Real Investor Radio Podcast

4kd.ai hosts Jack BeVier and David Moses discuss how David’s real estate management company is rolling out AI agents to nearly 28 employees, including the data, permissions, and workflows behind the system. They also examine where agents can improve operational memory and risk review, and why deterministic controls and human judgment still matter.

What is Real Investor Radio Podcast?

Real estate entrepreneurs are the best people. On Real Investor Radio, we’ll cover advanced residential real estate investing topics. We’ll discuss how what you have seen in the headlines will affect your real estate investing business. And we’ll go deep on these topics to help you make better decisions and take specific action.

Jack BeVier (00:00)
Hey everybody, welcome to another episode of Forked.ai. this is your host, Jack Bevere, along with my co-host David Moses. David, wonderful to see you, sir.

David Moses (00:08)
Great to see you two. Looking forward to seeing you in person very shortly here.

Jack BeVier (00:13)
Yes, yeah. We are convening every four months as we do a real investor round table. Get about thirty or so very active real estate investors from lots of different markets all over the country. We all get together and kind of share, put put together a soft agenda and share kind of what's going well, what's not going well, the challenges we have and try to just, you know, kind of use the room as a as a mastermind to help.

Make our businesses better, come back with actionable things that we can actually improve our businesses. So we got that coming up in Charlotte very shortly next week. And yes, I look forward to seeing you there, man. That's gonna be a lot of fun.

David Moses (00:50)
It will indeed. It will indeed. So so we were talking before we before we started this this session here that I I I'm very close to reaching my goal. my goal is November ninth to have every every single employee at the company has an AI agent that they can work with. And that AI agent is able to draft emails for them.

It's able to see everything they can see. So all the files they can see, their agent can see, all the permissions they have in the various CRMs that they're in and out of. we use property meld, we use App Folio, we use a software called Sync for community management. And so on the community management side and on the property management side, including accounting, even even our biz dev, we'll all have

an AI agent. We're about five agents away.

Jack BeVier (01:45)
How many people are we talking about?

David Moses (01:48)
it is I think it's twenty eight.

Jack BeVier (01:51)
Okay.

David Moses (01:53)
And

I'm quite certain that I need to add some more open AI tokens, probab probably I'm guessing three more. but because as as we grow, we're we're also I'm I'm building a workflow that tests on it. Well, first it's kind of frustrating because not all CRM systems have audit logging that is accessible through the API. it which it it just sucks in general, because that should never

That should never happen. Audit logging in twenty twenty-six should really only be it shouldn't even be available through the UI. Just it should be only API. It should be only MCP. There's really n

Jack BeVier (02:28)
Right. It's too much. Yeah.

David Moses (02:30)
there's no reason audit logs should be reviewed by a human ever. but anyway, a lot of them just don't have them accessible from the API. And that the the in the underlying issue there being

that we can't we we have to essentially create our own logs. So we're polling all the systems so that we can determine what records changed and most importantly who changed them. So yeah, it's going to give us some really cool information. We'll we'll basically take look, here's the record, here's what it was before. you know, it'll essentially just, you know, give us summary of any fields that have changed. And if no fields have changed, usually because somebody changed something by accident and changed it back before.

it pulled the next time, then, you know, where that last updated field updates, but no no information has changed. you know, but you have who made the change. And that's important for us because we're we're essentially for adoption for us, I don't it it's it's not going to be based on tokens, right? It's not going to be based on this is how much time and energy and t you know that they spent with their AI agent, although that's a good way of measuring

in general, what we really want to measure is how much of the work that you do on a regular basis is actually being done, you know, where the final product is delivered by you without the assistance of AI. And I consider that an accounting person coding an invoice or a property manager sending an email to a tenant or to an owner whose property we manage, a community manager.

having a conversation with a a board member and writing a note about it. All those things should be

Jack BeVier (04:09)
Yeah.

David Moses (04:11)
influenced by what the human is doing and directed by the human, but memorialized by AI. That way you know the records are just wildly more useful and the context we need is gonna write is going to be right in the systems that we're already using.

Jack BeVier (04:27)
All right, let me I have a thousand questions. Just to refresh and contextualize the conversation here, because this is I think a place where a lot of businesses would like to get to. And you'd learn a lot getting just getting to this point, right? There's a lot of work, took a lot of work for you to get to the point where you could even do this from a practical perspective. So let's talk about the architecture real quick, just to refresh listeners' memories. So you got

Sync is your HOA management system, app folio for property management. What's accounting again?

