How Microsoft's AI VP automates everything with Warp | Marco Casalaina

1. 0:00 – 2:14

   Introduction to Marco Casalaina

   1. MCMarco Casalaina0:00

      Warp is pretty magical, but you can add to the magic and make it work more smoothly.

   2. CVClaire Vo0:04

      You're talking about setting up little micro-agents that do little tasks for you, either one-off ones like we saw in Warp or recurring and triggered ones, and then this is making your life just easier.

   3. MCMarco Casalaina0:17

      As soon as I started using it for certain things like managing Azure, giving Azure subscriptions and stuff like that, then I was hooked. I was like, man alive, this is a really capable tool.

   4. CVClaire Vo0:27

      Until you start working with these agents, you don't really discover all the things that you can do with command lines. But I think once you start to test those, then it kind of opens up your mind to what is really possible. [upbeat music] Welcome back to How I AI. I'm Claire Vo, Product Leader and AI obsessive, here on a mission to help you build better with these new tools. Today, I have Marco Casalaina, VP of Core AI Products and AI Futurist at Microsoft. Marco's gonna speed run through five AI use cases where micro-agents can reduce the friction of getting little tasks done, whether they're technical or not so technical. Let's get to it. Meet Rovo, your AI teammate, connecting knowledge, people, and workflows so teams can work smarter and move faster. It helps people find answers, make decisions, and automate work securely and with context through search, chat, agents, and studio. Rovo runs on the Teamwork Graph, Atlassian's intelligent layer that unifies data across your first and third-party apps so no knowledge gets left behind, and you always get personalized AI insights from day one. And the best news? It's already built into Jira, Confluence, and Jira Service Management paid subscriptions, so the power of Rovo is already at your fingertips. Know the feeling when AI turns from tool to teammate? If you Rovo, you know. Discover Rovo, AI that knows your business, powered by Atlassian. Get started at rovo.com. That's R-O-V, as in victory, O.com.

2. 2:14 – 3:57

   Why Marco chose Warp for administrative tasks

   1. CVClaire Vo2:14

      [upbeat music] Marco, thanks for joining How I AI. I am excited because we're gonna see a tool, Warp, that we haven't yet seen on the podcast, and we're gonna see you use it for maybe not its primary pitched use case, which is kind of agentic coding, but for some sort of more ancillary support use cases that you found to be really useful. So before we get into them, like, why have you hooked so deeply into Warp in particular?

   2. MCMarco Casalaina2:46

      I started using Warp, uh, ironically because our own-- one of our own teams here at Microsoft tuned me into it. They-- It was our PowerShell team, and they were like, "You should try this Warp thing. It automates PowerShell really well." And so I tried it, and as soon as I started using it for certain things like, uh, managing Azure and, you know, giving Azure subscriptions and stuff like that, then I was hooked. I was like, man alive, this is a really capable tool.

   3. CVClaire Vo3:15

      And if you're looking for the sexiest episode of How I AI, it is this because we are gonna show you [laughs] how, how to manage Azure resources with AI, which actually I'm making a joke 'cause I think it's so funny, but these are the kinds of things that if you are a software engineer or an engineering leader y- or just building something, you are spending so much time on DevOps, admin, configuration, IAM, all that kind of stuff takes all your time, and you don't actually get to the fun part of coding with AI. So, you know, show us maybe that specific use case and why you think Warp was such a good fit for that and what the pain was before you had

3. 3:57 – 6:00

   Demo: Using Warp to manage Azure resources and permissions

   1. CVClaire Vo3:57

      a tool like this.

