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

20:02Brad Axen: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 exactly and then get it into the system okay yeah

20:27Jackie Brosamer:so it doesn't matter what you've got it's going to figure out a what 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 ncp 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 lom is seeing like all of these operations that it can now access so all that stuff about like creating items it figured out um okay and i actually see the uh it's like this is a funny i normally would just read the csv um so i'm like i'm like laughing a little bit at like how much work it's going through for this but

21:23Brad Axen:uh it is what it is i know i have i have that same experience using like a cursor max mode where i'm don't know if you need to work to think that hard exactly how to do this but you know it's not my

21:36Jackie Brosamer:brain it's the ai's brain 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 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 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

22:05Brad Axen: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. One of the like really underappreciated 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 mushed together. And that's where a lot of the day-to-day data work is, is trying to match all those things. How I AI is now on Lenny's list with my personal selection of the best AI engineering courses on Maven.

22:44Brad Axen: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 Naresh Riganti, MIT instructor and AI scientist at AWS, or Sandor 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, visit maven.com slash Lenny to enroll now. Use code Lenny's list for$100 off. That's maven.com slash Lenny to get ahead in the AI era and start building.

23:35Brad Axen: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.

23:48Jackie Brosamer:And this is something like I could follow up with this and say like, okay, grab

23:52Brad Axen:images or even generate images and like, I want to I want to AI generated Apple image.

23:59Jackie Brosamer:Exactly. Yeah. And the 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 CSB and walk away and come back and then you're going to 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.

24:32Jackie Brosamer:It's something I can take payments with. So I can now say, okay, let's make a payment link for three pumpkins. And we'll let that run for a little bit too.

24:43Brad Axen:This is not the topic I thought I was going to 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 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 want to be able to do this really easily this sort of like ability to just type in a short command to get a really custom software solution backed by you know either a platform or not I think is pretty cool

25:34Jackie Brosamer:for people 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 it uses my items has a price look at that yeah and so we could just throw in a real credit card right now and this would work And we would collect on that.

26:13Jackie Brosamer: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 the next step? And how do we make the agent do the next step? And so for me, I think a thing 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 that'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 I'm going to make a new window that we're going to use to make the like vibe coding half this so we'll just go vibe code and nvp 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 N file.

27:14Jackie Brosamer: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.

27:24Brad Axen: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 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. Exactly. Yeah.

27:47Jackie Brosamer: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 Python package here using UV, I'll tell it about that dot end 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, you know, I don't want the model to know about my API.

28:25Jackie Brosamer:And so then I'll say, can you make a 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 MCP half is really easy. So yeah, I always start that way. Let's just prove that everything works.

28:47Brad Axen:That you can do the thing and then we can figure out how to invoke the tool. Yeah.

28:50Jackie Brosamer:And this is actually another feature of Goose that I'm kind of glad it accidentally triggered, is that it tried to read the.env 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. And so it can't see it, but it's going to have to just trust me that what I said is in there and then use it. And so OK, let me follow along over here. so I'm gonna just uh we have a new file now send test email that should be using this um and it just wrote that and if I wanted to like follow along in detail I could do I could 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 okay can you um and I'm gonna give it that demos email got it so now it's

29:44Brad Axen:written the script and you're just going to double check this thing works and that i'm going to get

29:47Jackie Brosamer:an email out of the script and so it figured out what i meant by the dot end so it's like okay i found a thing and it's got this hard-coded recipient that it's going to go edit and you can see like uh if i like just read down there it like just fixed that for it now that i told who it's going to send it to and it's figuring out all this virtual end stuff okay so so just

30:13Brad Axen:AI just like us figuring out its virtual environment. That is the theme of today's episode. Yeah, every time.

30:21Jackie Brosamer:Okay, and then let me go over here and see if we got it. And I'm sure it's going to end up in spam or something.

30:27Brad Axen:Oh, there it is.

30:29Jackie Brosamer: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.

30:38Brad Axen: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 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.

31:04Jackie Brosamer:Yeah, exactly. And like, I just 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. OK, so now that this is working, let's turn it into an MCP. And then this is an example of 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 a thing where I'm going to actually go get it that context so that it can use it. And so I'll just go find like the, yeah, MCP Python SDK.

31:44Jackie Brosamer:And we'll just grab it from the readme. And so at this point, I could actually tell Goose the URL and like it could download this readme and it would work. But I'd rather just like copy and paste, honestly, because it's easier.

31:56Brad Axen:I'm the same as you. I'm just like, let's just drag the whole page and paste it in.

32:02Jackie Brosamer: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.

32:14Brad Axen:I agree, be nice to your LLMs.

32:16Jackie Brosamer:So I'm going to say now we're going to make an NCP server out of this. Here's reference code. And then I'll say, can you use that example to make an NCP with a send 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 a good start for it.

32:42Brad Axen:And while it's thinking, does Goose auto-select models? Do you have a default? Do you have a favorite?

32:49Jackie Brosamer: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 for writing code and using these tools, currently I'm using Cloud Sonnet, which is great. But when I you know if I wanted to like go write a design doc I might actually switch to like one of the reasoner models from opening eye or I could even like try out like a local only model and run QN. 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 and it's following that example pretty well it looks like and that's actually good code i'm gonna i'm gonna interrupt it honestly because i 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 going to pause that and i like the i like the the judgment yeah good code it's like definitely the right idea i i know I'm not going to read line by line because I kind of trust it at this point.

