it in the we would be able to to build it in the we would be able to to build it in the first place. first place. first place. But I was kind of empowered by the But I was kind of empowered by the But I was kind of empowered by the previous exercise. I was allowed to previous exercise. I was allowed to previous exercise. I was allowed to experiment, so I decided to build the experiment, so I decided to build the experiment, so I decided to build the full idea as a proof of concept full idea as a proof of concept full idea as a proof of concept on my own. So, um the discovery portion on my own. So, um the discovery portion on my own. So, um the discovery portion was three people, but the design and was three people, but the design and was three people, but the design and build was just myself. And it took build was just myself. And it took build was just myself. And it took around 2 and 1/2 weeks around 2 and 1/2 weeks around 2 and 1/2 weeks to build this. And as I worked on it to build this. And as I worked on it to build this. And as I worked on it piece by piece, especially uh when I piece by piece, especially uh when I piece by piece, especially uh when I reached the point where I had actual reached the point where I had actual reached the point where I had actual live component previews working, I was live component previews working, I was live component previews working, I was really mind-blown at what I was able to really mind-blown at what I was able to really mind-blown at what I was able to achieve. I moved through the project achieve. I moved through the project achieve. I moved through the project without any um without any um without any um without any restrictions in mind. Um without any restrictions in mind. Um without any restrictions in mind. Um I was just trying to push the limits. I was just trying to push the limits. I was just trying to push the limits. And um And um And um the tracker was picking up links from the tracker was picking up links from the tracker was picking up links from the GitHub repo, from Storybook, from the GitHub repo, from Storybook, from the GitHub repo, from Storybook, from Figma, sorting them according to status, Figma, sorting them according to status, Figma, sorting them according to status, tagging them with the correct library tagging them with the correct library tagging them with the correct library names. Search worked perfectly, and I names. Search worked perfectly, and I names. Search worked perfectly, and I was really excited about this product, was really excited about this product, was really excited about this product, and I shared it with fellow designers. I and I shared it with fellow designers. I and I shared it with fellow designers. I iterated a little bit based on the iterated a little bit based on the iterated a little bit based on the feedback, but everyone was pretty feedback, but everyone was pretty feedback, but everyone was pretty excited. excited. excited. I built the prototype initially as a I built the prototype initially as a I built the prototype initially as a start, and then I used Figma start, and then I used Figma start, and then I used Figma only later in the process for some only later in the process for some only later in the process for some visual fine-tuning. Some things that I visual fine-tuning. Some things that I visual fine-tuning. Some things that I just couldn't explain to claw to claw just couldn't explain to claw to claw just couldn't explain to claw to claw code, I code, I code, I I wanted to deliver an image, and that I wanted to deliver an image, and that I wanted to deliver an image, and that worked. worked. worked. But the live project was was I was what But the live project was was I was what But the live project was was I was what I was iterating on directly. I was iterating on directly. I was iterating on directly. And the prototype was built within a And the prototype was built within a And the prototype was built within a week, and then it took another week and week, and then it took another week and week, and then it took another week and a half to rebuild it for some fixes, to a half to rebuild it for some fixes, to a half to rebuild it for some fixes, to set up a hosting, and deploy it in our set up a hosting, and deploy it in our set up a hosting, and deploy it in our internal platform as an internal tool, internal platform as an internal tool, internal platform as an internal tool, as well as on an external public-facing as well as on an external public-facing as well as on an external public-facing site with that that had a little bit of site with that that had a little bit of site with that that had a little bit of a curated a curated a curated um um data and information. data and information. data and information. And delivering this And delivering this And delivering this this product was a defining moment for this product was a defining moment for this product was a defining moment for me, where I moved from a designer to a me, where I moved from a designer to a me, where I moved from a designer to a design engineer. design engineer. design engineer. This is of course enabled by AI, but This is of course enabled by AI, but This is of course enabled by AI, but most of all, it was enabled by the fact most of all, it was enabled by the fact most of all, it was enabled by the fact that I could own the entire process. We that I could own the entire process. We that I could own the entire