How Block’s custom AI agent supercharges every team, from sales to data to engineering | Jackie Brosamer & Brad Axen

VP of engineering Jackie Brosamer and principal engineer Brad Axen join me to demo Goose, Block’s open-source AI agent that runs locally, plugs into your existing tools through model context protocol (MCP) servers, and peels away the rote parts of work so people can focus on insight and impact. This episode is packed with in-depth demos: starting with a messy farm-stand sales CSV, Goose analyzes the data, builds visualizations, and generates a shareable HTML report. We then spin up an MCP that lets Goose talk to Square’s dashboard for inventory management, vibe code an email MCP that can send payment links automatically, and unpack how environment setup, debugging, and tool orchestration get handled behind the scenes. What you’ll learn: A practical, repeatable workflow for turning any working script or function into a custom MCP—and exposing it to natural-language controlHow to transform messy CSVs into visualizations, HTML reports, and actionable business insights without needing a data science backgroundWays to hook Goose into live business systems (e.g. Square inventory, payments) so analysis flows directly into operational actionThe thinking behind Block’s decision to open-source GooseLessons from Block’s bottom-up meets top-down adoption modelWhy organizational transformation, not just picking the right LLM, will separate AI winners from laggards over the next few yearsHow to scale an internal MCP catalogThe organizational transformation required to fully leverage AI capabilities— Brought to you by: CodeRabbit https://coderabbit.link/howiai—Cut code review time and bugs in half. Instantly. Lenny’s List http://maven.com/lenny—Hands-on AI education curated by Lenny and Claire — Where to find Jackie Brosamer: LinkedIn: https://www.linkedin.com/in/jbrosamer/ — Where to find Brad Axen: LinkedIn: https://www.linkedin.com/in/bradleyaxen/ — 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 — In this episode, we cover: (00:00) Introduction to Goose and its data analysis capabilities (02:27) How Block embraced AI across the organization (04:48) What Goose is and why Block open-sourced it (07:45) Demo: Analyzing farm-stand sales data with Goose (12:18) Creating shareable HTML reports from data analysis (14:15) Model context protocols (MCPs) that Goose uses (18:56) Demo: Using Square MCP to create a product catalog (23:35) Creating payment links from analyzed data (26:30) Demo: Building a custom email MCP (31:18) Testing the new email MCP with Goose (36:09) Debugging and fixing MCP code errors (38:44) Connecting workflows: sending payment links via email (41:30) Lightning round and final thoughts — Tools referenced: • Goose: https://block.github.io/goose/ • Pandas: https://pandas.pydata.org/ • Plotly: https://plotly.com/ • Python: https://www.python.org/ • ChatGPT: https://chat.openai.com/ • Claude: https://claude.ai/ • Cursor: https://www.cursor.com/ • Mailgun: https://www.mailgun.com/ — Other references: • Block: https://block.com/ • Model context protocol (MCP): https://www.anthropic.com/news/model-context-protocol • GitHub: https://github.com/ — Production and marketing by https://penname.co/. For inquiries about sponsoring the podcast, email [email protected].

Speaker names marked ? are inferred from speaking time and the show’s known hosts — they are not voice-verified.

• 0:00Speaker 00

  Goose is our AI agent. We kind of designed it to be really agnostic. You tell it what you needed to do by connecting it to different capabilities, and it can just solve any problem. What I'm going to do is take that CSV that Jackie was working with. I'm just going to pop it over and I'm going to say, can you read through this data? Use it to create items in my square dashboard.

• 0:22Claire Vo?

  So we took a CSV that we didn't even have to look at, that probably had data that was not in this exact format, and you created a product catalog.

• 0:30Speaker 02

  What a lot of my work and what my team is trying to do is not just make it faster for someone like me or on my team who has data expertise to go through this, but to allow our finance team, our sales team, anyone in the company to be able to dig in and self-serve a lot of this data rather than having to ask an expert and wait for that to come back.

• 0:48Claire Vo?

  You have been the first person that's told me it was the salespeople that were begging for it. We hear so much, you know, engineers are leading in and they want to vibe code and they want to do all that. But it's nice to hear that the folks close to customers and close to revenue are also seeing the value.

• 1:06Claire Vo?

  Welcome back to How I AI. I'm Claire Voe, product leader and AI obsessive here on a mission to help you build better with these new tools. Today, we're speaking with Jackie and Brad at Flock, who are going to show us how their open source AI agent, Goose, can be used to do everything from vibe data analysis to vibe coding and MCP. Let's get to it. This episode is brought to you by CodeRabbit, the AI code review platform, transforming how engineering teams ship faster with AI without sacrificing code quality. Quality code reviews are critical, but time-consuming. CodeRabbit acts as your AI copilot, providing instant code review comments and potential impacts of every pull request, beyond just flagging issues.

• 1:50Claire Vo?

  CodeRabbit provides one-click fix suggestions and lets you define custom code quality rules using AST grep patterns, catching subtle issues that traditional static analysis tools might miss. CodeRabbit brings AI-powered code reviews directly into VS Code, Cursor, and Windsor. CodeRabbit has so far reviewed more than 10 million PRs, been installed on 1 million repositories, and has been used by 70,000 open-source projects. Get CodeRabbit free for an entire year at coderabbit.ai and use the code HOWIAI. Thanks for being here. Thanks for having us.

• 2:30Speaker 00

  Yeah, excited to chat.

• 2:31Claire Vo?

