How this PM uses MCPs to automate his meeting prep, CRM updates, and customer feedback synthesis | Reid Robinson (Zapier)

MCPs, I will say, it's a concept that's really hard to understand for folks. Yeah, definitely don't think about the word. It really just is like app integrations for your AI tools. You can create these collections of tools from all the apps you use and give them access to Claude, to Chattopadhyay, to Cursor, all the places that have inputs for MCP servers today. I use agents all the time, but it is hard to break that muscle memory of this is a deterministic workflow versus an instructive agent. Even if it has access to the same tools and can do the same things. And when it comes down to it, the two things we see people wanting to do is one, giving their favorite AI tool the access to knowledge that lives in their apps, as well as giving them the ability to actually do things in those apps. Those are the two things that if that sounds like something that you need in an AI app you use, look for MCP or connectors as it's often being called now as well for that. Welcome back to How I AI. I'm Claire Vaux, product leader and AI obsessive here on a mission to help you build better with these new tools. Today I'm talking to Reid Robinson, product manager on AI at Zapier. And what I love about my conversation with Reid is he's going to show us how to put MCPs to work inside Claude to take over tasks that you really hate. We also talk about whether AI can be the perfect always on team that works while you sleep and some use cases to make your kids and your partner a little happier. Let's get to it. This episode is brought to you by Work OS. AI has already changed how we work. Tools are helping teams write better code, analyze customer data, and even handle support tickets automatically. But there's a catch. These tools only work well when they have deep access to company systems. Your co-pilot needs to see your entire code base. Your chatbot needs to search across internal docs. And for enterprise buyers, that raises serious security concerns. That's why these apps face intense IT scrutiny from day one. To pass, they need secure authentication, access controls, audit logs, the whole suite of enterprise features. Building all that from scratch? It's a massive lift. That's where Work OS comes in. Work OS gets you drop-in APIs for enterprise features so your app can become enterprise ready and scale up market faster. Think of it like Stripe for enterprise features. OpenAI, Perplexity, and Cursor are already using Work OS to move faster and meet enterprise demands. Join them and hundreds of other industry leaders at workos.com. Start building today. Hey, Reid. Thanks for joining How I AI. Thanks for having me here, Claire. Excited to chat today. What I love about how you've described your role at Zapier, which I use all the time I say is like load-bearing infrastructure over at ChatPRD, is you've worked your way into a role where you get to kind of like pick what you're working on next in AI. And so I'd love to hear about what you're focused on and how that's actually impacted how you think about some of your personal workflows. Absolutely. So, yeah, the way I often describe my role is often the Sisyphus of AI at Zapier, just pushing the rock up the hill, wherever that rock may be and whatever the hill might be. Right now, the thing I'm most excited about and where I'm choosing to spend a lot of my time working on AI is on our approach to MCPs. So we've got a server approach as well as what we're doing on the client side. You know, MCPs, I will say, still, I think, both kind of very hyped and underutilized by people because I think it's a concept that's really hard to understand for folks. So I'd encourage our listeners and our watchers who are a little nervous about wading into the world of MCPs to just really think about, you know, if I could give my favorite AI chat client or IDE or whatever access to a bunch of tools to do things for me, what would I want them to do? And then go hunt for an MCP that does that thing. And I think you have built a product that has tried to abstract away some of that complexity for Zapier users, at least. Could you walk us through kind of a little bit of your approach there? Yeah, absolutely. And I think you said it really well, the two kind of use cases I give people to just like think about MCPs is, yeah, definitely don't think about the word. It really just is like app integrations for your AI tools. And when it comes down to it, the two things we see people wanting to do is, one, giving their favorite AI tool the access to knowledge that lives in their apps, as well as giving them the ability to actually do things in those apps. So it's really those are the two things that if like that sounds like something that you need in an AI app to use, look for MCP or connectors as it's often being called now as well for that. And yeah, the approach that Zapier took for anybody not familiar with Zapier, we're like one of the world's largest AI orchestration automation platforms. And what that really means on the MCP side is we've got 8,000 apps on Zapier that are like every SaaS app you can imagine. There's 30,000 searches and actions amongst that. And that's all exposed via Zapier MCP. So you can create these like collections of tools from all the apps you use and give them access to Claude, to Chattopiti, to Cursor, to all the places that have kind of inputs for MCP servers today. Do you mind pulling that up and just showing us a little