AI Tinkerers - "One-Shot"
00:13:57 · Joe Heitzeberg, Luke Harries
[00:13:57] S1: I'm jumping jumping a couple steps ahead for a second. The thing that I immediately saw from it, going back to your original tweet around email, WhatsApp, and and calendar, was to build a cloud... Or an MCP server. Yes. Or client. Sorry. I wanna build a a client in my server infrastructure that uses this MCP WhatsApp interface behind the scenes as part of an app that is providing a service. [00:14:24] S0: Yeah. [00:14:24] S1: So wanna automate my... Part of my WhatsApp interfacing with my community or my business or for my business Yeah. As me [00:14:32] S0: Yes. [00:14:32] S1: Natively as me, but with agents. Right? [00:14:34] S0: So what's... That's why I actually built first. Yeah. And so the way I built it is I was... If you look at the code... [00:14:46] S1: We should look at the Yeah. [00:14:47] S0: I can show you the code briefly. So, yeah, what you've got here, you've got this bridge, which is all the Go files, and you've got the MTP server, and so these are the Python files. And if you look, I've actually have an extraction whereby whatsapp dot py is all the, like, business logic. But then there's a very thin wrapper in main dot py, which just takes each of the functions in WhatsApp dot py, adds a nice arg string, and adds a at MTP dot tool, which is just like a Python line Mhmm. Python client to expose it. But but... And what this does is it makes it very easy for your MTP clients to access your MTP tools. Mhmm. But what's interesting about this MTP system is it's actually mainly set up for, like, human interaction in the loop doing approvals.
00:14:47 · Luke Harries, Joe Heitzeberg
[00:14:47] S0: I can show you the code briefly. So, yeah, what you've got here, you've got this bridge, which is all the Go files, and you've got the MTP server, and so these are the Python files. And if you look, I've actually have an extraction whereby whatsapp dot py is all the, like, business logic. But then there's a very thin wrapper in main dot py, which just takes each of the functions in WhatsApp dot py, adds a nice arg string, and adds a at MTP dot tool, which is just like a Python line Mhmm. Python client to expose it. But but... And what this does is it makes it very easy for your MTP clients to access your MTP tools. Mhmm. But what's interesting about this MTP system is it's actually mainly set up for, like, human interaction in the loop doing approvals. [00:15:42] S1: Yeah. [00:15:42] S0: I don't think really anyone's using MTP clients in a fully automated way. But why I've done it this way is you can actually wrap all these whatsapp.whatsapp.py tools, and instead just expose them to any other LLM framework. Framework. [00:16:00] S1: Mhmm. [00:16:00] S0: So another, like, experiment I did with this was you can connect it to the OpenAI agents SDK Mhmm. And you can just pass those in. I think the... And then it's like a very clear, you know, it's like any agentic system can call it in the loop. [00:16:15] S1: Sure. Yeah. Cool. Which, I mean, makes sense. I I don't wanna always be in the loop for things that are clearly trivial.
00:16:15 · Joe Heitzeberg, Luke Harries
[00:16:15] S1: Sure. Yeah. Cool. Which, I mean, makes sense. I I don't wanna always be in the loop for things that are clearly trivial. [00:16:20] S0: No. No. What... What's quite nice is, like, when most of the usage is is exactly as you said. It's like people normally in group chats often in places like Brazil or India where lots of, like, businesses or groups are running on it. So you can imagine you have, like, a fitness WhatsApp group Yeah. Or a voice AI WhatsApp group. Mhmm. And you want to basically, like, do a roundup of all the messages of the last week, like, you can kind of run that. But exactly, like, someone like you who's a a Tinkere would probably actually like, okay. I've done that once. Now how do I actually put that in the loop? [00:16:55] S1: Yeah. Yeah. It makes sense. And I want sort of something that's, you know, especially in WhatsApp, there's lots of groups I'm part of that I'm not gonna be spending my entire day watching every thread. Yes. But occasionally, there's a thread that breaks out that I definitely wanted to pay attention to. [00:17:10] S0: And what's very cool as well is, like, the advanced search. Yeah. So you could be... You're in a bunch of WhatsApp groups, and you're like, oh, like, what's the, coolest things happening about MTP or conversational conversational AI? AI? And you just ask it. Yeah. We'll do the search and then do the roundup for you and then synthesize it all together. [00:17:28] S1: What... So one of the groups of mine is doing that. I'm wondering if they're using your MTP.