  I am so excited to have you two on HowI AI because I have been so impressed how Block has, as a full organization and a large organization at that, really embraced AI, it seems, everywhere and for everything. And, you know, everybody's worried about AI-native startups, but you're one of the companies that I really think is going there very fast as a much larger organization. So how did you lean in as an org so fast and so broad?

• 3:03Speaker 02

  I think it's a combination of both like bottoms-up and tops-down. We saw, you know, a lot of concentrated pockets. Once ChatGPT came out, that we're really finding a lot of value out of these tools. For example, salespeople, they're like, I, any tool, give it to me, like, I'll use it, help me get those leads. And we also saw a lot of engineers, you know, starting to lean in as these tools became really good at coding. And kind of as that started from the bottom, I think a lot of our leadership saw a lot of promise, and they've been, you know, trying to make some of those practices a little bit more consistent among groups. I think that it's really a great time to focus on organizational transformation, because to me, that's really what's going to define who ends up the winners in whatever this AI future is, is who not just leans into this technology, but even

• 3:48Speaker 02

  more than that leans into the organizational transformation, which can in a lot of ways be even harder. It's like really easy to get a technology to go exponentially, and humans don't go exponentially so well.

• 3:59Claire Vo?

  You have been the first person that's told me it was the salespeople, it was the salespeople that we're begging for. We hear so much, you know, engineers are leading in, and they want to vibe code, and they want to do all that. But it's nice to hear that the folks close to customers and close to revenue are also seeing the value.

• 4:16Speaker 02

  Yeah, I think it's, you know, everyone finds like that different first use case that really gets them hooked. And one of the things I've been really impressed with, with some of our Non-developers especially, like we all kind of know how people use it for Vag coding, and I think that's like well discussed is non-developers are just so creative and so tolerant of like stringing together a bunch of different tools just in a way that you never would have imagined. And that's, I think, really going to be the power is getting these tools closer to the people that actually understand the problems and see what wacky things they come up with with this new technology.

• 4:49Claire Vo?

  Not only are you all leading the way in terms of how organizations, and I totally agree with you, I think the biggest transformation is cultural and operational. The tech piece is like a lagging piece of it, you can figure out. But what I also love about what you're doing is not just how you're embracing it internally, but how you're trying to drive and help others adopt it externally. And so I'm wondering if you could tell us a little bit about the adorably named Goose and what Goose is and why you all built it.

• 5:18Speaker 00

  So Goose is our like AI agent. And there's a lot of people have a lot of different definitions for what an AI agent even is now. But I'll say specifically, what we mean by that is it's powered by an LLM, but it has a whole collection of tools that it's going to go use to solve problems for you. And this is like something we're really excited about in part, just because it lets us like build for ourselves and like come up with workflows that work for our company. But like you said, we open sourced it because we think there's a lot of extensibility for everybody. And we kind of designed it to be really agnostic. Like you, you tell it what you needed to do by connecting it to different capabilities, and it can just kind of solve any problem. And I think we'll get to show some of that

• 5:59Speaker 00

  today. And that's all powered by MCP. So that's a big part of this like open source puzzle is how do we make this work, no matter what you want it to do. And MCP really helped us get in like early into helping to establish the protocol and have a way for us to connect it to anything. And people can develop their own MCPs and just make things work.

• 6:21Claire Vo?

  Got it. So you, and I just want to show here, it's up on GitHub, it's open source, it's your agent, your agent framework powered a lot, it seems, by MCPs, which I think we're going to talk about later, that anybody can can use and extend extend upon.

• 6:38Claire Vo?

  And what made you all think about open sourcing this?

• 6:40Speaker 02

  Yeah, open source is, I think, a really big emphasis just as a value for our company. And I think there's two ways we think of it. Number one, this is just like the right thing to do, you know, for the world in some way. But then there's also, we think that there's so much benefit in terms of having this open ecosystem and really seeing these patterns emerge from not just, you know, the engineers that we have in our company, but from engineers all over the world. And I think we're really seeing that come to fruition with a lot of the growth that we've seen in MCP, you know, and all the MCP servers that are out there. And it's only been, you know, what, like six, eight months?

• 7:14Claire Vo?

  Yeah.

• 7:15Speaker 02

  And then I think we also wanted to really lean into open source in order to take advantage of all these different models that are coming out. A lot of the tools that come bundled, you know, released by these different model providers can only use like that kind of models. And we know that every month a new model's coming out. One might be better at coding, one might be better at writing. And we think there's a huge amount of power in being able to bring together data across all these different MCPs and then also pair that with really any model that you want.

• 7:46Claire Vo?

  Okay, so speaking of data, I think you're going to show us how to do vibe data analysis, which is a first for HowIAI. So it's a flow that you use internally. So this is definitely something, we're not making it up. You use this exact flow day to day, but we're going to use some fake data so we can screen share and really get into how it all works. And so Jackie, what kind of business are we today that we're going to do some data analysis with?

• 8:13Speaker 02

  Yeah, so I tried to make this as realistic as possible. When I don't work in tech, I actually have a small farm that is not very profitable. And so we're going to be doing some analysis that I've actually done with my own internal data that kind of shows us how we can look at some business data and make some recommendations. And so what we're going to do is go ahead and look at this to try to find this local CSV of data that has July data for my farm stand, which Does a bunch of vegetables and what we've asked is we've asked Goose to use Pandas, which is a Python library, to tell me the items how to have the best revenue and like what

• 8:57Speaker 02

  the busiest days of the weeks are. And then I left a general kind of question at the end. Just what are some trends? Because I think it's always interesting when you get a slightly different result as you run this. And so you can see the first thing that we're doing here is it's using Rip Grab to find the CSV. And we found that Rip Grab is actually really effective, even though it's really simple. There's a lot you can get done with it versus something fancier like a semantic search. It identifies this July data at CSV. Then it writes a Python command. It found some error where it didn't have this installed. Oh, no, this is maybe going into cursed virtual environment territory, but it looks like it's going to solve itself.