bit of what that looks like? And while you're pulling up your screen, I do bless you, MCP framework provider. But we got to work on the branding here. So I think your description is exactly right. Like app connectors for your AI is such a simpler way for the everyday consumer to understand this. And so, OK, so you're showing us Zapier here for folks that are just listening. And just can you walk through, oh, you have 8,000 tools or 8,000 apps you can add tools from. So this is your MCP server that you've added a custom set of tools that you're going to use pretty consistently, either for a use case or just as an individual, right? Yeah, exactly. And so the way that it works is I kind of set up the ones that I'm using specifically for Claude. And so what's nice on Zapier side, unlike many other MCP servers, is we actually are more like a platform for creating service. You can create multiple. And what that means is you can create specific sets of tools to use with Claude or with a particular agent or with ChattyBT or with Cursor, really anything out there that supports it, which is nice because for me, those tools are different from one place to the other. And yeah, you can see or for those who can't see, you can add tools from things like Slack, Evernote, Glean, Coda, Google Calendar. And you can actually start to customize those tools as well. So whether you want to restrict them to using certain databases like I've done with Coda, I for my use within Claude, I really am using it for particular documents and particular sheets, for instance, and other sides like with Evernote, I want to restrict it to writing to certain notebooks. So it really allows you to customize the way you want your tool to work in different places, which is quite nice because then it's like a single URL to give over to Claude and connect to. And now if I switch over to Claude here, you can see that Claude now has like a single Zapier connector. But in that Zapier connector is like all of the different tools that I want Claude to be able to access. Yeah. And one of the things that I'll call out for the sort of more advanced MCP users and a challenge that I've always had is when you're adding these individual MCP, like there's a Google Calendar MCP and I'm sure there's a Coda MCP, is when you're adding these individual ones, you kind of have to do that configuration at the provider level. And what I like about this approach is like this custom collection of tools is actually a really nice way to think about the MCP tools that you need, either just in general or for a specific use case. And then for MCP clients out there, I think we're going to need at some point, and I know you're working on this, but like you just need more granular control over tools. I mean, like priority, I think, of tool calling is really important. I have two MCPs that I use really frequently in Cursor and they're always like competing for which one I'm trying to call because I say it's like search projects. Everything has projects in it, always calls the wrong MCP. And so I do think like the meta abstractions around MCPs are going to start being more important as they become more adopted. So that's Claire's manifesto on MCP design. All right. So you have this custom MCP. I mean, what are specific things this unlocks for you? So what use cases are you using here to actually get more work done? Yeah, so for me, there's like things that I don't love doing is really where it helps me. So one like and for one of the things you just touched on, which is like the model's ability today to pick which tool is a bit murky. I think Claude is a phenomenal place. They've done a great job with tool calling. One of the tricks for anybody listening, check out Claude Projects. In particular, one of the things that you can do in Claude Projects is provide very detailed instructions for use cases. And so, for instance, I'll share my screen here, but I have one that's all about the way I like logging and looking up data from our CRM for things. And I've actually told it how it should use tools, in which order it should use tools, what data should go where, when it's creating records with those tools. And so then in Claude, when I'm trying to do things, I can actually be like, oh, I'm doing a CRM thing. I'm actually going to go ahead and select my CRM project and then shoot over a message. And now Claude's ability to like execute across many different tools sequentially is so much better. So I highly recommend if anybody's like running into those things, try out Projects. Highly recommend it. Yeah, I've heard a lot of people talk about using Claude Projects for knowledge, like loading it up with knowledge. But I haven't heard anybody talk about what you specifically gave as an example, which is use Claude Projects to give specific instructions relative to MCP tool usage and a workflow. And so folks, listen up. You can do that in Claude Projects and probably other clients to just make your use of your tools more efficient. OK, so you have this Claude Project. It looks like one of the things you hate doing is updating your CRM like a true account. I do actually tell people. MCPs are highly underappreciated by customer facing teams. Like what do customer facing teams hate doing? Updating Salesforce. We hate it. We hate it. And so like, you know, keeping good customer records, whether it's for a sales use case or research use case, whatever, is like really tedious. And there are actually amazing MCPs out there to do this. So I love to see how this works