WEBVTT NOTE Sentence-level transcript of https://www.youtube.com/watch?v=3XI90A3ENSg NOTE One cue per sentence. Cue ids are the line anchors on /transcripts/3XI90A3ENSg.html. A cue ends where the next begins, or 2 s after its last word. s1 00:00:00.000 --> 00:00:01.309 All s2 00:00:01.309 --> 00:00:03.309 [music] s3 00:00:12.400 --> 00:00:12.719 right. s4 00:00:12.719 --> 00:00:14.000 Hi everybody. s5 00:00:14.000 --> 00:00:16.480 Can you hear me? s6 00:00:16.560 --> 00:00:16.880 All right. s7 00:00:16.880 --> 00:00:22.640 So, uh, my name is M. Shrieve and I work at Automatic. s8 00:00:22.640 --> 00:00:32.320 Um, and if you're not aware of what Automatic is, we are the company behind WordPress.com and Tumblr and a number of other properties. s9 00:00:32.320 --> 00:00:40.480 Um, and we're a fully distributed company uh with over 1,400 uh people in 82 countries. s10 00:00:40.480 --> 00:00:56.960 Um, and I'm here today to talk about our approach to uh, AI enablement and upskilling our organization um, to use all of these uh, new tools and ways of working. s11 00:00:56.960 --> 00:01:07.520 Um, so our bet is that you don't just get good quality learning or work out of just handing people the tools. s12 00:01:07.520 --> 00:01:14.159 you need to give them real time to learn and uh experiment. s13 00:01:14.159 --> 00:01:26.799 Um so what we've been doing is running these two week um enablement programs where we bring people in in person for a twoe immersive experience. s14 00:01:26.799 --> 00:01:39.439 And uh the way that we do that is um through 50% facilitated learning um through our uh learning and development team and our AI enablement team. s15 00:01:39.439 --> 00:01:48.240 We pull together workshop hosts from within the company to run workshops and hands-on um activities. s16 00:01:48.240 --> 00:01:53.280 Uh and we'll look a bit at what that curriculum looks like shortly. s17 00:01:53.280 --> 00:01:56.000 Um and then 50% real project work. s18 00:01:56.000 --> 00:02:07.520 So, we have folks bring in um real work that they want to get done or a tool or dashboard that would help them and their day-to-day work. s19 00:02:07.520 --> 00:02:17.360 Um or these can also be creating new skills or MCPs to enable them to work faster outside of the program. s20 00:02:17.360 --> 00:02:23.840 And another large part of this is uh encouraging peer sharing. s21 00:02:23.840 --> 00:02:30.879 um so sharing their own workflows to show um kind of the art of what's possible. s22 00:02:30.879 --> 00:02:40.560 And uh as they work throughout the two weeks, we also do a number of uh project demos at the end of each day. s23 00:02:41.760 --> 00:02:45.360 So we've uh we've ran three flavors of this. s24 00:02:45.360 --> 00:02:55.200 um our main set being for engineers where we go uh a lot more in depth um getting into applied AI. s25 00:02:55.200 --> 00:03:08.879 We've also um experimented with crossf functional programs um with product engineering and design getting together in a room and discussing kind of the future of of how we all work together s26 00:03:08.879 --> 00:03:11.280 um with with these new tools. s27 00:03:11.280 --> 00:03:24.480 And then we've also extended into non-technical teams and run workshops with our finance group, our executive leadership team um and other functions as well. s28 00:03:25.920 --> 00:03:35.120 So our engineering curriculum starts the first few days uh covering the basics skills and how to create them. s29 00:03:35.120 --> 00:03:49.680 um learning how to use MCPS and specdriven development um as well as kind of the foundations of how to use AI responsibly and how to um apply it in a way that's mindful. s30 00:03:49.680 --> 00:03:53.040 Um and then we start getting into deeper topics. s31 00:03:53.040 --> 00:04:05.840 Uh creating MCPs um for new functionality, getting into the hook system of codecs and claude and being able to extend the harness that way. s32 00:04:05.840 --> 00:04:13.680 Um up to uh autonomous agents and running routines and such in the background. s33 00:04:13.680 --> 00:04:17.440 Um and then we end on some different applied topics. s34 00:04:17.440 --> 00:04:22.160 Um so again automatic is behind WordPress.com. s35 00:04:22.160 --> 00:04:36.720 So uh we normally run a workshop on applied WordPress AI um and some of the cool features that are in WordPress core uh around AI as well as uh being able to create your own personal assistant. s36 00:04:36.720 --> 00:04:48.160 So we really try to walk people um from the foundations up into uh the ability to start creating these new things for themselves. s37 00:04:49.360 --> 00:04:53.759 And one thing that we found out is you cannot just write this curriculum once. s38 00:04:53.759 --> 00:04:59.120 As we're all aware, AI is constantly changing from day to