• 9:40Speaker 02

  Sometimes I'll tell it like, check your Python environment so that it makes sure it sources it, but it decided to go ahead and create a new virtual environment here. One of the things I really like about Goose is I'm terrible at maintaining developer environments. And so it'll go through and try to just like debug that for me.

• 9:55Claire Vo?

  I mean, how many of us, maybe this is a very niche comment, have been victimized by trying to get the right version of Pandas installed? Because I definitely have. Okay. And just taking a step back, we didn't see the input data, but is this just like general day by day sales of different products?

• 10:10Speaker 02

  Exactly. This was just a list of, you know, item, quantity, date, price. And so from that, it's able to go through and say, okay, you know, your top generating, your top revenue generating items are berries. We love berries, very high margins. And it's got, the best days are like Thursdays. And so and then I just had this, you know, bonus question of like, what are some key items and trends? It'll kind of lead into some stuff later. So cherries have the highest average value. It goes through, you know, what are your mid, high, low items? And then, you know, goes through some weekly patterns. And so without even asking, of course, it comes out with some recommendations, which I really love.

• 10:50Claire Vo?

  Let's just pause on these recommendations. So what I love about this is you have this ugly file. You probably could have. Tossed in a spreadsheet or done some of this analysis yourself and you're you're doing sums and you're doing pivot tables and you're trying to explore this and you probably have to do different tabs for all these different analyses and this you can really drop in and it's maybe a relatively if you scroll up it's you know relatively simple analysis by day by product but under the hood you have this pretty powerful data analysis package and so I'm presuming you can go from this level of analysis to something much, much deeper.

• 11:24Speaker 02

  Yeah, that's right. And I when I'm doing something like this live with something like goose, what I'll usually do is kind of you know, have it take a high level first pass and then you know, dive into specific sections and say like, hey, can we go deeper here? You know, use this particular type of method, you know, do a line regression that tries to figure out price elasticity or something like that.

• 11:42Claire Vo?

  Well, and I have to say, as a mom of young boys, I do feel like I spend, you know, $1,500 on strawberries every month. So this is really hitting home. Okay, so we can go down and then I'd love to see, I like the idea of when you're prompting a data analysis to say, give me the data analysis, but also give me some recommendations. And so it's really saying here, you know, high margin items, which is great. Uh, look at why Friday drops because you know, maybe they would expect that to be a higher day, weekend sales and then some, oh, price adjustments. That's really interesting. So what would you do next after this?

• 12:20Speaker 02

  Yeah, so I don't think that this is like very good to share. And so a lot of times what we see is that people really like to share these kinds of analyses as local webpages, especially people who aren't technical or just a whole new world is opened up with them to them as they figure out how to use AI to turn some of the stuff into HTML and share it with each other. We see a lot, we have a way for people to use goose to share these internal static websites and we see that really popular, especially among, you know, some of our business users that want to kind of create their own dashboards for, you know, whatever.

• 12:52Claire Vo?

  Well, this is generating, I'm just reflecting on what I've seen so far. So it seems like Goose has sort of a virtual machine in which it can write code and wrestle with Python dependencies. Love that for Goose. It has the ability to spin up hosted HTML and websites. Is that right? Is that what it's kind of doing here?

• 13:10Speaker 02

  So it's all running locally. I think that's one thing that's like really unique about Goose. And part of the reason, you know, we started that way is that we, a lot of our developer environment stuff happens locally. And so that was like a really natural fit. And then we also saw within the open source community that this has actually been really popular with kind of the crowd that really wants to maintain end to end control over their workflows. One of the things we've seen with Goose is that some of the most promising use cases are, you know, you tell Goose to do something, you kind of go away and, you know, wait for that task to complete as it does things like, you know, write code errors.

• 13:46Claire Vo?

  Oh.

• 13:47Speaker 02

  And so it pops, it's also cool because it can, it went ahead and popped this up for me.

• 13:52Claire Vo?

  Yep.

• 13:52Speaker 02

  This is not the prettiest website it's ever made with this fake data, but you can see, you know, it's able to make these bar charts with Plotly. And I could go ahead and dig in and try to refine this if I wanted it to be, you know, a little bit more well-designed.

• 14:07Claire Vo?

  Got it. And, you know, if I was being cheap and easy about sharing it, I would just print as a PDF and shoot it over and it would look nice.

• 14:15Speaker 00

  When we run this internally, we have an MCP that it connects to where you can just publish it to the company, like kind of keep it internally private, but share it with anybody.

• 14:24Claire Vo?

  And what are the MCPs sort of out of the box that if I cloned the Goose repo right away, would it have ready to go? And then what are some kind of ones that you've either built or integrated, specific to maybe what you do at Block?

• 14:40Speaker 02

  Yeah, so we have like a collection of different MCPs.

• 14:45Speaker 02

  Some of them we've taken from the open source community, some of them we've developed internally because, you know, for example, we have an internal data MCP that I use every day that helps, you know, sort through where's the revenue for X product. I mean, it knows all that context. And we're also working on trying to have external MCPs, you know, connect to our business products. A lot of what people are using use for and a lot where we saw the first value is just MCPs that connect to all of our key internal systems. So Google Drive, probably the one I use the most. Brad mentioned this one we have internally called BlockCell that's really popular because it's a click of a button, you know, you can publish a website and send a URL to anyone in the company. We also have a developer extension that does a lot of this like command line and tool stuff.