in your flow. Yeah, absolutely. So one of the first things I do is I have my daily planning one, and that actually goes through my full calendar. And one of the nice things is I've given it access to internal lookup tools. So, for instance, when I run this, it can actually look up the person on meetings with Zapier usage, their company's Zapier usage, our past sales interaction with them. And it's able to follow the process of doing all that lookup. And then when it comes back with ultimately my daily update, it has all of that research included. So again, really one that I've helped a lot of our sales team get set up with. And we've actually been like demoing it when we go to like events. That's been pretty fun. But yeah, on the CRM side. So let's say that I have the biggest one for me is actually my like post meeting notes management. I'm a big fan of Granola. They're a great tool. But I struggle with the fact that sometimes I don't want to log those notes or I don't do it all the time. Or it can just be really tedious to go about doing that. And so one of the things that I found really helpful here is I can I have like a flawed project that has a bunch of instructions on just how to log this data, where should it log. And then I can go in and actually select that project. And then what it can do is it should be able to have access to all the tools and it'll start like running it through for this. And now this one's gonna be interesting because I have the project configured to like our production database and it's going to try it with a different one. So let's see if this works for that. But it should be checking against this coda document for things and seeing like what are the interviews I have scheduled and what are the things that are coming up. And I go back to my little buddy Claude here. It's going to tell me that, sure enough, nothing was found. Then it can choose to start doing additional things where I've taught it to like use our internal lookup to find this person's thing. I'm going to skip this for now. Don't want to pull in actual stuff here. And then some other things is Glean. Like now I've given it an action as well to search like our internal Glean tool, which is awesome because then I could see like, oh, well, we talked about this customer in Slack or we had notes from the CSM on what this meeting is supposed to be about. So it helps do a lot of that. And then eventually what it gets into doing is start to say like, OK, this didn't exist. Here's what I looked up based on the notes from the meeting. Like, let me go create that and run with it. And that updates your coda with what? Ah, so, yeah, that updates the coda with like, and this is I'm doing a demo in here for y'all. Essentially, like the coda that I do have is a lot of the times I work on some of our like new products and new features. I'm doing like customer research in these like smaller dedicated sprints. And so we typically will have something in coda. I might also need to update our actual theorem, which will be this HubSpot as well. So I'd have that as like an additional tool to log it as an activity on the meeting. But for the most part, I'm making sure that I have a record of this meeting, who I met with, what if there were next steps? What were the next steps? It'll include some details on like what is if there's a bigger opportunity, like what are the opportunity details? You can really get it to include a lot of things. And I think that's where if I go back to the prompt for a second, things like this here where you'll see I kind of like our users always say they train the model. So if that makes sense to you, you can train the model on how to populate your CRM fields because everybody's CRM fields are unique. Like nobody uses standard cookie cutter CRMs for the most part. Folks love their custom fields, but models don't know what those custom fields are and what those choices are. So great way, again, just to get it to be familiar with you and working specifically for you. What I think is really interesting here, again, as like a Power Zapier user is I have a similar flow, which is I take granola transcripts. I use the granola app in Zapier, but I have mapped this out in the standard workflow builder. So I have done, I think now that I'm seeing this, the inefficient task of saying, OK, like if this look up this record, if the record doesn't exist, do that. If the record does exist, do this. And so I have this like very similar CRM record updating flow in Zapier. But it's very step by step, kind of like deterministic workflow. And what I like about this, and I should be doing better because I'm supposed to be like fairy godmother of AI, is you can actually just in natural language describe that flow. And I know this, I use agents all the time, but it is hard to break that muscle memory of like this is a deterministic workflow versus an instructive agent. Even if it has access to the same tools and can do the same things. And so have you found that one one path or the other is more or less brittle, meaning like. Is is this actually more resilient, this sort of like MCP agentic instructions piece more resilient to the complexities of your data, or do you find that it fails more or less than like kind of these nice netted out workflows? Yeah, it's a very good question. I think the on the kind of reliability or where they fail there, they've got their like pros and cons. The pros of doing things like asynchronously is certainly things can take longer. Like one of the biggest challenges