day, week to week. s39 00:04:59.120 --> 00:05:04.240 The top model might be different uh depending on the latest release. s40 00:05:04.240 --> 00:05:17.360 Um so we're constantly needing to update the curriculum and stay current to make sure when we running these programs, we're teaching the right thing and we're not teaching six months out of date. s41 00:05:17.759 --> 00:05:28.000 Um, another interesting part I wanted to highlight here is we have our own uh internal uh MCP server called context automatic. s42 00:05:28.000 --> 00:05:40.800 And this allows us um to rapidly add new tooling sets for MCPs that might not exist or that we want to build our own um like governance and observability s43 00:05:40.800 --> 00:05:42.160 layers on. s44 00:05:42.160 --> 00:05:55.280 Um, and one of the cool things that, uh, I'll highlight shortly is, uh, some of the projects coming out of these cohorts is extending these abilities. s45 00:05:55.280 --> 00:06:04.639 So, as people go through the capabilities, um, compound and we're able to do more as a company uh, because of that. s46 00:06:04.880 --> 00:06:14.960 Another main focus of our program is that these aren't just a number of people that we're sending through. s47 00:06:14.960 --> 00:06:27.840 We're also wanting each person we send through um to be a multiplier uh within the company and extend our reach to the folks that we can't get to yet. s48 00:06:27.840 --> 00:06:35.600 Um, so so far this year we've ran seven of these cohorts of groups of about 45 people. s49 00:06:35.600 --> 00:06:44.800 Um, and we're aiming to get around 600 people through these programs by the end of the year. s50 00:06:44.800 --> 00:06:54.720 Um, which is about 2/3 of our engineers as well as uh some of those other focus areas that I highlighted at the beginning. s51 00:06:54.720 --> 00:07:03.599 And we would like to equip all these people with uh ways of sharing their knowledge out and again extending our reach. s52 00:07:03.599 --> 00:07:07.120 So we've tackled this in a few different ways. s53 00:07:07.120 --> 00:07:16.160 Um we are beginning a guides program or um I think other companies call this like their champions program. s54 00:07:16.160 --> 00:07:32.800 And what we want to do is extend our team's reach into other areas and have these um like top practitioners that we've identified within the company be able to help us out and uh continue s55 00:07:32.800 --> 00:07:35.120 spreading the knowledge. s56 00:07:35.120 --> 00:07:41.680 Um because we're distributed, we also have began these local AI gettogethers. s57 00:07:41.680 --> 00:07:56.000 So people that have gone through the program um are able to then run these like little events within their regions and um run workshops and we'll help support that as well. s58 00:07:56.000 --> 00:08:01.039 Um and we've done about 10 of those so far in various different areas of the world. s59 00:08:01.039 --> 00:08:09.680 Um and it's been been exciting to see like what some of these people that have gone through the program have have gone on to do and teach. s60 00:08:09.680 --> 00:08:23.039 Uh we also um organize these things called AI ride alongs and these are little workshops that we run um basically showing how you work, how you use a different tool. s61 00:08:23.039 --> 00:08:36.320 Um because what we found is seeing someone in your similar role or um in in a similar job to you, being able to see how they use it uh is a lot more s62 00:08:36.320 --> 00:08:40.959 um easy to grasp than just you know talking about the concepts. s63 00:08:40.959 --> 00:08:48.240 Um and then we're also attempting to build a shared skill and MCP infrastructure. s64 00:08:48.240 --> 00:09:01.440 So again that context aid C um system that I mentioned but also uh encouraging people to create and share skills and build uh on top of each other's work s65 00:09:01.440 --> 00:09:08.720 so that we're all kind of building um towards the same kind of platform. s66 00:09:08.720 --> 00:09:19.200 And then we have an always on uh help Slack channel where we also ask people that have gone through this program to help out um and just kind of s67 00:09:19.200 --> 00:09:27.920 be available for anyone newer uh to working this way to have a place to come and ask questions at any point of the day. s68 00:09:31.120 --> 00:09:40.640 So, I'm going to share a few of the the metrics that we've been tracking and um improvement we've seen throughout the program. s69 00:09:40.800 --> 00:09:50.640 Um, one of these is intentionality and um just applying to applying AI to your work in a more thoughtful way. s70 00:09:50.640 --> 00:10:01.440 Maybe these people came in at the beginning just using it as a chatbot or um you know not fully using an agentic workflow. s71 00:10:01.440 --> 00:10:07.120 Um so having