• 15:30Speaker 02

  We also have a computer controller one that just did, and that's how it just opened this Chrome window.

• 15:35Claire Vo?

  Got it. Cool.

• 15:36Speaker 00

  That's the stuff that bundles with Goose. So when you get it, it's like you're going to have like five really simple, like memory developer.

• 15:43Claire Vo?

  Yep.

• 15:44Speaker 00

  And then when we use it internally, we have like 40 or 50.

• 15:48Claire Vo?

  Yep. And Jackie, how often are you doing an analysis like this in your week using Goose?

• 15:56Speaker 02

  Um, if I'm doing an analysis, I'm using Goose. The question is more like, how many analyses do I do per week? I would say that I probably actually use it more in my day to day life for writing. But there's people in my team that, you know, are professional analysts or professional data scientists that are doing this, you know, every day. And I think increasingly what a lot of my work and what my team is trying to do is not just make it faster for someone like me or on my team who has data expertise to go through this, but to allow our finance team, our sales team, you know, anyone in the company to be able to dig in and like self-serve a lot of this data rather than having to ask an expert and wait for that to come back. I think we've all been talking about like the age of self-serve data

• 16:40Speaker 02

  for a long time and it's like kind of gotten better, but we all know that you usually still go after data scientist. And so I think it's really interesting to think about how can we, you know, kind of short circuit that and allow everybody to focus less on kind of. The wrote parts of data analysis and spend more time talking about, you know, the insights and the context and the creative parts that we all want to spend our days on.

• 17:05Claire Vo?

  Okay, so we've talked about the salespeople love their AI, the farmers love their AI, but can we please get back to what people can wrap their head around, which is the software engineers. So you have this, you have this great, great data and you want to do something with it. And so you have this data, you know, maybe you want to do something with it to improve your business. Brad, what's the next step in your mind here?

• 17:31Speaker 00

  Yeah, let me, let me share some on my screen this for this and we can show a little bit about like how a developer can build MCPs and use that to actually like connect to what someone is doing into like existing products or to like solve new problems. And this is really how I spend my day to day. Like, I feel like at this moment in time, I'm, I'm just developing MCPs left and right.

• 17:54Claire Vo?

  And I'm going to just pause right there because no matter how many times people hear it, they still need an MCP explained to them. So we're going, Brad, we're going to take your explanation of what is an MCP.

• 18:05Speaker 00

  Let me do that by showing you the page for it in Goose here. So in, in this, we have a, just this huge collection of extensions in Goose and these are all implemented with Model Context Vertical. So each of these is an MCP server. And what that means is that it has a collection of tools that it exposes to the agent. And it can do a couple of other things like provide data resources and all that other stuff. And so it's, it's like a protocol that lets the agent talk to a third party and get things that it can do and data it can read. And most importantly, it's kind of the arms and legs for the model. So this is how the model goes and interacts with the real world and like makes changes in online systems.

• 18:48Claire Vo?

  Okay, so you're spending. All your time building MCPs. It seems like everybody is spending all their time building MCPs. So why don't you walk us through how you're spending your, your days?

• 18:59Speaker 00

  Yeah. And so let me start by showing you an existing one before we start building. And so I've turned on a real square MTP server. So this is like from, this is available like as an online MTP server that people can use to like run their business. So this is my Square dashboard and it's totally empty right now. This is a kind of an account I set up for the sake of the demo. And we're going to connect that through our agent and actually have it fill things in. So what, what I'm going to do is take that CSV that Jackie was working with. I'm just going to pop it over and I'm going to say, um, can you read through this data? And use it to create items and vice versa.

• 19:44Speaker 00

  Dashboard. And so this is something that you could do with all kinds of input formats. Like for example, I could give it an image and like maybe a picture of a menu or something like that. And so since it's multimodal, it's just going to go figure out that source, translate it into the API calls that it needs.

• 20:02Claire Vo?

  And I'm thinking as a product builder who has built many import your data products, where you're always trying to say like, it has to be a CSV in this format, in these columns with this column name. And what I've just realized this opens up for you is like, drop in your arbitrary messy whatever data. Don't have to reformat it. Let the MCP figure out the translation.

• 20:25Speaker 00

  Exactly.

• 20:25Claire Vo?

  And then get it into the system. Okay.

• 20:27Speaker 00

  Yeah. So it doesn't matter what you've got. It's going to figure out, it could be a PDF, whatever. It's going to do its best to like, figure out how to make that work. You know, the first thing it does is it just reads it. And uh, it's then going to go, this is actually a really interesting part. I think the Square team did a great job designing this MTP, because it has so many different things that you can do on Square, that it's like too much for the model to handle all at once. So what it actually does under the hood here is it, is it says like, oh, if you need to know about catalog, I give you a method to look up what you can do in catalog. And then under the hood, the LLM is seeing like all of these operations that it can now access. So all that stuff about like creating items, they've figured out.

• 21:11Speaker 00

  Um, okay. And I actually see the, uh, it's like, this is a funny, I normally would just read the CSV. So I'm like, I'm like laughing a little bit at like how much work it's going through for this, but uh, it is what it is.

• 21:25Claire Vo?

  I know I have, I have that same experience using like a cursor max mode where I'm like, I just don't know if you need to work to think that hard.

• 21:33Speaker 00

  Exactly.

• 21:33Claire Vo?

  How to do this, but you know, it's not my brain, it's the AI's brain.