process. We were within the radical speed month, I were within the radical speed month, I were within the radical speed month, I was allowed to experiment. I I I had the was allowed to experiment. I I I had the was allowed to experiment. I I I had the agency agency agency and made all of the necessary decisions. and made all of the necessary decisions. and made all of the necessary decisions. In large organizations, this is very In large organizations, this is very In large organizations, this is very hard to do, hard to do, hard to do, but here I could just build whatever I but here I could just build whatever I but here I could just build whatever I thought was um thought was um thought was um was needed, and I didn't have to spend a was needed, and I didn't have to spend a was needed, and I didn't have to spend a lot of time in negotiations and lot of time in negotiations and lot of time in negotiations and handover. And then that was 2 and 1/2 weeks, so I And then that was 2 and 1/2 weeks, so I kind of had 1 week left kind of had 1 week left kind of had 1 week left Um a radical speed month, so I paired Um a radical speed month, so I paired Um a radical speed month, so I paired with a fellow designer and here you'll with a fellow designer and here you'll with a fellow designer and here you'll be able to see the incredible shift and be able to see the incredible shift and be able to see the incredible shift and speed and process that happened. In only speed and process that happened. In only speed and process that happened. In only 6 days, we went from zero to uh through 6 days, we went from zero to uh through 6 days, we went from zero to uh through the entire process to building an iOS the entire process to building an iOS the entire process to building an iOS chat for WooCommerce merchants that um chat for WooCommerce merchants that um chat for WooCommerce merchants that um allows them to answer shoppers in real allows them to answer shoppers in real allows them to answer shoppers in real time, reply from their phone, or even time, reply from their phone, or even time, reply from their phone, or even set up AI to answer the uh questions for set up AI to answer the uh questions for set up AI to answer the uh questions for them. And this is a fully working proof of And this is a fully working proof of concept that includes authentication concept that includes authentication concept that includes authentication through wordpress.com, includes a through wordpress.com, includes a through wordpress.com, includes a Jetpack connection. If If you use Jetpack connection. If If you use Jetpack connection. If If you use WordPress, you might know what that is. WordPress, you might know what that is. WordPress, you might know what that is. Um Um Um we also built a widget that inherits the we also built a widget that inherits the we also built a widget that inherits the site theming site theming site theming where the site visitors can actually ask where the site visitors can actually ask where the site visitors can actually ask the questions, as well as the the fully the questions, as well as the the fully the questions, as well as the the fully capable AI agent that scans the site for capable AI agent that scans the site for capable AI agent that scans the site for information and answers visitors' information and answers visitors' information and answers visitors' questions in real time, and also questions in real time, and also questions in real time, and also discerns whether it can answer a discerns whether it can answer a discerns whether it can answer a question or or not. What was important here was that the What was important here was that the the alignment and the the ideation part the alignment and the the ideation part the alignment and the the ideation part was fairly easy. It was fairly easy for was fairly easy. It was fairly easy for was fairly easy. It was fairly easy for us two designers to align and shape the us two designers to align and shape the us two designers to align and shape the features with because we always have the features with because we always have the features with because we always have the users in mind. And on the process side, users in mind. And on the process side, users in mind. And on the process side, um um what was interesting is that we started what was interesting is that we started what was interesting is that we started the exploration as a cloud code project the exploration as a cloud code project the exploration as a cloud code project folder where all of the chats and ideas folder where all of the chats and ideas folder where all of the chats and ideas were recorded into a file system. were recorded into a file system. were recorded into a file system. And I I noticed that that um And I I noticed that that um And I I noticed that that um significantly uh sped up collaboration, significantly uh sped up collaboration, significantly uh sped up collaboration, as well as build later. And we've uh as well as build later. And we've uh as well as build later. And we've uh continued I've continued this practice continued I've continued this practice continued I've continued this practice in my in my daily work. in my in my daily work. in my in my daily work. Um the main artifact we worked on here Um the main artifact we worked on here Um the main artifact we worked on here as well was the prototype. And that's as well was the prototype. And that's as well was the