Pod Insights How I AI How Microsoft's AI VP automates everything with Warp | Marco Casalaina About this episode Marco Casalaina, VP of Core AI Products and AI Futurist at Microsoft, demonstrates how he uses AI tools to automate administrative tasks that typically consume valuable time. Rather than using Warp as a coding assistant (its primary marketed purpose), Marco leverages it to manage Azure resources, scan documents, compress videos, and more. He shows how these “micro-agents” can reduce friction in everyday workflows, allowing him to focus on higher-value activities. Marco also demonstrates how Microsoft 365 Copilot and ChatGPT can create triggered workflows that respond to emails or check for information on a schedule, highlighting how the line between consuming and building AI agents is blurring.
What you’ll learn:
How to use Warp to manage Azure resources and assign permissions without navigating complex web interfacesTechniques for automating document scanning and processing directly from the terminalMethods for analyzing and compressing video files using AI-generated FFmpeg commandsHow to create simple rules that dramatically improve AI performance for specialized tasksWays to build triggered workflows in Microsoft 365 Copilot that automatically respond to emailsHow to configure ChatGPT to perform scheduled tasks like checking for new contentStrategies for creating consistent AI interactions using AutoHotkey shortcuts—
Brought to you by:
Rovo https://rovo.com/—AI that knows your business
Lovable https://lovable.dev/—Build apps by simply chatting with AI
—
In this episode, we cover:
(00:00) Introduction to Marco Casalaina
(02:14) Why Marco chose Warp for administrative tasks
(03:57) Demo: Using Warp to manage Azure resources and permissions
(06:00) How CLI tools eliminate GUI friction for complex tasks
(07:18) Creating rules to improve AI performance for specialized tasks
(10:28) Demo: Document scanning automation
(13:00) Combining odd and even pages using a Python automation
(15:04) The value of ephemeral AI solutions vs. permanent tools
(17:12) Video compression using FFmpeg commands
(20:22) The concept of “ad hoc agents” for specific tasks
(22:31) Demo: Creating triggered workflows in Microsoft 365 Copilot
(25:51) Demo: Setting up scheduled tasks in ChatGPT
(27:17) How AI automation changes time management
(29:14) Teaching AI skills to the next generation
(30:30) Strategies for improving AI performance with AutoHotkey
—
Detailed workflow walkthroughs from this episode:
• How Microsoft's AI VP Automates Everything with 5 Micro-Agent Workflows: https://www.chatprd.ai/how-i-ai/microsofts-ai-vp-automates-everything-with-5-micro-agent-workflows
How to Create an Automated Meeting Scheduler with Microsoft • 365 Copilot: https://www.chatprd.ai/how-i-ai/workflows/how-to-create-an-automated-meeting-scheduler-with-microsoft-365-copilot
• How to Scan and Merge Two-Sided Documents into a Single PDF with AI: https://www.chatprd.ai/how-i-ai/workflows/how-to-scan-and-merge-two-sided-documents-into-a-single-pdf-with-ai
• How to Automate Azure User Role Management with AI in the Terminal: https://www.chatprd.ai/how-i-ai/workflows/how-to-automate-azure-user-role-management-with-ai-in-the-terminal
—
Tools referenced:
• Warp: https://www.warp.dev/
• Microsoft Azure: https://azure.microsoft.com/en-us
• Azure CLI: https://learn.microsoft.com/en-us/cli/azure/
• Microsoft 365 Copilot: https://www.microsoft.com/en-us/microsoft-365/copilot
• ChatGPT: https://chat.openai.com/
—
Other references:
• NAPS2: https://www.naps2.com/
• PyPDF2: https://pypdf2.readthedocs.io/
• FFmpeg: https://ffmpeg.org/
—
Where to find Marco Casalaina:
LinkedIn: https://www.linkedin.com/in/marcocasalaina/
—
Where to find Claire Vo:
ChatPRD: https://www.chatprd.ai/
Website: https://clairevo.com/
LinkedIn: https://www.linkedin.com/in/clairevo/
X: https://x.com/clairevo
—
Production and marketing by https://penname.co/. For inquiries about sponsoring the podcast, email jordan@penname.co.
Transcript Speaker names marked ? are inferred from speaking time and the show’s known hosts — they are not voice-verified.
0:00 Speaker 00 Warp is pretty magical, but you can add to the magic and make it work more smoothly.