• 21:37Speaker 00

  Yeah, yeah. So we'll, we'll see, I'll let it cook for a minute here. And see how it figures this out. But effectively what's happening is it's just deciding to use uh, shell commands to grab the prices from that CSV. And then it's going to turn that into an API request and actually send it to uh, the square dashboard and create like a product category and then fill in the items. So we should just be one request away from getting that solved.

• 22:05Claire Vo?

  Got it. And you know, instead of sitting here and waiting, Jackie, I'm presuming Farmer Jackie would have to go in here and one by one sort of enter, enter this data in and make sure it's right and all that kind of stuff.

• 22:19Speaker 02

  Uh, one of the like really underappreciated uh, things about LLMs is like how much they function is like data duct tape. You know, it's like, it doesn't quite fit. You can do something to just kind of make it all mush together.

• 22:31Claire Vo?

  Yep.

• 22:32Speaker 02

  And that's where a lot of the day-to-day data work is, is trying to match all those things.

• 22:36Claire Vo?

  How I AI is now on Lenny's list with my personal selection of the best AI engineering courses on Maven. You can spend months thinking and playing with AI before really integrating it into your workflow or shipping an actual AI feature. If you want to start building, then these hands-on Maven courses are for you. Learn directly from Aishwarya Narash Raghanti, MIT instructor and AI scientist at AWS, or Sander Shuloff, who has authored research with OpenAI, Hugging Face, and Stanford. To pivot into an AI role or successfully lead your company's next AI initiative,

• 23:18Claire Vo?

  visit maven.com slash Lenny to enroll now. Use code Lenny's list for a hundred dollars off. That's M A V E N dot com slash Lenny to get ahead in the AI era and start building.

• 23:36Claire Vo?

  Okay, look at that. So we took a CSV that we didn't even have to look at. That probably had data that was not in this exact format. And you created a product catalog out of it.

• 23:48Speaker 00

  And this is something like I could follow up with this and say like, okay, grab images or even generate images and like.

• 23:54Claire Vo?

  Yeah, that's what I was gonna ask.

• 23:56Speaker 00

  Yeah.

• 23:56Claire Vo?

  I wanna, I wanna AI-generated apple image.

• 23:59Speaker 00

  Exactly, yeah. And the, um, I'll skip it for the sake of time, but like, there's so much you can do to just like navigate through all of this. And this is something where like, we're watching it live for the sake of the demo, but what really the best version of this is like, handed the CSV and walk away and come back and then you're gonna just see that this is done. And so that kind of like background task thing is the, I think the best mode for Goose in a lot of ways. But yeah, it like goes and figures this out and this is like a real account. So what's cool about this is that this isn't just like a little website showing that I have prices for apples. It's something I can take payments with. So I can now say, um, okay, let's make a payment link for three pumpkins. And we'll let that run for a little bit too.

• 24:43Claire Vo?

  This is not, this is not the topic I thought I was gonna get from you all today. You know, I had a lot of things in mind, but using AI to generate farm stand payment links for gourds was just not on the top of my list this, uh, this afternoon, but I'm excited to see it. Okay. So I think, you know, one of the other things that I think, and I know this is running locally and we won't get into like sort of the local mobile debate right now, but I just think that the ability to do this stuff via text on the go is so powerful. Imagine somebody wants to buy the three pumpkins off the back of your truck and you wanna be able to do this really easily.

• 25:24Claire Vo?

  This sort of like ability to just type in a, a, a short command to get a really custom software solution. Um, backed by, you know, either a platform or not, I think is pretty cool for people.

• 25:35Speaker 00

  I, I think there's like so many little details too, that again, like while you're watching it, it's a little slow, but, but it just figures this out for you without any intervention. Like, oh, it's, it has to decide which location I'm selling these from, for the payment link. And it's just, it just like saw that, it needed it. And, and like when it looked up what locations I've got here. And, uh, like just, it just unblocks itself, which is really nice. So you can just wait for this to go. And so, okay, so I actually have a real payment. And this is just going to load up and it uses my items, has a price.

• 26:06Claire Vo?

  Look at that.

• 26:08Speaker 00

  Yeah. And so we could just throw in a real credit card right now and this would work and I, and we would collect on that. And, and so this is like, okay, so this is a bit of a tour of an existing MCP, like how you connect these agents to real products. And, but then I think what's like part of my job is really like, okay, what's, what's the next step? And how do we make the agent do the next step? And, and so for me, I think, I think we could switch to from here is like, maybe we go give it another MCP so that it can send these payment links in an email. And so I have a test email account here. It's totally empty. And I think we can work with that and then just try to show you how you can literally like extend the existing conversation. So I'm going to leave this open and we'll come back to it.

• 26:52Speaker 00

  And I'm going to make a new window that we're going to use to make the like vibe coding half of this. So we'll just go vibe code and CP together. I'm also going to open up a terminal window so that we can follow along. And I did do one thing in advance, which is I went and grabbed an API key here in an end file. And, and I set that up just in advance. So we didn't have to show the API key on the screen. And so we're going to use that to set up an MCP server with Mailman.

• 27:24Claire Vo?

  And I want to just pause here because we've heard this a lot on this podcast, which is people are always saying, you know, you can, you can do the output. I'm sure you could take this link and send the email. But anytime you're about to create an output, instead think about how can I create a tool or a prompt or an input? That could do this for me. So instead of saying, great, I'm going to email this link, you say, great. I'm going to build an MCP to send emails.