   2. MCMarco Casalaina3:58

      Yeah, let's do this. So I was working with my colleague, Govind, the other day, and I needed to assign him access to a number of Azure resources. And you know, you give them granular roles. So here I needed to give him Azure AI user and Azure AI project manager, and this was part of a, a big project that Govind and I are working on. Now, to do this, it's actually not that easy, to be honest, to do this in, in Azure, you know? A-and especially if I do it with a web interface. There is a web portal where I can go in there, and for each individual role, I can go find the role and assign it to Govind, and then the next role and assign it to Govind. It's not very efficient. If I were-- For all the roles I needed to give Govind, I mean, this would've taken me an hour. So instead, I do stuff like this. This is my prompt. I say, you know, I, I found Govind's email address in here to begin with, and then I'm like, okay, now, uh, give him, uh, Azure AI user and Azure AI project manager on this subscription that I'm looking at. And here it, [chuckles] it does it, right? So it will call AZ. AZ is this command line interface, and this is Warp's superpower. Aside from being a coding agent, which as I know, you know, a lot of people use it for, and I mostly don't, actually. I actually use it more like this. Whenever there's a command line interface, a CLI that can do something, uh, Warp is freaking great at that. And so it will call AZ repeatedly until it runs into the ground. Now here, I think it made a mistake somehow, whatever it was doing, an AZ role, this one. It, it kind of made a mistake here, and then it got right back to it, and it did it, and then it's like, okay, I'm done. And then I say, okay, actually, I need to give him contri- contributor role on the whole subscription. And it does that too. Uh, no problem. And so I use this for all kinds of stuff, uh, here. But, you know, for Azure administration, and, uh, close your ears, Microsoft people, I have also used this to administer GCP. Worked just as well with gcloud, the gcloud c- uh, CLI.So it's, it's great

4. 6:00 – 7:18

   How CLI tools eliminate GUI friction for complex tasks

   1. MCMarco Casalaina6:00

      at this stuff

   2. CVClaire Vo6:01

      I was gonna say, if you have been victimized by AWS, Azure, or GCP admin interfaces for assigning roles, this is exactly the kind of, kind of workflow you wanna see. And a meta thing I wanna call out for people, because I've worked in dev tools for quite some time, and one of the challenges as a product person and an engineer working on dev tools is exposing a, a GUI on these very complex, very, um, interactive sets of permissions, capabilities, configurations. It's actually a really hard design problem.

   3. MCMarco Casalaina6:39

      Like a virus.

   4. CVClaire Vo6:39

      It's like a very hard, you know, front end design problem. And what I love about AI having access to CLI tools, APIs, MCPs, all these ways to more programmatically access these capabilities, is you can actually abstract away all of that front end stuff and just let a user kind of query the system and get what needs to get done. And so if you're on the other side of this, you're not the user, but you're the builder of something like Azure, this makes it so much simpler to expose a quote unquote, like, user interface to, to someone like you who needs to get,

5. 7:18 – 10:28

   Creating rules to improve AI performance for specialized tasks

   1. CVClaire Vo7:18

      get a job done. And then I have to call out a second thing, which is [laughs] you're also doing what, what I would-- I used to... Sorry, RIP Stack Overflow a little bit. But, you know, I used to, like, Google, "How do I kill all processes for Adobe?" And then, like, find the command line, you know-

   2. MCMarco Casalaina7:38

      Mm-hmm

   3. CVClaire Vo7:38

      ... uh, the command, and then paste it in. And then, you know, you get the error, and you paste it back into search, and you try to find it. And what I love about these more agentic processes that have access to the terminal and the command line is you can just do that all in one, all in one interface.

   4. MCMarco Casalaina7:54

      Totally. Yeah. Exactly. Now, I will tell you though that it, there's a trick to making this stuff work. I mean, Warp is pretty magical, to be honest, but you can add to the magic and make it work more smoothly, and there's a couple ways you could do that. I mean, if you think about what I did with AZ, really, uh, if you look at my MCP servers, well, this one's i- it's, it's off right now, but I do connect this to the Microsoft Docs MCP server when I'm doing, like, Azure administration. Because sometimes... You know, in this case, I knew exactly what roles I wanted to give Govan, but there are times when I have no idea what role somebody needs to do something. Like, I'll be like, "Give this person whatever role they need to use Azure Document Intelligence," a- and like, you figure it out, right? But rather than leaving it to its own devices, I can do as I'm doing here, I can connect it to the Microsoft documentation MCP server, which is a pretty good MCP server, and then it'll go look it up, and that makes it work much better. Uh, another piece of this, and we'll see it again in a moment, is, is the rules. So now, originally, like, out of the box, uh, [chuckles] when I, when I, when I tell it-- So I give it these rules. And so, like, if I'm giving rules on a resource group, roles on a resource group, I should say, I do need to activate my owner access first. So this is one of the common problems that I have, is that I have not activated my owner access, which is, like, a hurdle I have to go through. And so I make Warp remind me, and Warp will be like, "So hey, did you activate your owner access before I start doing this? 'Cause otherwise it's gonna fail." So you can give it these rules and MCP servers that kind of help it along, uh, and, and help it use this stuff. Of course, that's useful for coding as well, uh, but, you know, I find it super useful for these kinds of things that I use it for.