right now with MCP stuff is they just they can't take that long. And so if you have like a lookup process that might take like seven minutes, like that's not going to work here where that does. You can start to do a lot more of that in like deterministic workflow land, so to speak. The other big thing, though, to be honest, like the distinction that that what it really boils down to, because Zapier also has an agent's product where you could do this as an agent thing. But really what this boils down to is just giving the tools, giving the knowledge and the ability to take actions to the all the AI apps where you use them. It's kind of like the old product thing about like, you know, meeting your user where they are right, right place, right time. And I have found that that is probably the biggest thing, because there are so many times where I am, you know, like if for anybody with keen eyes who would have saw one of the projects I have here, it's actually even like idea jammer. I have a whole project hooked up to different tables and stuff like that for myself when I'm just like jamming on a topic. And it then will like research like, have we explored similar ideas or where might this be relevant? And it has more training, more like prompting there to like challenge me and certain methodologies to challenge me on that. So it really boils down to just like meeting people. And I'll be clear, like one of the things we're seeing, though, from like enterprises that are adopting this is the fact that they're trying to make sure that these tools work for all of their employees, like automatically, so that if they've rolled out Cloud for the entire organization, when they log in and they connect to AppYarit, like has the tools that they should need for their role, that it's created by some like ops admin or someone. And that's been really powerful. As an AI founder, you're used to sprinting towards product market fit your next round or that first enterprise contract. But speed isn't enough for AI startups. Buyers expect security, compliance and transparency from day one. That's why serious AI startups use Vanta. With deep integrations and automated workflows built for fast moving AI teams, Vanta gets you audit ready fast and keeps you secure with continuous monitoring as your models, infra and customers evolve. AI innovators like LangChain, Rider and Cursor scaled faster and closed bigger deals by getting security right early with Vanta. Listeners can claim a special offer of $1,000 off Vanta at vanta.com slash how I AI. There are pros and cons to each. You know, you mentioned three different methodologies. There's MCPs put in like the client where you're actually working. There's agents which do some of this and like sort of a native client. And there's these deterministic workflows. And you do have a workflow that does use AI within a more deterministic flow. So do you want to walk us through through that one and just talk about why you selected this kind of model of implementation for this particular use case? Yeah, absolutely. So one of the things for me, again, I like prep for a lot of customer interviews and we have a lot of data. And sometimes one of the most embarrassing things for me, or it feels embarrassing, is when I get on a call with a customer and they're like just a user interview that may have booked it via LinkedIn. They may have booked it via a referral from someone at a partner, right? Like they come in from all over the place. Like my Calendly link seems to like spread decently wide. And sometimes I'll get on a call previously and I'd be like, I don't know who you are. I don't know if your company uses Zapier. I don't know if they, you know, sometimes they're like, oh, yeah, we're both a customer and a partner, right? And I'm like, whoops, I didn't know that. And so what I and what I worked with and our sales facing team had similar issues. And so one of the first things that we did was we used Databricks, which houses like a lot of our data and makes that usable. And so they built like this whole series of things that allows like just simple look up for, you know, given an email address, come back with like a whole write up of it. And so essentially, this is a fancy looking workflow. But the gist of it is that for all the meetings that I'm having, it goes out, fetches that. It goes out, fetches that research lookup, which takes time, and then it deciphers that into a, like it uses actually a Gemini step since it handles more like the document type that I was working with, and creates the, or appends it technically to the Coda page for that customer interview. And so this is really helpful for me, again, because it's just like now when I'm going into my meetings, I get things like this, where this is also where I'll like take some of my notes. And so I can actually see like, oh, they did use it, and get some really like crisp things to walk into the meeting knowing. And I think for anybody, especially in bigger companies, like one of the biggest challenges we consistently see is they just like, they're using, when they start Qsai, they're using like the base models with like no additional context added. And so the unlocks for them often become, how do you get your whole sales team to not only like use AI to log things, but also like fetch information from their CRM and from their data systems when and where they need it. And that becomes really cool because, you know, technically I could then throw like Databricks lookups into an MCP tool and put that to