• 27:46Speaker 00

  Exactly. Yeah. Like, how do you take that whole end to end workflow and solve every part? Yeah. Okay. So let's, let's talk it into vibe coding and MCP for us. So the way I like to do this usually is I'll start with the scaffolding and making sure that everything kind of connects and works. So I won't even say MCP at first. I'm going to just say like, let's try to send an email. So I'll tell it like I have a staff holded iPhone package here using UV. I'll tell it about that dot N file I mentioned. And I'll tell it what's in there because I don't want it to actually read this. It's like, yeah, I don't want the, the model to know about my API key.

• 28:26Speaker 00

  And so then I'll say, can you make the Python, Python script in this directory that sends a test email? And this is like the vast majority of the work, like it going from a blank slate to sending a test email. That's the hard part. The the M C P half is really easy. So yeah, I always start that way. Like, let's just prove that everything works.

• 28:47Claire Vo?

  That you can do the thing and then we can figure out how to invoke the tool.

• 28:50Speaker 00

  Yeah. And this is actually another feature of Goose that I'm kind of glad it accidentally triggered is that it tried to read the dot N file. Because it was like, oh, what am I working with? And we denied that, actually, because it's like a security concern. So there's a bunch of stuff that we try to catch.

• 29:08Speaker 00

  And so it can't see it, but it's it's going to have to just trust me that I what I said is in there and then use it. And so, OK, and let me follow along over here. So I'm gonna just.

• 29:19Speaker 00

  We have a new file now, send test email that should be using this. And it just wrote that. And if I wanted to like follow along in detail, I could do. I can I could read it in an editor or something like that. But for the most part, I'm just gonna trust it and hope it works. And so let's say, OK, can you?

• 29:39Speaker 00

  And I'm gonna give it that demos email.

• 29:42Claire Vo?

  Got it. So now it's written the script and you're just gonna double check this thing works and that I'm gonna get an email out of the script.

• 29:49Speaker 00

  And so it figured out what I meant by the dot N. So it's like, OK, I found a thing. And it's got this hardcoded recipient that it's gonna go edit. And you can see like, if I like just read down there, it like just fixed that for it. Now that I told it who it's gonna send it to. And it's figuring out all this virtual N stuff.

• 30:11Claire Vo?

  OK, so so just A I, just like us, figuring out its virtual environment. That is the theme of of today's episode.

• 30:21Speaker 00

  Okay, and then let me go over here and see if we got it. And I'm sure it's gonna end up in spam or something.

• 30:27Claire Vo?

  Oh, there it is.

• 30:29Speaker 00

  And so we got a test email sent with Python. And it goes to spam because obviously this is all demo stuff. That's not surprising.

• 30:38Claire Vo?

  And whenever I, you know, I get engineers asking me a lot. They're like, Mailgun, it's well documented. I can write the thing. But I think about the number of characters you wrote in Goose and just the number, like the typing that had to happen

• 30:52Speaker 00

  Yeah.

• 30:53Claire Vo?

  in the file. And I just think it has just saved you 15 minutes of time of like looking at the docs, copying it over, you know, checking that it works. And we did it in probably two minutes.

• 31:04Speaker 00

  Yeah, exactly. And like, I just, I've, I've never built an email sending service. So it's like, I don't know this API at all. It didn't have to ask me for that. It's like, oh, it knew the endpoint name and everything. That's all trained in, which is just fantastic.

• 31:18Speaker 00

  Okay, so, so now that this work is working, let's, let's turn it into an MCP. And then this is an example of like a little bit of model knowledge going a long way. So this model isn't trained recently enough to know about the MCP SDKs. So that's, that's a thing where I'm gonna actually go get it that context so that it can use it. And so I'll just go find like the

• 31:42Speaker 00

  yeah, MCP Python SDK. And we'll just grab it from the read bean. And so at this point, I could actually tell Goose the URL and like it could download this read bean and it would work. But I, I'm rather just like copy and paste, honestly, because it's easier.

• 31:56Claire Vo?

  I'm, I'm the same as you. I'm just like, let's just drag the whole page and paste it in.

• 32:03Speaker 00

  Yeah, and it's like, okay, great. Like, it's already got these links. All I need is just this one example and that should be enough. And so I'll say, you know, okay, be nice to your LLMs, of course.

• 32:14Claire Vo?

  I agree. Be nice to your LLMs.

• 32:17Speaker 00

  So I'm gonna say now we're gonna make an MCP server out of this. Uh, here's reference code.

• 32:26Speaker 00

  And then I'll say, can you use that example to make an MCP with a base and mail tool? And we'll see how far it gets with no other context, actually. We might need to tweak stuff, but hopefully that's like a good start for it.

• 32:41Claire Vo?

  And while it's thinking, are you doing, does Goose auto-select models? Do you have a default? Do you have a favorite?

• 32:49Speaker 00

  We currently don't auto-select models because people bring so many different models to Goose. And so for us, we kind of switch context by context, like Jackie was mentioning. So like for writing code and using these tools, currently I'm using Claude Sonnet, which is great. But if I wanted to go write a design doc, I might actually switch to like one of the Reasoner models from OpenAI, or I could even like try out like a local-only model and run a QN.

• 33:20Speaker 00

  Okay, so let's see what it's doing. I'll check in again. And I'm just gonna like take a look. Okay, so it's got a new file and it's combining like what we were doing before.

• 33:30Speaker 00

  And it's following that example pretty well, it looks like. And that's actually good code. I'm gonna interrupt it, honestly, because I know what it's going. It's going down like a slightly wrong path because it doesn't know how I'm going to integrate it. So I'm just gonna pause that.

• 33:47Claire Vo?

  I like the judgment.

• 33:50Speaker 00

  Yeah.

• 33:51Claire Vo?