David Moses (04:59)
We use well for I I call it app that we we we have ops accounting and corporate accounting. So ops accounting means accounting as an operation for others. We're we're accounting for your, your property and how it does, your community. We're doing your books. That's, essentially accounting as a service. Those are done directly in those CRMs, like directly in App Folio, directly in sync. And then our corporate books right now are done in QuickBooks. I would say

Jack BeVier (05:22)
Online.

David Moses (05:23)
yeah, QuickBooks Online.

I have no real great defense for it other than it seems to be reasonably reliable in downloading transactions from the actual financial accounts that you know that w where they're housed. I I I see no other reason to choose any one ERP system from another. They're all they're all pretty much.

Jack BeVier (05:43)
And did any other any other sources of data, any other softwares that you're using as yeah, property build, sorry, for maintenance.

David Moses (05:49)
Yes. We'll we'll we'll use property meld. yep. We

currently use Z Inspector for inspections. We probably won't unless they very quickly get an API. we're we're building little our own little mini inspections in hopes eventually we'll either replace them or we don't really want to replace them. We'd rather just use them. But if they don't have an API, it's really

Jack BeVier (06:10)
If you don't do an API though, yeah.

David Moses (06:12)
Yeah, it's kinda useless to us. so we you know we use Z Inspector. Obviously we have

our phone system through dial pad. We've got our emails through Microsoft and files files file storage through Microsoft as well. and our meetings are generally done if they're on the community side in Zoom because communities kind of demand it. They just I don't know they just trust Zoom and and then we use Teams for most other other types of meetings. And we use a software called Fireflies.

And a software called Plaud. So if Fireflies does, you're in a web meeting, it'll jump in no matter what the platform is, whether it's Go meet or it doesn't matter. it doesn't matter the platform, it'll it'll jump in, record, take notes. and then and plod is like for live recording. Okay. I'm like I'm I'm at a meeting, I'm in a meeting face to face. I use plod for recording and a couple other people at at the office have that.

and then their phones, they they'll go in and record. and then they just, the idea is that they'll give those to their agents and then we have a Mongo. Mongo is basically just our repository for everything. It's a no SQL database. it has very, very quick write capabilities. and it I think in our businesses it's very common to write a whole lot of data that

most of which you're never gonna need to retrieve, at any, particular time for any particular reason, but it's just you just need to need to accumulate it. So Mongo gives us very quick write access. And that's that. That's basically our stack our tech stack. know, those are the

Jack BeVier (07:44)
And are you

and you're using Hermes as an agent? As her as Hermes agents, cloud? Like do you just

David Moses (07:47)
Mm-hmm. Harney's the harness, yeah.

Jack BeVier (07:50)
you go in Hermes and you do you the do the cloud agents?

David Moses (07:54)
our w it's all hosted on a Mac Studio.

Jack BeVier (07:56)
All hosted on a Mac Studio?

David Moses (07:59)
One singular Mac Studio hosts all of our agents. it is it has been a challenge

Jack BeVier (08:03)
It is it's

David Moses (08:04)
to get to enforce the agents to save things to my to to OneDrive and SharePoint instead of saving it to the local drive because like all of a sudden it'll be like 90 gigs was added in a day from some agent doing some long-running thing. And usually it's me who's created the issue. And then I've got a

Hey, migrate all this stuff off of here. We don't have unlimited storage on this little on this little Mac Studio. But it's it's a robust Mac. I it's ninety six gigs of RAM, or maybe it's 128 gigs of RAM. It's a it's a it's a powerful machine. and it yeah, it hosts everything. We back it up to a physical drive every night, and then we also back it up using Backblaze, and I think that's every six hours. And that's that.

Jack BeVier (08:46)
So you're the agents that are running on this Mac Studio, did you create separate virtual mach like how how did how you have multiple agents running on one Mac studio? Just walk me through that.

David Moses (08:56)
It's one harness

to multiple agents. So it it's only one Hermes instance. It's only one

Jack BeVier (09:01)
okay. Okay.