   5. CVClaire Vo9:42

      Well, and what I will call out, and this is no shade, but this is not the most sophisticated prompting I've ever [chuckles] seen in my life. It's just like, "Hey, when you're trying to do this, remind me to do that. If you're waiting on me, like, pop open a browser, like, wait for me to do the thing, and then y- always use the CLI tool." And so I actually love looking at your prompting here 'cause it's very conversational. And I think people get, like, wrapped around the axle on, like, my prompts have to be in this specific format and have to be these, like, very gracefully designed things. And honestly, for most stuff, just taking the step of writing, like, two or three steps that you need a system to follow are what makes things more eff- more effective.

6. 10:28 – 13:00

   Demo: Document scanning automation

   1. CVClaire Vo10:28

      And then speaking of kind of, like, step-by-step processes, one of the other things I love about what you're doing with Warp is you're just taking, again, I think these things that you could do in a UI, and they would be annoying to do and not fun, and just having a, you know, smart technical agent do them on your behalf. So you wanna walk us through how you did, how you did that with your, your daughter's homework? [chuckles]

   2. MCMarco Casalaina10:57

      Yeah. Let's, let's talk about that. My daughter is studying for a math test right now, and it's tomorrow. And her teacher gave her a practice test, and I decided to scan that in. Because sometimes what I'll do is, she'll take the test, but I'll, I'll take the practice test, I'll scan it in, and then I feed it to ChatGPT, and I'm like, "Make me variants of these problems." And it will do it. Like, inequalities and things like that, it'll make other inequalities that are similar but different so that she gets a little bit more practice on these things. So I needed to scan this in. Now, my scanner has a feeder, and so it sucks in the pages, but this was a two-sided, uh, practice test, and so I needed to scan the odd pages, and then I needed to scan the even pages, and then I needed to put it together. So what do I do? I go to Warp here, and I say it exactly, "Scan the documents from the feeder and save it to this directory as this filename." And it does. It totally does do that. And so it figures that out, and done. It's done. And then-

   3. CVClaire Vo11:55

      Wait. Can I, can I pause you really quickly?

   4. MCMarco Casalaina11:57

      Yeah.

   5. CVClaire Vo11:57

      Did this activate the scanner?

   6. MCMarco Casalaina11:59

      Absolutely it does.

   7. CVClaire Vo12:00

      What? Okay. [chuckles]

   8. MCMarco Casalaina12:01

      Yeah.If I were, if I were home right now, which I'm in the office right now, but if I were home right now, I would do this again, and you would see my scanner would wake right up and start scanning.

   9. CVClaire Vo12:09

      So you didn't even have to press the little button and pop open the thing, and you just-

   10. MCMarco Casalaina12:13

       Not a thing.

   11. CVClaire Vo12:14

       Okay.

   12. MCMarco Casalaina12:14

       All I had to do was put the sheets in the feeder, and as soon as I type this thing in, boom, there it goes.

   13. CVClaire Vo12:19

       So for, for the youths listening and watching this show, as a, as a parent, you spend a lot of time with a scanner and a printer. I don't even know if you all know what that is. [chuckles] But this is, this is, uh, peak, peak efficiency. If efficiency for me is being able to just, uh, remotely start the scanner-

   14. MCMarco Casalaina12:38

       Mm-hmm

   15. CVClaire Vo12:38

       ... um, from, from my AI coding tool.

   16. MCMarco Casalaina12:41

       And I'm not gonna lie, like I scan like her birthday cards and like the Valentine's Day cards and things like that. Like I am deathly afraid that one day there will be a fire and all of these historical documents that she's made will be destroyed, and so I scan those in too because it's easy, right? It only takes me a second. Then I type this in here, and now there it is.

7. 13:00 – 15:04

   Combining odd and even pages using a Python automation

   1. CVClaire Vo13:00

      Okay, so you scanned one side.

   2. MCMarco Casalaina13:02

      So I scanned one side. Now, uh, Warp is kind of bimodal, so it works both as a, as an agent, as a not agent. So then I just pressed the up key.