  The code.

• 33:52Speaker 00

  It's like definitely the right idea. I'm not gonna like read line by line because I kind of trust it at this point, but what I am gonna do is I'll make my one-line contribution to this project right now, which is I know I want it to be running not as a remote URL. I want it to just be a standard I/O MCP if you work in it. That's the difference here. So I'm just gonna make it standard I/O. And then I'm gonna ask it like a weird question to help me set this up in Goose. So I'm gonna say to help me do that, can you get the path in this virtual end? So really, I'm just trying to make sure that I have a portable command that I can run in Goose. And so I'm gonna ask it to figure out that virtual end.

• 34:36Speaker 00

  So some of that. And that should just take like one or two tool calls from it.

• 34:41Claire Vo?

  And is this your just general flow for making MCPs all the time? Build me the, build me the function, then here's the code to turn it into an MCP. I'm going to make my one line contribution. I'm going to ask it this very specific question that I know works in my system. And then you're going to get it, get it going.

• 34:59Speaker 00

  Yes, exactly. And so, once you have that, like a core functionality working, then you give it this example and turn it into the MCP. Exactly that. And so, um, okay, so it got me this, like, this is the path of the virtual Python, which is what I needed. And then I'll ask it like also, um, what's the abstract of the Python file? And that's going to be the two ingredients that I need to go make this work. And it's just, you know, running shell commands to do this. So I've already got it there. So let's do this. And I'm going to go into that, like, existing settings. And I'm just going to immediately add a new custom extension that we just built. So I'm going to call this email.

• 35:44Speaker 00

  We're going to do that path to the Python file. Oops, and I didn't paste the other one. So let me just go to the terminal and grab this.

• 35:53Speaker 00

  And there, and we're going to do, we're just going to run that server we just created. And that should be everything.

• 36:02Speaker 00

  Oops, I got an error. See what that is? I'm just going to paste the output.

• 36:09Speaker 00

  Oh, so there's actually a code error.

• 36:11Claire Vo?

  Oh, well, there you go.

• 36:13Speaker 00

  And I'm going-

• 36:14Claire Vo?

  It wasn't good code.

• 36:16Speaker 00

  It's so, um, I'm going to tell it this, um, I'm going to tell it this error and see if it can just fix it.

• 36:24Claire Vo?

  So I like that you actually say, I got an error. Can you help me? Cause I just go straight to just paste the error in.

• 36:32Speaker 00

  Yeah, it's probably Spartan. I, I like spend a little too much time, like having a conversation, honestly, with the L ones. And, uh-

• 36:42Speaker 00

  And so like, hopefully it can figure this out without me thinking too hard about what's in the file. We can like, watch it work, of course.

• 36:51Speaker 00

  And honestly, I think the thing that it did here is this resource. So it's fixing that, but um, yeah, okay, okay. So it figured it out at about the same time I did.

• 37:03Claire Vo?

  Okay, so I, this is gonna be the new podcast. It's human developer, AI developer, who figures it out? Who spots it first?

• 37:12Speaker 00

  I, the, uh, the debugging flow is like something that I thought was gonna be what kept me employed with the AI writing all these code. But I'm like, oh, it's actually pretty good. It's pretty fast.

• 37:25Speaker 00

  Yeah, so we're gonna try that again now that we've edited that file. I don't get interrupted because again, I think it's doing some extra stuff we don't need. And I'm just gonna toggle that. Where did it end up in the list? I'm gonna toggle that on again. Oops, okay, new error, sorry about that. Normally this works in one shot, actually.

• 37:47Claire Vo?

  Do you find as, as an engineer, that you have shifted your debugging strategy to this, which is just, I'd rather loop with the, the agent and just get it to figure it out than sit here and you use my eyeballs and my fingers to solve this thing? I'm just curious how that's happened internally to yourself.

• 38:10Speaker 00

  I think I basically, I almost always let the LLM try once. Like if it, if it knows what to do to fix it, I'm like, great, that's faster than me figuring out. And then the thing that I think I am better at than it is, is like just being tenacious. So if it's like, if it's not figuring it out, it's like, okay, I will take over. And so this version is like, I'll, I'll take a look at like whatever idea

• 38:37Speaker 00

  it's coming up with. And if it like, seems like it's in the right direction, I'll let it finish.

• 38:44Claire Vo?

  We did it!

• 38:45Speaker 00

  Hooray. Um, great. So now that we've got the like, in farce loading, and we actually, so what we just did is we like, turned that thing we just built on in the existing chat.

• 38:56Claire Vo?

  Okay.

• 38:56Speaker 00

  So it's, it's a, it actually should now see it. So I'm gonna say like, great, we just enabled that. Can you see the new tools? Um, try sending a test to you.

• 39:09Speaker 00

  And let's see if that works. So now we've at least like got it running and yeah, it sees the tools, right? So and it's and it's trying this like get email status, which doesn't, we don't need that. It but it's like, great. It sees that everything is ready to go. And then it's like sending the MVP email test. And it is success. And so it's working. And so we kind of built it, plugged it into Goose and then immediately tested it out. And let me go check my inevitable spam folder. Yep, there it is.

• 39:41Claire Vo?

  You did it.

• 39:42Speaker 00

  Great. So despite all the spam checks, uh, we've got that working. And then and then now we can kind of finish that off by bringing it back to where we started, right? So we know that works. I'm going to go over to this existing chat. And these are two separate conversations, right? So like this, this LLM knew all about everything we just did. I'm going to close that out. This one has no idea that that just happened. So I'm just going to go in and toggle that on and off real quick. And we're going to go back here and I'm going to say, I just enabled an email tool. Can you send that payment link to my demo email address?