David Moses (09:01)
Hermes instance. They just it's just all all of our we have our our our essentially our call it our our our chief technology officer agent who basically builds the agents, decides permissioning is actually kind of easy because it just mirrors whatever Microsoft

permissions are. If they can see the folder, they can see the email, they can see the, that's all, that's all there. And then on the on the on the side of the sync and app folio, the API doesn't let you do everything. And you can't pay bills, it from Appfolio or from Sync. but through the API, there's really there's no way of permissioning one agent's work like hard

hard permissioning it so that they literally can't make a call in you know in sync. So we have workarounds for that, which is we'll either have an end it end workflow that basically like if somebody would only have read access to a particular system. So let's say I I've got to have read access to QuickBooks because I've got to be able to check to see if this if this was invoiced, I have to be able to pull out the invoice. I have to be able to, you know, whatever I have to do, but I I but I only want read access.

you could actually create a you for QuickBooks, you create a key that's like this is only a read access API key. So you don't have to worry about ever any anybody making a a call that that they're not allowed to make. That doesn't hold true in sync or app folio. So what we have to do is we create these workflows in N8N where we hard code the call. So it's either, this is how you make a call, we have a separate API key that we generate.

And this little very small, very easy N8N workflow, all it does is receives the the call formatted exactly the way it's supposed to be formatted for the app folio API, but then it hard codes the command. So it's either, you know, if they have read only if they only are getting read access to a particular endpoint, or if they only have access to certain endpoints, then it will allow them to make a call using any of those endpoints or using any of those commands.

But it's hard coded in the N at N workflow that it will reject it if it's not an accepted, you know, command or endpoint. So we have to create our own permissioning behind that.

Jack BeVier (11:20)
As that done at the So you have one Hermes agent that has access to all of these systems, but then the subagent you manage permissioning on the subagent level by employee and their role.

David Moses (11:37)
Yeah, so okay, so just just a little difference between from what I understand, and I may be wrong on this, but open claw versus Hermes. So in OpenClaw, it's this shared agent ecosystem where they all share the th the memory, they all share, the skills. It's all a big C. Whereas with Hermes, it's it's different. Each agent has their own little

pond, right, that that they that they live in. And they can only talk to each other if we give them permission to talk to each other. They're they're fairly well siloed. Their memories are, you know, one one agent can't access another agent's memories unless

Jack BeVier (12:17)
Sorry to be pedantic, but and you mean sub agent right now, right? 'Cause there's only one Hermes agent.

David Moses (12:22)
Hermes is the harness. So Hermes is the harness. So all the all the agents are spawned, right? Like they're they're they're they're operating in parallel. They're not yep.

Jack BeVier (12:28)
yeah. Okay. Okay. Yeah. They're operating parallel. Okay. Okay.

That that's the that's the thing I was screwing up. Got it. Okay, cool.

David Moses (12:36)
Yep.

So so then they can spawn each agent that we can actually interact with. So there's there's subagents that are temporary subagents. you create two subagents, you're gonna run a

Jack BeVier (12:45)
Three projects, tasks. Yeah.

David Moses (12:47)
yeah. th those are things that you wind up doing, like when you're using things like Claude and OpenAI, like and and Grok for sure, they they'll spawn the subagent. They don't tell you how it's doing it, right? Like it's it's it's getting it right.

That's all you care about, but in some instances it's spawning multiple sub agents as it sees that it's necessary in order to make sure or validate what it's what it's telling you. And of course that's still happening with our agents, but with our agents, because we want you know, we're we've got live data, we've got, you know, these are financial transactions in many cases. They're you know, these are this important data that affects people's lives. So we typically when we're doing

anything, there is there is at least a validator agent by rule. you're gonna enter this tra you're gonna enter this you know that this transaction into QuickBooks. You have to have a validator agent that looks at the call you're about to make, looks at the transaction and says, I agree with with how the first agent determines to do it. But that's all sub agents kind of behind the scenes. We don't talk to those sub agents. we talk directly to the agents.

Jack BeVier (13:52)
Is the

is the validator agent, for example, or like

The corporate the corporate guidelines policies and procedures is that memorialized in an age in a in a in a you know a permanent agent state that acts as a you know a manager, so to speak, to make sure that one of the employees agents doesn't perform a task which is outside of policy? Or are you relying upon the direction of the employee to be within guidelines, within guardrails?