   3. CVClaire Vo13:12

      Mm-hmm.

   4. MCMarco Casalaina13:12

      So you see, the second time I did this, it had generated this command line here.

   5. CVClaire Vo13:16

      Oh.

   6. MCMarco Casalaina13:16

      And when I pressed up, it just go, will go straight to this command line. And so I'm like, well, I'm basically doing the same thing again, but now I'm sort of doing the even pages, so I just change odd to even over here, and it just did that. So it didn't even need to call the large language model to do this. But then I wanted to put it together. So I said, "Now put together the odd pages and the even pages and just make the math practice test out of it." And so now it wrote some Python to do this, actually. Uh, I guess it installed PyPDF2.

   7. CVClaire Vo13:46

      [chuckles]

   8. MCMarco Casalaina13:47

      And it wrote a little Python file and ran it, and then it removed it. So I mean, in a sense, I am using here Warp as a coding agent, ironically sideways. Uh, but you know, it did it. I mean, in the end, absolutely, it most certainly did, uh, create a unified thing.

   9. CVClaire Vo14:06

      Now, I have to give, um, these AI coding tools and IDEs, et cetera, a little product feedback, which is I want like a time to task little timer here, and I want it to say, "Hey, you did this in 112 seconds," and give me like confetti, because again, this is one of those things I just think about how you would've done it before, which is you would've walked over to your scanner, which I have one right here. I would've pulled up the terrible native scanner software, you know, if you know it. If you know, you know. And I would've like scanned the thing and downloaded the PDF and then flipped it and scanned the thing and downloaded the PDF and then like found some PDF opener and then like dragged and dropped the pages in the right, the right order and then saved that file, and it would've been so, so, so annoying. And instead, you get to sit where we all wanna live right now, which is in the terminal, in the terminal in dark mode, and just ask it to

8. 15:04 – 17:12

   The value of ephemeral AI solutions vs. permanent tools

   1. CVClaire Vo15:04

      do this thing. And I think something that, you know, maybe less technical people don't appreciate is if you look at this and you look at these commands Warp are generating, a lot of stuff on your computer you're able to do programmatically.

   2. MCMarco Casalaina15:18

      Right.

   3. CVClaire Vo15:18

      And until you start working with these agents, you don't really discover all the things that you can do with command lines. But I think once you start to test those, then it kind of opens up your mind to what, what is really possible.

   4. MCMarco Casalaina15:35

      Well, what's interesting is it caused me to look for ways that I could do things for the command line. So this scanner thing, this wasn't magical. There is, as far as I know, not a way in Windows to CLI invoke a scanner unless you install NAPS2. So if you look at my rule for this, and I, I, what I said is, "When you're in Windows and I tell you to scan something, use NAPS2 to do it." And I gave it the location of where I installed this thing called NAPS2, which is this scanner CLI. It's an open source scanner CLI for Windows. So I installed this. I made a rule for it, knowing that I scan things so frequently that this would save me a vast amount of time. Uh, so you know, again, like it's magic, but it's not entirely magic. You do have to do a little preparation for this trick to work.

   5. CVClaire Vo16:24

      This episode is brought to you by Lovable. If you've ever had an idea for an app but didn't know where to start, Lovable is for you. Lovable lets you build working apps and websites by simply chatting with AI. Then you can customize it, add automations, and deploy it to a live domain. It's perfect for marketers spinning up tools, product managers prototyping new ideas, or founders launching their next business. Unlike no-code tools, Lovable isn't about static pages. It builds full apps with real functionality, and it's fast. What used to take weeks, months, or even years, you can now do over the weekend. So if you've been sitting on an idea, now's the time to bring it to life. Get started for free at lovable.dev. That's lovable.dev.

9. 17:12 – 20:22

   Video compression using FFmpeg commands

   1. CVClaire Vo17:12

      I am just laughing because, again, I think my pitch at the beginning of this podcast, which is this is the most glamorous episode of How I AI, which is we're gonna do Azure role, role assignment. We're gonna do drivers for your, your scanner that can be run via the CLI. And then you have one more use case, which is-

   2. MCMarco Casalaina17:32

      I do

   3. CVClaire Vo17:33

      ... as somebody who, who does a podcast and works with a lot of videos, is really useful, um, that I thought maybe you could walk us through.