00:17:28 · Joe Heitzeberg, Luke Harries
[00:17:28] S1: What... So one of the groups of mine is doing that. I'm wondering if they're using your MTP. [00:17:31] S0: It it may well may well be. Yeah. But the... I mean, the hard stuff truthfully is this what's meow bit under the hood. This is... Basically just done the nice [00:17:40] S1: Do worry about being blocked? So I You won't be blocked. The the user of it will be [00:17:46] S0: Yeah. The bit I need to add a risks bit to this Uh-huh. Repo. But the... I think read is very, you know, pretty safe. Yeah. And it's also... If you think about the spirit of WhatsApp, it's like not actually going Yeah. You know, you're reading your messages and querying your message. Do do... I think the mass sending though, that is scary. Yeah. And you should be careful if you're trying to do WhatsApp. [00:18:07] S1: And I think... I mean, some kinda high level conceptual view, these businesses, WhatsApp and etcetera, were designed for human interaction. [00:18:15] S0: Yes. [00:18:16] S1: And, you know, we may build agentic systems that use those pretending to be humans, but the business is disrupted. Right? Yeah. At some level. So they're not gonna like that, or they're gonna have to adapt. [00:18:25] S0: Yes. [00:18:25] S1: And there's gonna be a mess. You know, actually, two weeks ago, the first time I... You know, we've all seen lots of captchas. I saw a crazy one. This captcha made me listen to three bits of sound [00:18:35] S0: Mhmm.
00:18:35 · Luke Harries, Joe Heitzeberg
[00:18:35] S0: Mhmm. [00:18:36] S1: And tell what I was listening to. Wow. So I was like, which one of the four clips is water running? I had to listen to four clips and choose a b c, I and had to do that exercise three times. Took forever to get through this caption. Can only imagine because of... You know, they obviously really don't want robots. Now robots are coming. What's what's gonna happen with with all these wonderful... What is this? [00:18:56] S0: I think, first of all, is if you think about the spirit of WhatsApp... MCP is like it is human in the loop. Yeah. And so if you're, say, a business in Brazil and you're sending out invoices over WhatsApp, currently, that's incredibly clunky. Yeah. But now you can your WhatsApp MCP with your Salesforce MCP. [00:19:17] S1: Yeah. [00:19:17] S0: And like you can actually there be orchestrating that. Mhmm. I I think your side note, which is really interesting, is like, what actually does the future of communication look like in a Yeah. World where AI is at par. And I personally really like where the world coin direction is going. I'm not sure if you've scanned your eyeball. No. But the... It's some pretty cool privacy stuff of like, you scan your eyeball, you uniquely prove that you are one human. And then that you could build a messaging protocol on top, which is like, okay, what's a reasonable number of messages for a human to send? K. It's in the hundreds but not the thousands. And then you can also, like, punish bad actors who are overly extending their their Yeah. Their message systems or sending spam.
00:19:17 · Luke Harries, Joe Heitzeberg
[00:19:17] S0: And like you can actually there be orchestrating that. Mhmm. I I think your side note, which is really interesting, is like, what actually does the future of communication look like in a Yeah. World where AI is at par. And I personally really like where the world coin direction is going. I'm not sure if you've scanned your eyeball. No. But the... It's some pretty cool privacy stuff of like, you scan your eyeball, you uniquely prove that you are one human. And then that you could build a messaging protocol on top, which is like, okay, what's a reasonable number of messages for a human to send? K. It's in the hundreds but not the thousands. And then you can also, like, punish bad actors who are overly extending their their Yeah. Their message systems or sending spam. [00:19:59] S1: Yeah. Interesting. There's something there. There's, you know, clear trade offs. I don't know if you're aware, but in The US, if you're on global entry system and you go back to The US from overseas, you walk up. It's the best experience of this genre that I know of. Yes. Like, you you don't... I don't take out my glasses or just my hat. I literally just look at the screen for a moment, a second, and it's like, welcome back. I don't show any ID. I don't show anything. I scan a passport. It's just face recognition. It's the best implementation of it, and it's a breeze. And I love that [00:20:29] S0: Yeah. [00:20:29] S1: The the convenience of it. [00:20:31] S0: He he says government conscience