Claude. It's really funky. Those typically take too long though. Yeah. Well, if you are the AI Sisyphus of your company, one of the things I might recommend, and I think you probably would as well, is you like buddy, buddy, buddy up to the data engineering team. That's for sure. Because that's a really useful source of interesting, rich information. And then one other thing I want to call out that may have zipped by people, especially those that are listening, is if you go into your user context zap that you just showed us, you chose Google Gemini. And I just want to reiterate why, because I've heard this a lot from different guests, which is the Google models in particular are just like great at files. They love a file. It's great at files. So Gemini, really good at large files, files context, video files, audio files. And so anytime you have sort of like a file based challenge ahead of you or use case, I see a lot of AI power users reaching for the Gemini models. Is that what drove this particular use case? Yep. You nailed it. Because yeah, the output from our data team is actually to date a PDF. And so it works very well with that. Actually, it's HTML. So I convert the HTML to a file, because then it works really, really well. And a lot less tokens, which is nice. Yeah. I think we're seeing the ascendancy of the markdown file for the open AI and anthropic models or chat GPT and CLAWD. And I do think Gemini has taken this side angle where it's like, but if you have a PDF or if you have some other file format, we're your model. So I think it's really interesting for folks who want to go to the next level of implementation, again, to not only feed rich context into their AI use cases, but also really understand a couple of the high level nuances of the major commercial models so you're picking the right one. Because I would guess you'd get a worse output with a different model just because of the data input. Okay. That is super, super useful. And then so you've talked a lot about customer interactions, CRM updates, meetings, but you also get a lot of asynchronous customer feedback, including from me. And shout out, whoever is on the receiving end of my support and product feedback tickets. Thank you. I appreciate you. You're always really, really responsive. How do you drive that responsiveness using AI or systematically across a pretty large customer footprint? Yeah, it's fun. There's a lot of things. I'll walk through one of the things I have found impactful, especially with like our newer products that we're pushing out. One thing I'll say, I can't show this, but again, does work with data and getting better relationships with data engineering. I think when we've started to like unlock more and more capabilities with data on that front as well, like with MCP just this week, our team got to the point where we're now properly like analyzing a lot of feedback and actually creating pages in Coda for review things for our team as we walk in based on like new trends that are emerging amongst the data automatically, which is quite fun. But one of the things that we've also done here that really helps is just like making it more searchable for folks. This is really helpful for like not even the core build team that's working on the product, but when I'm working with, for instance, like sales or I'm working with PMMs that are supporting us with launches, they'll often have questions of like, hey, what feedback have we been receiving lately? Or like, are people doing this sort of use case, right? And they're just, they have very specific questions or they're trying to understand something. Or it's the designer who, as we're diving into a topic, we want to like really quickly surface times where users have had issues with the like error log system and they want to like find like, hey, can we find that? And so we created like a little chatbot here that essentially just like, it's really simple, but it is fed with a bunch of like databases essentially. And then just like makes that really easily searchable, right? It's a standard chatbot rag type thing. I won't go into it in much detail, but it's like internally locked down for us and all those things, which is really helpful. And we also use this sort of system externally as well. Like you'll see one of the things that we do here is I have our MCP helper chatbot transcripts. And so I have this kind of like end user facing chatbot and you'll see it, it has these like knowledge sources, which are basically just like our help docs, as well as one table, which is like a Google sheet type thing. It's our sappier world of that. And I love this little system and I'll just talk about it for a second. And it's really just, you know, for anybody that's working with data and knowledge management things, it's difficult to keep it up to date. And I found myself previously constantly like trying to go back to our knowledge sources that these bots had and just like trying to manually keep it up to date on like a monthly or quarterly basis. But one system I ended up finding that worked really well for me is I built like one, there's a zap somewhere that essentially every time there is a closed support ticket, or if there's a finished chatbot transcript, it analyzes the conversation and tries to say like, what is the core FAQ from this? Like what was the core issue? What was the solution, if any? And is that already in the knowledge base that we had? If not, please propose an entry. And so what I then do is I have my like human step here, where I can