0:04 Claire Vo? You're talking about setting up little microagents 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.
0:17 Speaker 00 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.
0:27 Claire Vo? 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.
0:44 Claire Vo? Welcome back to How I AI. I'm Claraville, 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 is going to speed run through five AI use cases where microagents 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.
1:28 Claire Vo? 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 dot com.
2:15 Claire Vo? Marco, thanks for joining How I AI. I am excited because we're going to see a tool, Warp, that we haven't yet seen on the podcast. And we're going to 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?
2:46 Speaker 00 I started using Warp 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 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.
3:15 Claire Vo? And if you're looking for the sexiest episode of How I AI, it is this, because we are going to show you how to manage Azure resources with AI, which actually, I'm making a joke because I think it's so funny, but these are the kinds of things that if you're a software engineer, or an engineering leader, 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 a tool like this.
3:57 Speaker 00 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.
4:08 Speaker 00 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 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 Azure, you know? 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 have taken me an hour. So instead, I do stuff like this. This is my prompt. I say, you know, I found Govind's email address in here to begin with.
4:48 Speaker 00 And then I'm like, okay, now give him Azure AI user and Azure AI project manager on this subscription that I'm looking at. And here 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, Warp is freaking great at that. And so it will call AZ repeatedly until it runs to the ground. Now here, I think it made a mistake somehow, whatever it was doing in AZ role, this one. It kind of made a mistake here. And then it got right back to it. And it did it.
5:33 Speaker 00 And it's like, okay, I'm done. And then I say, okay, actually, I need to give him contributor role on the whole subscription. And it does that too. No problem. And so I use this for all kinds of stuff here. But you know, for Azure administration and close your ears, Microsoft people, I have also used this to administer GCP. Works just as well with G-Cloud, the G-Cloud CLI. So it's it's great at this stuff.
6:01 Claire Vo? 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 want to see. And a meta thing I want to 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 GUI on these very complex, very interactive sets of permissions, capabilities, configurations. It's actually a really hard design problem. It's like a very hard, you know, front end design problem.
6:42 Claire Vo? 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 get a job done. And then I have to call out a second thing, which is you're also doing what?
7:24 Claire Vo? 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, 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.
7:54 Speaker 00 Totally. Yeah, exactly. Now, I will tell you, though, that There is 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 of ways you could do that. I mean, if you think about what I did with AZ really, if you look at my MCP servers, well, this one's off right now, but I do connect this to the Microsoft Docs MCP server when I'm doing Azure administration. Because sometimes, you know, in this case, I knew exactly what roles I wanted to give Govin. 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." And like, you figure it out, right?
8:38 Speaker 00 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. Another piece of this, and we'll see it again in a moment, is the rules. So now, originally, like, out of the box, 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,
9:24 Speaker 00 did you activate your owner access?" Before I start doing this, because otherwise it's gonna fail. So you can give it these rules and MCP servers that kind of help it along and help it use this stuff. Of course, that's useful for coding as well. But, you know, I find it super useful for these kinds of things that I use it for.
9:42 Claire Vo? Well, and what I will call out, and this is no shade, but this is not the most sophisticated prompting I've ever 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 always use the CLI tool. And so I actually love looking at your prompting here because it's very conversational. And I think people get like wrapped around the axle on like my prompts have to be in a 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
10:23 Claire Vo? to follow are what makes things more effective. 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 want to walk us through how you did, how you did that with your, your daughter's homework?
10:56 Speaker 00 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 practice test. And so I needed to scan the odd pages and then I needed to scan the even pages
11:39 Speaker 00 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 file name and it does. It totally does do that. And so it figures that out and done, it's done.
11:54 Claire Vo? Wait, can I, can I pause you really quickly? Did this activate the scanner?
11:59 Speaker 00 Absolutely it does.
11:59 Claire Vo? What? Okay.
12:01 Speaker 00 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.
12:09 Claire Vo? So you didn't even have to press the little button and pop open the thing and you just, okay.
12:14 Speaker 00 All I had to do was put the sheets in the feeder and as soon as I typed this thing in, boom, there it goes.
12:19 Claire Vo? 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, but this is, this is a peak, peak efficiency, efficiency for me is being able to just remotely start the scanner from, from my AI coding tool.
12:40 Speaker 00 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 scanned those in too, because it's easy, right? It only takes me a second. Then I typed this in here and now there it is.