• 40:26Speaker 00

  So it doesn't have any of that like, it doesn't have to, its memory doesn't have to worry about it.

• 40:29Claire Vo?

  It doesn't know the functions or any of that stuff. So this is the real test.

• 40:34Speaker 00

  Yes. So it has no idea other than that this thing just got created. And it's doing the same thing that the other one did, which is like, okay. It's it's like checking and knows where it's coming from. And yeah, hopefully we'll get it to send something. At this point, it's like writing more content, right? Because it's like, I'm sure it's going to try to be cute about the the like body.

• 40:55Claire Vo?

  Are we going to get a pumpkin emoji in the?

• 40:58Speaker 00

  Right. Yeah, that's what I'm hoping for. Okay. And we should have something in spam. Yep. And so we've got produce store payment. We've got our payment link, um, order details, all of that stuff. And, you know, the same link should bring us back.

• 41:17Claire Vo?

  So there are two levels of faces I make on this podcast. This is one of them. I go, ah, and then this is the other one where something works. So you've gotten the raised hands podcast reaction. So just to recap, everything Goose did for us today, I'm like still, still processing. Jackie, we got your CSV. We took some like dirty produce data, got some insights on how to make it better. Brad, you took that and populated a store with your produce items, then created a way for people to buy those items through a nice

• 41:56Claire Vo?

  little friendly link. Then you vibe coded an MCP live, thrilling. As somebody who's avoided building an MCP for no less than six weeks, now I feel like I have no, no excuse other than to just go do it. And then you use that MCP to send somebody a pumpkin purchase email.

• 42:19Speaker 00

  That's right.

• 42:21Claire Vo?

  This is so great. Okay. This has been incredibly fun. I have to ask you both as part of our lightning round questions. Jackie, what's your favorite MCP tool in your stack right now?

• 42:35Speaker 02

  I hate to say it, but it's probably Google Drive. That is, as a manager where I live, and I'm just so happy to be able to not have to copy and paste and click and save the time.

• 42:46Claire Vo?

  Okay, Brad, what's your favorite?

• 42:47Speaker 00

  Definitely Shell. I just, you know, I've lost, I've lost all my memory of the arguments to various Shell commands. It's just 100% filling them in for me at this point.

• 42:57Claire Vo?

  Okay. And then if you could make a pitch to people inside an organization that are hesitant about getting started with AI, or even people that are outside of technology that just say, I don't know. How could this apply to me? Why would I use it? Seems really complicated. What would you, what would you say to them?

• 43:16Speaker 00

  Find the thing that you don't like doing and automate that. Like, don't, don't, if you love programming, don't try to automate your programming. That's like fun for you. You maybe figure out when, when you want to make that trade off. But it's like, oh, I hate writing the unit tests. That's the thing I'm gonna have the AI do.

• 43:30Claire Vo?

  Okay, get rid of toils. Spoken like a true, true engineer. Jackie, what about you?

• 43:35Speaker 02

  I think really treating it as a learning experience and realizing that this is the worst the models are ever gonna be. And so even if it's not something that transforms your daily life right now, even by keeping up with the tools and seeing where it fails, seeing where it fails is like just as useful, seeing where it succeeds. And still really treating it as an experiment and a way to learn versus, you know, a magic bullet that's gonna magically solve everything.

• 44:00Claire Vo?

  Okay. And then Brad, we saw how polite you are. We have to ask both of you our favorite question, which is when AI is not doing what you want? And you're starting, maybe you're getting exasperated, I don't know. What's your tactic? You seem very polite. So every, I saw every line started with, great. But you really screwed that up. So Brad, what's your, what's your strategy here?

• 44:23Speaker 00

  I, so I thought this was kind, but I realized now it's even more brutal. Is, is that like the moment it's not good. I just, I just throw out the session. I throw out the whole convo and I start over. And it's like, I, cause I, what, like, it's so much work to convince it to do the thing you want. It's so easier to start, so much easier to start over. And then I'm like, oh, I guess that like that thread with that model, it's just done forever now. So it's kind of sad, but.

• 44:45Claire Vo?

  Can you imagine if we did this at work where somebody started to say something that was totally wrong? You just like shut the door in their face and said, come back and just start, start totally, totally over. Okay. Uh, Jackie, what about you?

• 44:58Speaker 02

  When it's not functioning right, definitely start a new, uh, session. But what I like to do is, uh, have it. I'll give it like really key words that I want if I wanted the style of something to change. So you know, if something is out like to MBA, like a lot of times they'll say write it like you're a hacker. And another thing I like to do is have it like summarize everything that it did, the good parts and like take out the bad parts and start a new session based on those instructions.

• 45:22Claire Vo?

  Great. I have learned so much myself. I'm gonna go download Goose and build that MCP that I've been avoiding. Where can we find more information about this? Where can we find you too? And how can we be helpful?

• 45:35Speaker 00

  Yeah, definitely check out block github.io slash goose. That's like the homepage, all the install instructions. And it should lead you also to our like GitHub repo where we love contributions.

• 45:47Speaker 00

  And if you want to chat with us about it, we run a Discord for block open source. So get in there and like all of us are in there and we we like debug live and all that kind of stuff. So a lot of activity for sure.

• 45:57Claire Vo?

  Amazing. Well, thank you so much for sharing all this on the show.

• 46:01Speaker 02

  Thanks for having me.

• 46:02Speaker 00

  This is fun.

• 46:03Claire 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 how IAIPod.com. See you next time.