33:58Jackie Brosamer:But what I am going to 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 IOMCP if you work in it. That's the difference here. So I'm just going to make it standard IOMCP. And then I'm going to ask it like a weird question to help me set this up in Goose. so I'm going to 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 so that I can run in goose and so I'm going to ask it to figure out that virtual end so listen that and that should just take like one or

34:38Brad Axen:two tool calls from it 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 a this very specific question that i know works in my system

34:56Jackie Brosamer:and then you're going to get it get it going 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 yeah and so um okay so it got me this like this is the path of the virtual length python which is what I needed. And then I'll ask it like also, what's the abstract of the Picon 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.

35:39Jackie Brosamer:And I'm just going to immediately add a new custom extension that we just built. So I'm going to call this email. 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. And there, and we're going to do, we're just going to run that server we just created. And that should be everything. Oops, I got an error. see what that is i'm just going to paste the output um oh so there's actually a code error oh well there you go and i'm going it wasn't good yeah it's cool um i'm going to tell it this um i'm going to tell it this error and see if it

36:22Brad Axen:can just fix it so i like that you actually say i got an error can you help me because i just

36:29Jackie Brosamer:go straight to just paste the error in yeah it's probably spartan i i like spend a little too much time like having a conversation honestly with the loms and uh 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 um and honestly i think the thing that it did here is this resource so it's fixing that but yeah okay okay so it figured it out at about the same time I did yep okay so

37:03Brad Axen:this is going to be the new podcast it's human developer AI developer who figures it out who spots it first

37:11Jackie Brosamer:I the the debugging flow is like something that I thought was going to be what kept me employed with the AI writing all these codes but I'm like oh it's actually pretty good it's pretty fast yeah So we're going to try that again now that we've edited that file. I'm going to interrupt it because, again, I think it's doing some extra stuff we don't need. And I'm just going to toggle that. Where did it end up in the list? I'm going to toggle that on again. Oops. Okay, new error. Sorry about that. Normally, this works in one shot, actually.

37:47Brad Axen: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 then sit here and use my eyeballs and my fingers to solve this thing i'm just curious how that's

38:08Jackie Brosamer:happened internally to yourself 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 um 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 uh so this version is like i'll take go look at like whatever idea um it's coming up with and if it like seems like it's in the right direction i'll let it finish we did it hooray um great so now that we've got the like infars loading and we actually so what we just did is we like turned that thing we just built on in the existing chat okay so it's it's a x it actually should now see it so i'm gonna play like great we just enabled that can you see the new tools um try sending a test email 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 an NTP email test.

39:28Jackie Brosamer: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.

39:41Brad Axen:You did it!

39:42Jackie Brosamer:Great. So despite all the spam checks, we've got that working. 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 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 so it doesn't have any of that like it doesn't have to its memory doesn't have to worry about

40:30Brad Axen:the functions or any of that stuff so this is the real test yes so it has no idea other than that

40:37Jackie Brosamer: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 are we gonna get a pumpkin emoji and the right yeah that's that's what i'm open for um okay and we should have something in spam yep and so we've got a store payment we've got our payment link um order details all of that stuff stuff and you know the same link should bring us back so there are two levels of faces i make on this podcast this this is one of them where i go and then this is the other one where something

41:24Brad Axen:works so you've gotten the 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 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 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 excuse other than to just go do it. And then you use that MCP to send somebody a pumpkin purchase.

42:19Brad Axen:That's right. 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? 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 on save the time. Okay, Brad, what's your favorite?

42:48Jackie Brosamer:Definitely shell. I just you know, I've lost I've lost all my memory of the arguments to various shell command. It's just 100 % filling them in for me at this point.

42:57Brad Axen: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 say to them?

43:16Jackie Brosamer: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 going to have the AI do.

43:30Brad Axen:OK, get rid of toil. Spoken like a true, true engineer. Jackie, what about you? I think really treating it as a learning experience and realizing that this is the worst the models are ever going to 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 as seeing where it succeeds and still really training as an experiment and a way to learn versus, you know, a magic bullet that's going to magically solve everything. 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 get exasperated.

44:11Brad Axen: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?

44:23Jackie Brosamer:So I thought this was kind, but I realized now it's even more brutal 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 could that 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 that like that thread with that model it's just done forever now so it's kind of sad but can you imagine if we did this at

44:47Brad Axen: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 jaggy what about you when it's not functioning right definitely start a new uh session but what i like to do is a habit i'll give it like really keywords that i want if i want the style of something to change so you know if something comes out like to mba like a lot of times i'll say write it like you're a hacker um another thing i like to do is how to 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 great I have learned so much myself.

45:25I'm going to go download Goose

45:27Brad Axen:and build that MCP that I've been avoiding. Where can we find more information about this? Where can we find you two? And how can we be helpful?

45:35Jackie Brosamer: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. 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 like debug live and all that kind of stuff. So a lot of activity for sure.

45:58Brad Axen:Amazing. Well, thank you so much for sharing all this on the show. Thanks for having us.

46:02Jackie Brosamer:This was fun.

46:03Brad Axen:Thanks so much for watching. If you enjoyed the show, please like and subscribe here on YouTube or even better, leave us a comment with your thoughts. You can also find this podcast on Apple Podcasts, Spotify, or your favorite podcast app. Please consider leaving us a rating and review, which will help others find the show. You can see all our episodes and learn more about the show at howiaipod.com. See you next time.