David Moses (14:25)
So there is obviously reliance on the employees. but there's also the every single thing you ask your agent to do is memorialized forever. Right. So if you ask your agent to go look in David's emails for anything that could be, you know, used to blackmail him, like, you know, it it knows. It it it remembers that she said that and and but there it you know and and then we run like, you know

Hey, look through all of the agent's activity and tell me if you see anything that's a security risk or that's potentially a you know, a legal risk. And we, you know, but but no, like we don't have a master agent that's and and that's probably something we need to do. So like we don't have a master agent that's literally monitoring on a regular basis what each individual is discussing with their agent, right?

What we also what what we generally do in terms of enforcing policies is that they use skills. And I'm learning that skills are not a reliable way to automate anything. skills are soft guardrails guidelines at best in the Hermes world. They're probably not much better.

in any other system, if they are better at all. so what I'll say is if it's something that needs that is repetitive, that needs a reliable process, it should be, you know, an automation software like NADN should be engaged. Or you can do it as a Python script. You can do it, you can create scripts around it, but those scripts need to be

largely deterministic and so so think of it this way. It's like a skill is basically a recipe for how to make soup. Right. And it tells you all the ingredients. It tells you what temperature to use. It tells you in what order to put those ingredients and how long to wait between. but you're a human being and if you think it, you know, last time you made it it wasn't spicy enough or if you think whatever, you can just mess with it.

however you want to mess with it. Whereas a Python script or an NATN workflow, you're gonna go into the kitchen and y, you know, the all the ingredients are pre-measured for you sitting where they're supposed to be, and you're assembling them. And and and you don't have there's it's not you don't have like extra garlic sitting around, right? It's just this is these are the ingredients you get and this is the the steps that are enforced. The oven literally won't work.

until you, do this, it won't the the the oven only has one temperature and it's the temperature you're supposed to use. so so that's that's the kind of thing when you when you make it into a Python script or an N Aden workflow, that's the kind of thing that gets enforced. it just increases reliability considerably for us. And then we can and I just I like the visual nature that there's nothing inherently better about a Python script

or about an N it in workflow. They they essentially pref they do the same thing, but one is visually

Jack BeVier (17:32)
Yeah.

David Moses (17:34)
one one you can look at visually and see it firing. and I like that.

Jack BeVier (17:39)
Yeah. And there's no reason to leave something that is deterministic that you want to be deterministic. You want to be an if-then statement. There's no reason to leave it to chance. Even if the agent would get it right 99 out of a hundred times, just write it in code, and it yeah, it never never gets it wrong. It's a hundred, yeah. And cheaper. Yeah, exactly. Yeah, yeah.

David Moses (17:54)
What's the point? Yeah. It's a hundred out of a hundred. And and you're not and you're not wasting tokens on something that's completely yeah, it's

Jack BeVier (18:02)
The script's much cheaper to run than the tokens to figure out the result problem of

the problem.

So how are you are the agents that's super interesting. Are you are the agents per person? Like is it like each person's got an assistant and that assistant has a name now? And they're essentially assistant whatever the role was to just take stuff off of that person's plate? Is that the

David Moses (18:23)
so automations are generally automatically do this for me every time. Those are automations that kind of they go a level up and somebody else builds them. But it's not it it it's really it's

Jack BeVier (18:35)
And were they kept? Some somebody else builds them and

then where were they were were they compiled?

David Moses (18:39)
Yeah, w w say that again.

Jack BeVier (18:41)
All of the automations and NADN flows, where are those running from? Where are those compiled?

David Moses (18:46)
That's a they're running

on an EC two, like an Amazon EC two server. It's like a cloud server. Yeah, it's a cloud

Jack BeVier (18:49)
What's C what's EC two? Is that just a cloud server? Okay, gotcha.

David Moses (18:52)
server. so it's yeah, it's nothing. you know, it's it's it it's good enough.

Jack BeVier (18:59)
Mm-hmm.

David Moses (19:00)
and and fable, Opus, even even Soul and Astra from from OpenAI can manage it really well.