actually review the FAQs that it wants to submit. And all I have to do, I can edit it as well, like what the answer is. And if I approve it, it goes over to a different database, which is the one that the bot is actually using. So a really nice way that I have found consistently now on a number of projects just to like rapidly iterate and keep those things up to date so that users are just getting like their answers faster, which is really nice. Yeah, what I like about this is I often tell people who are trying to figure out use cases of AI or implement AI solutions, is they really get stuck on like the I'm doing X, how do I use AI to continue to do X or do X faster, whatever. And that's fine. I think that's like, I'm already taking meetings. How do I make taking those meetings a little easier? But the challenge I often give people is, let's say you had the perfect team with infinite time. What are the things your perfect team with infinite time would do in any one step? And your perfect support team with infinite time would look at every support question and would go see, do we have the right help desk content here? And if we don't, let's write great content, and then let's publish it, and then let's put that in chat. But none of us live in ideal worlds, we're super busy. And so I think this is like a really good example of that, where it allows you to operate at a next level of quality, not just like velocity, but a next level of quality. And then again, like the more high quality data you create, the more you can power interesting AI solutions to your customers like chatbots. And so, you know, again, anybody out there looking like, if I had a full fledged team of SDRs that were perfect and had infinite time, what would I do? Or like, you know, 10,000 support people with infinite time, what would I do? Like start to think about those use cases, and don't forget to pluck those off, because I think they can unlock some interesting ideas inside your team, and then let your team act as higher leverage folks. I like the way you put that. The other, I don't know if it helps ever to anybody, but the other way I often tell folks that are struggling with that is like, if you could run Chachabit in your sleep, what would you do? It is, you know, I've found a really good way to help people start brainstorming ideas. I will say as like a maybe a side on that, on the product design world, we found, we did one experiment really early on, that was kind of like Mad Libs, to help discover use cases and stuff. And it was a very interesting experiment in that it seemed to actually help people discover what they wanted to do. But it also challenged them to think through like what their pain points were. And it was really fascinating, just to experience. So for anybody looking at that in their products, try a Mad Libs style AI enabled system to like ask questions and ask follow up questions with free form text. Just to kind of take a step back and walk through what you what you showed us today. We have MCPs, Zapier MCPs in particular can give you a really custom set of tools to call. You like Claude, you like using Claude projects to give instructions on tool calling sequence and instructions. So you get really high quality outputs of that. And then you're really focused on, I heard you say very early on in the episode, avoiding things you hate, which is like all of us updating the CRM. You know, attending what we all attend, which are just in time meetings, right? You just get out of the next meeting and you show up in the next one without context and making sure you're prepped for that. And then kind of this virtuous cycle of customer feedback, support feedback, FAQs, you know, internal input, and then customer facing help content as kind of a happy, happy circle here. And so I think this is great for anybody who's spending a lot of time with customers, whether you're in sales or support or product, to be better prepared and get stuff done with less tabs open in your browser, which is what we all want. Well, Reid, I'm going to do a couple lightning round questions, and then we'll get you out of here back to pushing the boulder up the hill. My first question for you is, we've seen a lot of business use cases, what are like your favorite personal use cases? Like what are ones that have really surprised you either by making, you know, really sparking joy or just really solving a problem personally? Yeah, I'll touch on two real fast. Number one, in terms of solving a problem, family calendar planning. For anybody that has kids and families, like family calendar, it's a real thing. And for me, the struggle is, my wife and I both like a physical calendar in the house and we're reluctant to get like a full digital frame thing. So we have a physical one that we write things on, but I like live by Google Calendar. And if it's really not my Google Calendar, it like doesn't exist. And particularly if it's a family event that's in the middle of like a normal day, then someone can book a meeting over and that's really not good. And so I actually have a cloud project called Family Calendar. It has really detailed instructions on, it's not too detailed, but it basically tells it like which calendar to look at, how to add things if it's an event that's at my son's school or somewhere to leave time in my calendar to drive there and drive back if it's, you know, during the business hours so that that is blocked. And now what I do is like occasionally I just take a picture of the physical calendar and then it