   4. MCMarco Casalaina17:40

      This one is for you. So I record a lot of videos myself, actually, and I have my little YouTube channel, although I can't say I have a podcast. It's not as regular as yours. But, uh, yesterday, uh, I used the Game Bar thing, the Xbox Game Bar thing, to record a video off my screen. I said, "Maybe I'll try this, see how it goes." Well, for 10 minutes of video, this thing recorded a 1.7 gigabyte file. I don't know what it was doing, but I mean, it was insane.And I was recording this new tool that we're working on called Opal. Anyway, so I was like, "What is up with this?" to Warp. As you can see in my prompt here, I say, "Why is this file so big? Use FFmpeg to re-encode it, still keeping it at 1080p," because I didn't want it to, like, nestify the resolution, and make it more normal size. FFmpeg is a CLI that you can use to edit videos, and I use this all the time. I use it to strip audio off of videos. One day, my coworker sent me a video where, like, from seven seconds to 17 seconds, it suddenly went really quiet, and then it went back to normal. So I said to Warp, I'm like, "Use FFmpeg to, like, make the sound 300% from seven seconds to 17 seconds," and it totally does. But here, uh, it looks at the file, and it's like, "Okay, the video is 1.7 gigs because it has a huge bit rate, and it's at a huge resolution for some reason," and then it followed my instructions. It ran FFmpeg with whatever the switches were to re-encode this thing, and it did re-encode this down to 13 megabytes, which is what you would expect for, like, a 10-minute video of a screen share. Thank you.

   5. CVClaire Vo19:19

      Yeah, and so a- again, like, I think this is one of those things that in an alternative world, somebody would have, like, gone to search and say, like, video compression software, tried to open something, and, like, export and compress and figure this out. And instead, in just a couple seconds, you can use this more technical tool and get a lot of stuff done and also sort of understand the root cause. You know, another thing that I think people don't really appreciate about AI enough, and we had an episode, um, with a producer from Ken Burns' documentary production agency, is files are very rich with information, and giving an agent access to a file, you can tell a lot about that file. And then if you layer on an LLM, you can tell a whole, a whole lot about that file. And so I do think file manipulation is a real underappreciated use... Like, we do so much file generation, but I actually think file manipulation is a really underappreciated use case of

10. 20:22 – 22:31

    The concept of “ad hoc agents” for specific tasks

    1. CVClaire Vo20:22

       AI.

    2. MCMarco Casalaina20:23

       Right. Now, if you think about what I'm really doing with Warp, the way that I'm using Warp, I characterize it in a certain way. I call this an ad hoc agent because effectively, each one of these things that I'm doing, you know, when I'm assigning the Azure roles or when I'm scanning the stuff or when I'm doing stuff with the videos, I'm kinda creating a little mini agent, an unnamed agent on the fly to do something for me, and that's becoming a trend. Like, this is a thing that's starting to happen not just in Warp but in lots of different types of general purpose agents.

    3. CVClaire Vo20:58

       Yeah, and what I would say is also, I... What I love about AI and what I would recommend to people with AI is, like, just get used to ephemeral stuff. Like, just toss it. Like, if you ever need to compress a video again, don't save this script. Don't... Like, just, just come back and do it again, probably with a better model at some point, and it's gonna be just as cheap and just as easy. And so I think a lot of people get stuck in their head about like, "Oh, how do I make this a product?" or "How do I get this to production?" It's like, don't get it to production. Just next time do it over, [chuckles] do it over again. Maybe save a rule so you're not rediscovering the steps.

    4. MCMarco Casalaina21:32

       Right.

    5. CVClaire Vo21:32

       But, like, you don't need to build a whole, a whole thing here.

    6. MCMarco Casalaina21:36

       And that's, that's exactly the right idea, right? So when it... You know, for example, like, it happened once that it tried to call NAPS2, the scanner thingy, and failed because it couldn't figure out what the path to NAPS2 was. And so that's why I made that rule that's like, "When I tell you to scan, here's where NAPS2 is. When I tell you to scan from the feeder, this is the switch to scan from the feeder instead of the flatbed scanner thing." And now that it has that rule, it has never done it wrong since then, right?

    7. CVClaire Vo22:02

       Wow.