So that's good. And and we have but but the way the way we're using it is really it's more along the lines of you were gonna go enter this transaction. Don't enter that transaction. You were gonna go update this tenant's record. Don't do that. Right? You're gonna tell your agent what you wanna do. Your agent is gonna go scour all of our systems that it can access. The thing like if I ask you, it's if I said your only job today, like

I'm gonna I'm gonna pay you your salary. You're like you're not gonna get there's there's no I'm not gonna dock your money, but but all I want you to do, well let's say for the next two hours is I want you to record this one what happened on this one work order. That's all I want you to do. Right. And you need to fill the time, right? Some people are gonna twiddle their thumbs and fuck around. But some people are are are gonna overdo it, right? They're gonna, they're gonna go, they're gonna look at every single picture, they're gonna like, you know, kind of write a little note about every single picture.

And they're look at all the pictures together and see, okay, did that tell this whole story? Is there something missing? They're gonna look at what the what the tenant called in originally. And then they're gonna look at all the communication between the tenant and the technician or the tenant and the property manager along the way. And then they're gonna look at the closing notes and look at the closing pictures and then when they're all done with that, they're gonna they're gonna put this incredibly detailed set of notes into some system, right?

And I'm to to some degree I'm oversimplifying this, but it would be it's extreme overkill and i no one would ever do that who worked for you un unless you like literally force them to do that, because it just feels inefficient and wrong and stupid, right? Even though one out of every eleven times they do that, maybe one out of three times they do that, depending on the technician, they're gonna find something really fucked up. They're gonna find something

That just shouldn't have been done that way. Or they're gonna find something missing, or they're just gonna miss something that some other stakeholder is gonna call and ask about six months from now, right?

Jack BeVier (21:14)
Yeah. Yeah.

David Moses (21:16)
And hold their feet to the fire on it. And so

Jack BeVier (21:18)
Yeah.

David Moses (21:19)
and so what I tell them is like just there's no point for you to go in and put in a closing note. There's no point for you to go in after having this conversation with this tenant and go and create this work order.

With this ticket. It's it's silly. Your agent is gonna go grab all the context. It's gonna look at how many times has this person called before about the same issue? How many times did the previous tenant call at this unit about the same issue? Are there unattendant? If it's a multifamily, are there un other tenants in the same building? Where are those units relative to this unit? All these things that if you build a workflow around it, all these things are gonna get taken care of. But we can't build, we just can't build

automations and workflows around every single thing that we do. So and and it was we were beating our heads against the wall because a lot of this stuff is really common sense. And the agents will learn from our people's experience much faster if we just give them an agent. Talk to your agent. Tell your agent what you're trying to record. What what is what is the solution? What what is the what is the outcome that you're looking for? And the agent is going to go and look at all of the previous

times where this thing was recorded, which this this is how it'll build on itself over time. because as though, as the previous work gets better and better, those are the good examples that the that the agents can look at, look back at when they're trying to do these tasks in the future. So don't do it. Just have your agent do it. Your agent's gonna go to all the systems, grab all the context it needs, grab all the phone call transcripts, grab all the emails, grab all everything that's

That's not where it's actually supposed to be, right? 'cause I had a conversation with this tenant about the fact or, somebody in the office had a conversation about with the tenant about the fact that they're eleven days behind on their rent. And they mentioned something about, this work order and the person who's talking they just wanna they just want the money, right? just just pay us, all right? They're not they don't care about the, the jiggly door handle. They don't care about

The fact that they said that the lawn guy was cutting the lawn and a stone flew up and and hit the basement window and cracked it. Like the person collecting money doesn't care about that. But then that contact that context gets

Jack BeVier (23:29)
Yeah.

David Moses (23:29)
pulled in and that agent tells the property manager, Hey, wait a second, you know, before we record this, you know, this this three months later, the tenant finally calls in the work order because, you know, now the crack is is is now like some animals come in and whatever.

Jack BeVier (23:42)
Ha ha ha.

David Moses (23:43)
Right. And now we go like

Now the context can be, hey, go back to the lawn guy and be like, hey, dude, you were here, you cracked the window, whatever, whatever. and and it, you know, exactly. Like it's not and and be

Jack BeVier (23:55)
Yeah. Yeah. Mystery solved. Yeah. Yeah. Without digging for an hour. Yeah.

David Moses (24:03)
It's right, without without trying to solve, like, I don't understand. How did this, you know, situation go from from

Jack BeVier (24:06)
How'd get here? Yeah.