uses the various like find and update and create actions for Google Calendar through ZapierMTB and just like does all of it. And I love that. That's probably like one of the greatest things. Other than that, these days, Suno, they had a big V5 update recently. I've been loving it with my son and his other like friends in our neighborhood. We've made a lot of songs together. I literally just like talked to Claude and I was like, hey, Claude, you're going to write a kid's song for my son, Leo. He's four. Here's what we did today. And I just like told it what we did. And my son insisted that it have poop and fart jokes in it as well. And so I was like, well, you need to have some poop and fart jokes. And my son has listened to this, at least on Suno alone, 14 times. We gave it to one of his babysitters and they listened to it together like nonstop for an hour. And we've done this with like his friends and they've made songs for each other. And it's really fun. And it's the other thing, too, is like some of the older kids nearby, like one of the girls like 10, almost 10. And she's been learning about like prompting through this because she was like, oh, it said this, but like that's not right. And I was like, well, you got to be specific in this and you got to like instruct it. And so I have I gave them like a whiteboard with a dry erase marker and they're just like writing out their little prompts and then I input them for them. And so that's been a lot of fun. And I think hopefully a little bit educational. I have to I have to just bring us back to our starter topic, which is to Suno have an MCP? Good question. I am also a extreme Suno power user, love it. And imagine imagine you could take your customer prep meeting and just give yourself like a friendly jingle to remember what they're talking. You laugh, but I've actually I did that with I took our I took our MCP sales training session. I actually took the transcript from Zoom along with the deck and I gave it to Claude. And I said, come up with a pop song, I think, for this. Yeah. And I've actually shared it. And a couple of our like sales team and product team have actually listened to it and really liked it. I mean, yeah, we we teach kids with music. And humans have been, I don't know, music people much longer than we've been reading people. So it's it's fun to explore that. I might I might have you beat, which is I took a incident postmortem for like an engineering incident and then made it was like a punk song about how we needed to solve the root cause issues. And it was called Renew the Certs. It was it's a very it's a it's a certified banger. So we'll have to put a playlist together and put it in the show notes. OK. And then there's one last use case, which I love. I want to make sure we spend a couple of minutes on it with Notebook LM. Yeah, this one, I think Notebook LM I use personally for learning. I put like a lot of things in it to learn. But I got one that I got a lot of value from and a lot of brownie bonus husband points from with my wife, which was she was recently like job searching. And what I did for her on all of them was like when she got the interview, I would take their like careers page, I would take the job thing, I would find like more information. And I had like a prompt I used for the audio overview that was like, you are preparing Anna for this interview, like make sure it's specific to Anna. And she listened to all of these before. And she like constantly got feedback about the process that she was like the most informed applicant. She clearly understood the space because, you know, it always felt like talk about the competitors, what they're doing in the marketing world and what are trends going on there. And she loved that it was also like, so Anna, we're going to prepare you today. It was really cute. But it worked exceptionally well for her. She ended up getting like the ideal job that she really wanted. And yeah, it was pretty awesome. So I highly recommend that. It's also great bonus points for anybody out there with friends, family, interviewing the ways that you can really help them. OK, I'm going to have to make hats, which is like my love language is personalized A.I. podcasts. It's very good. It's very good. Husbands out there, wives out there, partners out there. Demonstrate your love by doing knowledge work via A.I. for the things that your partner needs. OK, this is this is amazing. This is really fun. So many tabs open in the sidebar. I'm sure so many other things you could show. Reid, thanks for joining. Where can we find you and how can we be helpful? Yeah, where you can find me. LinkedIn. I'm most active on LinkedIn. I do love the LinkedIn. So you can find me read our EID Robinson on LinkedIn. You'll probably find me pretty quick if you can help. Honestly, I'm a sucker for product feedback. Like try some of the things I've talked about today. Tell me what work. Tell me what didn't work. Tell me what you wish existed. I also love hearing from the folks who are thinking about the future of all of this. Who've tried like wacky things and they're like, hey, if only I could do this. I'd love that, like bigger picture thinking stuff as well. So if you've got some like wacky ideas in the world of tools and agents and automation stuff, let me know. If not, yeah, try Zapier MCP. Give us some feedback. Would love any and all. Amazing. Well, thank you so much, Reid. I really appreciate it. Really appreciate you having me on Claire. 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.