    8. MCMarco Casalaina22:02

       It does it right every single time, even though I'm scanning to a different directory, a different file, maybe a different format. It does it right every single time.

    9. CVClaire Vo22:10

       You know, I'm not saying I love AI more than humans, but sometimes it would be really, [chuckles] really nice to be able to get that consistency-

    10. MCMarco Casalaina22:17

        If you could get humans ruled

    11. CVClaire Vo22:19

        ... out of the people or the people around me. Um, you know, perhaps my, my, my children who d- who are not, uh, loaded with rules and context all the time and consistent help. [chuckles] But-

    12. MCMarco Casalaina22:30

        No.

11. 22:31 – 25:51

    Demo: Creating triggered workflows in Microsoft 365 Copilot

    1. CVClaire Vo22:31

       Well, let's switch over to maybe some less technical use cases, but ones I think are really interesting. Again, thinking about ad hoc agents and workflows, how you're using sort of more administrative task-based workflow, workflow-based things to kind of be prepped for the work you need to do in a day.

    2. MCMarco Casalaina22:51

       Yeah. Well, I mean, here I am in M365 Copilot. So this is Microsoft's general purpose agent for business, and a lot of people think of it like this. Like, I, I can ask it a question, "When am I doing How I AI?" And it shows it here. Here you go. It knows my calendar, and that's, that's cool. But what's happening now is that this and many general purpose agents like it are becoming agent builders. The line between consuming an agent and building an agent is blurring. So this is the new workflows agent, and this is an agent that builds an agent. So I'm gonna kick this thing off. And what I said here is, "When I get an email from Claire Vo requesting a meeting at a certain time, check my calendar. If that time is free, send her a 30-minute meeting invite for that time." And it will start to build this agent. Now, for the sake of time, I actually ran this in advance here, so I can show you what it will build in a second here. And what it has built is an agent. It's a triggered agent. It's an email triggered agent. And so an email comes from you, and it will extract the time from it. It knows enough to extract it in ISO 8601 format, which is the format that the API takes, the Outlook API. Uh, it will check my calendar, and it'll create the meeting invite. And if I save this thing, this becomesA triggered agent that is now associated with my Outlook. So if you send me an email and you're requesting a meeting, you're gonna get an invite from me if I'm free.

    3. CVClaire Vo24:25

       Oh. I'm not gonna abuse it, but I do, I do love it. Um, what I would say is really interesting here is the ability to set up synchronous response to asynchronous, um, requests. Meaning, you know, probably when I email you, you are busy. You are in a meeting. You do not have-- I mean, I'm s- I'm, I'm projecting now, but, like, you don't have the time to look at your calendar and say, "Does this time work for me or not?" But you know when you have five minutes, you know, like, "Oh, I'm supposed to meet with Claire, and she needs to be at the top of my queue because we wanna get this podcast done." And so I'm gonna set up the system so as soon as she's ready, I'm ready. And I think that's a really nice flow. Again, I call this, like, burning down your anti-to-do list, which is if you can get yourself out of the critical path of doing a task and get AI into that path instead, you can be highly responsive and, and not drop stuff, which I think is, is really useful. And I will say we got this thing scheduled quite well. So-

    4. MCMarco Casalaina25:30

       I'm not sure

    5. CVClaire Vo25:30

       ... if you ran this on me, [laughs] it was really good.

    6. MCMarco Casalaina25:33

       Well, you know, you're, you're a priority, Claire, so-

    7. CVClaire Vo25:35

       Ah

    8. MCMarco Casalaina25:36

       ... naturally.

    9. CVClaire Vo25:36

       I-- You know. He knows how to flatter the ghost. Or flat-flatter the ghost? Oh, my God. You know how to-

    10. MCMarco Casalaina25:41

        [laughs]

    11. CVClaire Vo25:41

        ... flatter the host. It's that, it's that Halloween podcast we did. It's still here.

    12. MCMarco Casalaina25:46

        That's right. That, that was such-

    13. CVClaire Vo25:47

        Still in my head

    14. MCMarco Casalaina25:47

        ... a fun podcast that you're still feeling the ghosts of it today.