people be a bit more intentional at how and when they apply AI. s72 00:10:07.120 --> 00:10:14.399 Um flow which is like how well they're able to integrate AI into their workflows. s73 00:10:14.399 --> 00:10:23.680 um if people feel as if um they're able to use it in a way that makes sense for them and not just using it for AI's sake. s74 00:10:23.680 --> 00:10:37.440 Um and then the the sharing part again is very important to us so that we can continue um reaching other people in the company and um kind of making everyone s75 00:10:37.440 --> 00:10:42.480 uh a a teacher and an expert on these topics. s76 00:10:42.480 --> 00:11:00.800 Um we also track uh individual lift on various metrics such as um skills and custom commands um how comfortable they feel using and applying MCPS and uh other topics like context management s77 00:11:00.800 --> 00:11:08.880 um and what we've seen uh from doing various surveys uh after the program. s78 00:11:08.880 --> 00:11:15.360 So we'll do one 72 hours after uh 30 days after and 90 days after. s79 00:11:15.360 --> 00:11:29.760 People will continue growing within those 90 days and um being able to apply things more and like they've had more time to experiment and try things. s80 00:11:29.760 --> 00:11:38.959 Um so we're still seeing people like gain confidence and experience uh even once they've gone through the program. s81 00:11:42.320 --> 00:11:53.360 Um so I wanted to highlight just a few of the things that folks have built um just within the two weeks of the program. s82 00:11:53.360 --> 00:11:58.560 Um one of these is uh an agentic analytics system. s83 00:11:58.560 --> 00:12:17.440 So uh we have WordPress has a uh e-commerce platform plugin called Woo Commerce and some of the people that went through our program um created a a gentic system for asking questions about your store and getting back answers. s84 00:12:17.440 --> 00:12:26.708 Um a number of folks that go through uh build on top of context a C. Um so one of our earlier cohorts s85 00:12:26.708 --> 00:12:27.040 [snorts] s86 00:12:27.040 --> 00:12:39.920 um they wanted to be able to use uh some of these tools for support um and built a Zenesk connector um which now we've had adopted through various teams throughout the company. s87 00:12:39.920 --> 00:12:51.680 Um we've built other providers in there that uh might not have a native MCP or again because we wanted to add additional observability there. s88 00:12:51.680 --> 00:12:55.680 Um we've been building out our own agent skills directory. s89 00:12:55.680 --> 00:13:13.600 Uh we don't prescribe a single tool so folks are able to use codecs or claude or uh any other number of tools open code etc. Um so we wanted to build our skills directory in a way that can be used across all of those. s90 00:13:13.600 --> 00:13:20.160 Um and the whole skills directory actually came out out as a project from one of these cohorts as well. s91 00:13:20.160 --> 00:13:28.320 Um and then finally another one I wanted to highlight here is uh guided admin support. s92 00:13:28.320 --> 00:13:45.920 So, um, during a help session, say you want to show someone exactly where something is, uh, within the dashboard, um, they built a tool using, uh, cloud code that allowed them to be able to, s93 00:13:45.920 --> 00:13:50.639 um, guide and lead a session, highlight different parts of the screen. s94 00:13:50.639 --> 00:14:00.880 Um, and this actually came not from an engineer, but one of our support folks um that felt a bit more comfortable after going through one of our programs. s95 00:14:01.199 --> 00:14:07.519 And that is the end of my presentation. s96 00:14:07.519 --> 00:14:18.160 But the one takeaway that I wanted people to take from this is uh give people real time to actually experiment and learn. s97 00:14:18.160 --> 00:14:23.440 um you can't just throw a bunch of tools at them and expect their way of working to change. s98 00:14:23.440 --> 00:14:34.880 You need to to make space and give an environment for learning um and and make that like the star of whatever your education program is. s99 00:14:34.880 --> 00:14:47.040 And uh I will be available for questions at our booth which is uh the automatic booth right over on the other side near that stage and the swag pickup. s100 00:14:47.040 --> 00:14:54.160 Um, so I'll be there for a little bit after this talk if you want to talk about anything I talked about here. s101 00:14:54.160 --> 00:15:09.199 Um, or you'd like to hear more about how uh how WordPress.com and Woo Commerce are uh embracing AI um with our official connections and MCPs. s102 00:15:09.199 --> 00:15:11.199 Um, so please stop by the booth. s103 00:15:11.199 --> 00:15:15.045 Um, and yeah, thank you. s104 00:15:15.045 --> 00:15:17.045 [applause] s105 00:15:30.110 --> 00:15:32.110 [music]