13:00 Claire Vo? Okay. So you scanned one side.
13:02 Speaker 00 I scanned one side. Now 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. So you, the second time I did this, it had generated this command line here.
13:16 Claire Vo? Oh.
13:17 Speaker 00 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 changed 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. I guess it installed PyPDF2 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. But you know, it did it. I mean, in the end, absolutely, it most certainly
14:02 Speaker 00 did create a unified thing.
14:06 Claire Vo? Now, I have to give these AI coding tools and IDEs, etc., 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 have done it before, which is you would have walked over to your scanner, which I have one right here, I would have pulled up the terrible native scanner software, you know, if you know it, if you know, you know. And I would have 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
14:47 Claire Vo? like dragged and dropped the pages in the right, the right order and then saved that file and it would have been so, so, so annoying. And instead, you get to sit where we all want to live right now, which is in the terminal, in the terminal in dark mode and just ask it to 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 Warper generating, a lot of stuff on your computer, you're able to do programmatically.
15:18 Speaker 00 Right.
15:18 Claire Vo? 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.
15:34 Speaker 00 Well, what's interesting is it caused me to look for ways that I could do things with a 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 NAPs 2. So if you look at my rule for this, and I, what I said is, when you're in Windows and I tell you to scan something, use NAPs 2 to do it. And I gave it the location of where I installed this thing called NAPs 2, 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 scanned things so frequently that this would save me a vast amount of time. So, you know, again, like, it's magic, but it's not entirely magic.
16:19 Speaker 00 You do have to do a little preparation for this trick to work.
16:23 Claire Vo? 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.
17:05 Claire Vo? Get started for free at lovable.dev. That's lovable.dev. 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 HowAI, which is, we're gonna do Azure role, role assignment, we're gonna do drivers for your scanner that can be run via the CLI. And then you have one more use case, which is-
17:32 Speaker 00 I do.
17:32 Claire Vo? -as somebody who does a podcast and works with a lot of videos, is really useful, that I thought maybe you could walk us through.
17:40 Speaker 00 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 yesterday, 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
18:25 Speaker 00 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, it looks at the file and it's like, okay, the video is 1.7 gigs because it has a huge bitrate 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.
19:10 Speaker 00 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.
19:19 Claire Vo? Yeah. And so 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 of 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 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
20:02 Claire Vo? 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 case. Like we do so much file generation, but I actually think file manipulation is a really underappreciated use case of AI.
20:22 Speaker 00 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 kind of 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.
20:58 Claire Vo? Yeah, and what I would say is also, 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 going to 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, do it over again. Maybe save a rule so you're not rediscovering the steps.
21:32 Speaker 00 Right.
21:32 Claire Vo? But like, you don't need to build a whole, a whole thing here.
21:36 Speaker 00 And that's, that's exactly the right idea, right? So when, 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? 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.
22:10 Claire Vo? You know, I'm not saying I love AI more than humans, but sometimes it would be really, really nice to be able to get that consistency out of the people around me. You know, perhaps my, my, my children, who, who are not loaded with rules and context all the time and consistently help.
22:30 Speaker 00 No.
22:31 Claire Vo? 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-based things to...
22:48 Claire Vo? Kind of be prepped for the work you need to do in a day.
22:51 Speaker 00 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 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 going to kick this thing off. And what I said here is when I get an email from Claire requesting a meeting at a certain time, check my calendar.
23:32 Speaker 00 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 with the Outlook API.
24:08 Speaker 00 It will check my calendar and it'll create the meeting invite. And if I save this thing, this becomes a triggered agent that is now associated with my Outlook. So if you send me an email and you're requesting a meeting, you're going to get an invite from me if I'm free.
24:25 Claire Vo? I'm not going to abuse it, but I do, I do love it. What I would say is really interesting here is the ability to set up synchronous response to asynchronous 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, I'm, I'm projecting now, but like you don't have the time to look at your calendar or 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 want to get this podcast done. And so I'm going to set up the system. So as soon as she's ready, I'm ready. And I think that's a really nice flow.
25:10 Claire Vo? 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 if you ran this on me, it was really good.
25:33 Speaker 00 Well, you know, you're a priority, Claire.
25:35 Claire Vo? So. You know, he knows how to flatter the ghost or flatter the ghost. Oh, my God, you know how to flatter the host. It's that it's that Halloween podcast we did is.