prototype. And that's the biggest shift for our process the biggest shift for our process the biggest shift for our process because normally we would start in Figma because normally we would start in Figma because normally we would start in Figma and we would work in Figma until we and we would work in Figma until we and we would work in Figma until we reach very high fidelity. But here reach very high fidelity. But here reach very high fidelity. But here uh, we had uh, very good plan. Then we uh, we had uh, very good plan. Then we uh, we had uh, very good plan. Then we um, um, um, built the the built the the built the the the prototype or the product and then we the prototype or the product and then we the prototype or the product and then we went back into Figma went back into Figma went back into Figma to just come back to it in a visual to just come back to it in a visual to just come back to it in a visual sense to build a mood board and for some sense to build a mood board and for some sense to build a mood board and for some UI fine-tuning. UI fine-tuning. UI fine-tuning. And in only 30 days, my process that has And in only 30 days, my process that has And in only 30 days, my process that has been similar for years has completely been similar for years has completely been similar for years has completely shifted. And that was true for many shifted. And that was true for many shifted. And that was true for many other people. other people. other people. The first project showed me how the The first project showed me how the The first project showed me how the engineer's role can be elevated from a engineer's role can be elevated from a engineer's role can be elevated from a builder to an enabler. And this is a builder to an enabler. And this is a builder to an enabler. And this is a skill that I believe will be crucial as skill that I believe will be crucial as skill that I believe will be crucial as more and more more and more more and more um, um, people in other roles start working in people in other roles start working in people in other roles start working in code. code. code. The second one moved me from a designer The second one moved me from a designer The second one moved me from a designer to a design engineer. to a design engineer. to a design engineer. Um, and here I'm talking about being Um, and here I'm talking about being Um, and here I'm talking about being able to push code to production in a able to push code to production in a able to push code to production in a well-established large system that well-established large system that well-established large system that requires serious onboarding and security requires serious onboarding and security requires serious onboarding and security practices. practices. practices. All of the company initiatives that I All of the company initiatives that I All of the company initiatives that I described together gave me the space I described together gave me the space I described together gave me the space I needed to experiment and find my own needed to experiment and find my own needed to experiment and find my own process that works process that works process that works within what we already have established within what we already have established within what we already have established in the company. And and the third in the company. And and the third in the company. And and the third project that I shared was just proof project that I shared was just proof project that I shared was just proof that we've unlocked speeds because I that we've unlocked speeds because I that we've unlocked speeds because I already had adjusted my process a little already had adjusted my process a little already had adjusted my process a little bit, but then bit, but then bit, but then we both leveled up together and had a we both leveled up together and had a we both leveled up together and had a shared understanding on how we can apply shared understanding on how we can apply shared understanding on how we can apply the tools so we could also easily meet the tools so we could also easily meet the tools so we could also easily meet each other. each other. each other. If you're in a large organization, try If you're in a large organization, try If you're in a large organization, try to implement this to implement this to implement this um even just at your team level. um even just at your team level. um even just at your team level. Uh changing processes or tools in large Uh changing processes or tools in large Uh changing processes or tools in large organizations requires shifting the organizations requires shifting the organizations requires shifting the human behavior behind them. So, provide human behavior behind them. So, provide human behavior behind them. So, provide your people with the access to the new your people with the access to the new your people with the access to the new tools, find your enablers and champions, tools, find your enablers and champions, tools, find your enablers and champions, create space for experimentation, and create space for experimentation, and create space for experimentation, and and give them agency so that they can and give them agency so that they can and give them agency so that they can break out of their habits and unlock the break out of their habits and unlock the break out of their habits and unlock the speed that AI tools can bring. speed that AI tools can bring. speed that AI tools can bring. Thank you.