    15. CVClaire Vo25:50

        I

12. 25:51 – 27:17

    Demo: Setting up scheduled tasks in ChatGPT

    1. CVClaire Vo25:51

       am. Okay. And then so this is sort of a more kind of reactive style, um, agent that you built. What about a sort of like more, um, cron-based, like, timeline-based one? 'Cause you-

    2. MCMarco Casalaina26:04

       Right

    3. CVClaire Vo26:04

       ... you showed me how to do this in ChatGPT as well.

    4. MCMarco Casalaina26:06

       Let's do this. Yeah. So, like, what if you don't have M365 Copilot? Now, this same kind of function is showing up in the consumer general purpose agents also. So let's say that, again, you are a priority, Claire, and so if you have a new podcast, I really, really wanna know. So I can actually set ChatGPT now to do this. I can say, "Every day look to see if there's a new podcast by Claire Vo and notify me if there's a new one." And lo and behold, it absolutely does do it. It will daily at nine AM. I didn't actually even say what time to do it, but it decided on nine AM. Every day at nine AM, it's gonna check for new podcast episodes by you. And if I want, I can actually turn on desktop notifications so it will notify me on my desktop, like, boom, new Claire Vo podcast. But, uh, once again, I have effectively built a little ad hoc agent here. This is an ad hoc-

    5. CVClaire Vo27:06

       Right

    6. MCMarco Casalaina27:06

       ... agent that's triggered, in this case, on recurrence. It's like, as you say, a cron job. It runs every day, and it will do whatever it needs to do to check to see if there's a new podcast by you.

13. 27:17 – 29:14

    How AI automation changes time management

    1. CVClaire Vo27:17

       I, I love it. And so, you know, just looking back at, you know, the theme of this show, you're talking about setting up like these basically these little micro-agents that do little tasks for you, either one-off ones like we saw in Warp or recurring and triggered ones, um, like we saw in Microsoft and ChatGPT. And then this is making your l- life just easier. So let's jump into lightning round questions. I have a couple questions for you, which is, one, you know, now that you have this, uh, kind of army or constellation of agents working for you, how has it changed how you spend your time?

    2. MCMarco Casalaina27:56

       This saves me many minutes a day. I mean, just think about last night, uh, I was scanning, as I said, my daughter's, uh, homework, my daughter's practice test, and I set Warp to running that. You know, I said, "Okay, Warp, you know, go scan that for me." And while it did that, she and I worked on one of the math problems themselves. So rather than me fumbling with the scanning software, the crappy thing that says now feed this and it's letter size and all that stuff, I just told Warp to do it, it did it, and I did something else while these agents are doing whatever it is I need them to do.

    3. CVClaire Vo28:32

       Well, and the only, you know, only f- your only physical job was literally flipping the paper. So you still had-- I mean, you still had a role.

    4. MCMarco Casalaina28:40

       I, I had-

    5. CVClaire Vo28:40

       Very important part of the system

    6. MCMarco Casalaina28:41

       ... something I needed to do in this case. Yeah.

    7. CVClaire Vo28:42

       Yeah, I, I agree, and I, I think you would probably agree that the tasks that you do end up spending your time on are higher leverage, more intellectually stimulating, more strategic, all those things where we wanna spend our time versus, like, digging through rolodex trying to figure out is it, like, project owner or project admin that has the right permissions for this particular, you know, part of our stack. So I think, I think just spending your time differently is such a high impact, high impact, um, effect of AI.

14. 29:14 – 30:30

    Teaching AI skills to the next generation

    1. CVClaire Vo29:14

       What about-- Actually, you know, my second question is, you know, what about your kids? I, I-- You and I have done-- We did a little mini episode on Halloween about a Halloween app you did. You know, you've talked a lot about helping your daughter with homework. Are-- Do your, your kids have any interest in this? Are you teaching them how to do this or is it still Daddy, you know, facilitating the, the AI tooling in your house?

    2. MCMarco Casalaina29:37

       Well, I only have one daughter, and she is not like me. I mean, I'm a tinkerer, so I will try these things over and over again. If I fail today, I'll try it again tomorrow because in this world, AI changes every day, and what didn't work yesterday may well work today. So I will absolutely hammer away at this thing until it works. Uh, she is more, I, I would say, a mainstream user. She's certainly capable of using this stuff, and in fact, she is a wizard at Canva, I tell you. And, like, the Canva tool, the Canva, the agent that's built into that, she's really good at that stuff. She could design something up just like that, much better than I can, frankly. But she's not a tinkerer like me, so she, she doesn't proactively try these AI things. So-I don't really need to teach it to her per se. I feel like these are things that she is learning for herself and learning how it benefits her for herself.