25:46 Speaker 00 Right, that was such a fun podcast that you're still feeling the ghosts of it today.
25:50 Claire Vo? I am OK. And then so this is sort of a more kind of reactive style agent that you built. What about a sort of like more cron based, like timeline based one? Because you showed me how to do this in chat GPT as well.
26:06 Speaker 00 Let's do this. Yeah, so like, what if you don't have M three sixty five co pilot? 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 want to know. So I can actually set chat GPT now to do this. I can say every day, look to see if there's a new podcast by Claire and notify me if there's a new one. And lo and behold,
26:36 Speaker 00 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 going to 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 podcast.
26:59 Speaker 00 But once again, I have effectively built a little ad hoc agent here. This is an ad hoc 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.
27:17 Claire Vo? 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, like we saw in Microsoft and ChatGPT. And then this is making your life just easier. So let's jump into lightning round questions. I have a couple of questions for you, which is one, you know, now that you have this kind of army or constellation of agents working for you, how has it changed how you spend your time?
27:55 Speaker 00 This saves me many minutes a day. I mean, just think about last night, I was scanning, as I said, my daughter's 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 its 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.
28:32 Claire Vo? Well, and the only, you know, only, your only physical job was literally flipping the paper. So you still had, I mean, you still had a role.
28:39 Speaker 00 I had nothing I needed to do in this case. Yeah.
28:42 Claire Vo? 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 want to spend our time versus like digging through role docs, 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, a high impact effect of AI. What about, actually, you know, my second question is, you know, what about your kids? I, you and I have done, we did a little mini episode on Halloween about Halloween app you did. You know, you've talked a lot about helping your daughter with homework.
29:28 Claire Vo? Do your kids have any interest in this? Are you teaching them how to do this? Or is it still daddy facilitating the AI tooling in your house?
29:37 Speaker 00 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. And 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.
29:59 Speaker 00 She is more, 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 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.
30:30 Claire Vo? 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 put you on the spectrum, a formal to casual prompters, you are a casual prompter.
30:45 Claire Vo? What is your tactic when AI is not listening? When it is not giving you the output you want? What do you do?
30:53 Speaker 00 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. Now, again, in Warp, there are rules. You might have noticed in my Warp rules, if you look closely, there is a rule there that says, never check in the .env file. You know, that environment file that sometimes has keys and stuff in it?
31:15 Claire Vo? Yeah.
31:16 Speaker 00 This is 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 use have rules. Now, sometimes, for example, 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, M B O five. So I have all these shortcuts like this.
31:57 Speaker 00 And I can say, "Answer from the perspective of Microsoft in 500 characters or less with no bullets or formatting, if I just want to give a quick answer to some question."
32:07 Speaker 00 And so I use this in a way that's repeatable to get these AI tools to do what I want them to do. That is, by the way, auto hotkey that I have running there. So I have all these kinds of shortcuts that I can use with auto hotkey that expand to repeatable prompts.
32:24 Claire Vo? Question, did Warp help you make all those auto hotkeys?
32:27 Speaker 00 These I have, I think, made entirely myself. I have never-
32:31 Claire Vo? Artisanally crafted.
32:33 Speaker 00 That is true, artisanally crafted, well-tested.
32:37 Claire Vo? I love it. So 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 going to get exactly what you want.
32:48 Speaker 00 Precisely.
32:49 Claire Vo? I love it. Marco, this has been so great. I just, I love the idea of, again, just solving these 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?
33:06 Speaker 00 Well, find me on LinkedIn. That's probably the easiest place. So you'll see me on Marco Castellana on LinkedIn, and I really do look like my picture.
33:16 Claire Vo? Perfect. And anything exciting coming up or YouTube channel? Anything that we can do to be helpful to you?
33:25 Speaker 00 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.
33:36 Claire Vo? Amazing. Well, thanks for joining How AI AI.
33:38 Speaker 00 Thank you for having me.
33:41 Claire Vo? Thanks so much for watching. If you enjoyed this 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.
Previous From journalist to iOS developer: How LinkedIn’s editor builds with Claude Code | Daniel Roth Next How Stripe built “minions”—AI coding agents that ship 1,300 PRs weekly from Slack reactions | Steve Kaliski (Stripe engineer) Page updated October 31, 2026 · transcript and summary are machine-generated