15. 30:30 – 34:07

    Strategies for improving AI performance with AutoHotkey

    1. CVClaire Vo30:30

       Okay. And then my last question for you is, and I'm really interested to see this, because again, I think you're a pretty casual prompter. If I've, if I was to put you on the spectrum of formal to casual prompters, you are a casual prompter. Um, what is your tactic when AI is not listening, when it is not giving you the output you want? What do you do?

    2. MCMarco Casalaina30:53

       I mean, I sort of am, in which I will often be like, "You moron. I specifically told you not to check in my .env file, and you did it anyway."

    3. CVClaire Vo31:05

       [laughs]

    4. MCMarco Casalaina31:05

       Now, again, in Warp, there are rules. You might have noticed in my Warp rules, if you look closely, there's a rule there that says, "Never check in the .env file." You know, that environment file that sometimes has keys and stuff in it.

    5. CVClaire Vo31:15

       Yeah.

    6. MCMarco Casalaina31:16

       Uh, it, this is my, my pet peeve with all coding agents everywhere is that sometimes they just check in your .env files without you asking them to do that. But, you know, another one of the things that I do though, you know, I make rules in Warp, but not all of the AI tools that I, I use, uh, have rules. Now sometimes, for example, uh, I get these kinds of questions that I need to fill out, and I want to limit them in terms of their characters. So I also will pre-program certain types of prompts. And so here, let's say, uh, MBA five. So I have all these shortcuts like this.

    7. CVClaire Vo31:57

       [laughs]

    8. MCMarco Casalaina31:57

       And I can say, "Answer from the perspective of Microsoft in 500 characters or less with no bullets or formatting," if I just wanna give a quick answer to some question. And so I use this in a way that's repeatable-

    9. CVClaire Vo32:11

       Mm-hmm

    10. MCMarco Casalaina32:11

        ... to get these AI tools to do what I want them to do. That is, by the way, AutoHotkey that I have running there. So I have all these kinds of shortcuts that I can use with AutoHotkey that expand to repeatable prompts.

    11. CVClaire Vo32:24

        Question, did Warp help you make all those AutoHotkeys?

    12. MCMarco Casalaina32:28

        These I have, I think, made entirely myself. I have never-

    13. CVClaire Vo32:32

        Artisanally crafted.

    14. MCMarco Casalaina32:33

        That is true.

    15. CVClaire Vo32:34

        [laughs]

    16. MCMarco Casalaina32:34

        Artisanally crafted, well-tested.

    17. CVClaire Vo32:37

        I love it. So you're use- you're... you've, you've created a library of yourself of little snippets that you know are effective, that you can hotkey into your AI tools that you know you're gonna get exactly what you want.

    18. MCMarco Casalaina32:48

        Precisely.

    19. CVClaire Vo32:49

        I love it. Marco, this has been so great. I just... I love the idea of, again, just solving these minor, minor points of friction with our, you know, genius large language models and supporting tools. Where can we find you, and how can we be helpful?

    20. MCMarco Casalaina33:06

        Well, find me on LinkedIn. That's probably the easiest place. So you'll see me. I'm Marco Casalaina on LinkedIn, and I really do look like my picture.

    21. CVClaire Vo33:15

        [laughs] Perfect. And any- anything exciting coming up or YouTube channel? Any- anything that we can do to be helpful to you?

    22. MCMarco Casalaina33:24

        Uh, just follow my LinkedIn channel. You'll see that I make blog posts and videos every few weeks or month, and so you can see my new blog post and video there on my LinkedIn channel.

    23. CVClaire Vo33:36

        Amazing. Well, thanks for joining How I AI.

    24. MCMarco Casalaina33:38

        Uh, thank you for having me.

    25. CVClaire Vo33:40

        [upbeat music] Thanks so much for watching. If you enjoyed the show, please like and subscribe here on YouTube, or even better, leave us a comment with your thoughts. You can also find this podcast on Apple Podcasts, Spotify, or your favorite podcast app. Please consider leaving us a rating and review, which will help others find the show. You can see all our episodes and learn more about the show at howiaipod.com. See you next time.

Episode duration: 34:09