David Moses (24:08)
how how did it get to this point? and and I think that

The more and more tools we give them and the smarter the agents are, the the more fun their jobs seem to be. The people, I mean, we have 20-something people that already have these agents. Probably only maybe 10 to 15 of them have had it for more than a month and a half. And they love it. They absolutely love it. And it's like,

It they have to retrain themselves to rely on the agent and then they get super pissed off if the agent is down for a minute or if you know it's like, my god

Jack BeVier (24:46)
The internet's out.

What are we gonna do?

David Moses (24:49)
The whole world is full like what's going on?

Jack BeVier (24:52)
Everyone go

home. The internet's out. Everyone go home. No no work was done before the internet. Go

David Moses (24:54)
If I if I if I

if I gave you a choice between losing power and losing internet

Jack BeVier (25:02)
Yeah.

David Moses (25:03)
for for a let's say a day, you'd be like ten times out of ten. I don't give a shit about the power. I got

Jack BeVier (25:05)
Yeah, no, no. Yeah, turn the yeah, turn the lights off. As long as my phone connects, I'm good. Yeah.

David Moses (25:11)
batteries. We're good.

Jack BeVier (25:13)
Yeah. That's hilarious.

So are the agents are these agents connecting to each of those each of those softwares, each of those CRM database or are they directly or are they connecting to Mongo, which is pushing and pulling the data to each of these derivative systems of record, I'll say.

David Moses (25:34)
So sometimes and and this is it's kinda tricky because the a this is where long running things with the right skills and the right mem you know, the kind of the right recipes, this is where the agents get really smart and start to use Mongo for 'cause Mongo mirrors everything in all of our systems. But it's it's not it's

Jack BeVier (25:51)
That's what I was gonna ask. Is is it it's a it's

a how much work was it to key? Is it it's a reflection of all of those databases? And are they all keyed together so that the the the unique keys or the common keys between each of those databases are mapped?

David Moses (26:10)
So

Jack BeVier (26:10)
does the you know, does the QuickBooks GL code does does an agent know that the QuickBooks GL code for this asset is that property in Appfolio?

Or is it just be like, look, the address is pretty much the same and it figures it out? It just figures it out. Like you didn't do the you didn't

David Moses (26:24)
It figures it out. we we get it like work order.

Jack BeVier (26:28)
do the work of doing that. The agent's doing a good enough job that you just

David Moses (26:31)
Yeah.

Jack BeVier (26:32)
Okay.

David Moses (26:32)
Yeah, I'm trying to think of it. I I was just trying to think of a situation where we actually do hard coded 'cause the some of the early stuff we kinda had to. But now, you know, we just got smart about how we memorialize things and how we you know, like an example is if it's a work order, we have a a separate maintenance company, right? from our from our management company. And when a work order gets created in property meld,

a subcustomer gets created in QuickBooks and the name of the subcustomer, the subcustomer is a subcustomer of the unit, which is a subcustomer of the building, which is a subcustomer of the owner. And so the sub the name of that, the the s the the the furthest down the the chain subcustomer is the work order number. So it's like

Jack BeVier (27:18)
Yeah.

Yeah. As the agent's doing more of that work, right? Like the the agent doesn't leave off the N dot in a n you know, north. You know, it it just it just takes that and it's the same. And then so just because it it never is creative or lazy or you know takes a shortcut, it just you know types the it just types the the letters the exact same. And so the data actu the data integrity created by the agents is actually much better than the data.

David Moses (27:44)
Yeah, I I I wouldn't say it doesn't

take shortcuts, but the shortcuts it takes aren't truncating the name of something. It the the shortcuts it takes are it just skips a step, or or or more more often it just forgets that this is where you get that information, not over here. And that's what I was talking about with Mongo. Mongo lets them aggregate data across multiple endpoints and actually get more information than the dat than they can actually get out of the database than even a human can get out of the database.

You the actual UI, going into App Folio, there there are things that relate to each other that aren't intuitive in the way Appfolio designs their database and the way they even design the UI, that it's super because in Mongo, all of these things, you know, taken in aggregate can get them the the data that they need.

Jack BeVier (28:34)
So do you have a schema in Mongo per software that it's connecting to?

David Moses (28:39)
It it's a mirror, right? So every single endpoint, every

Jack BeVier (28:41)
Mm-hmm.

David Moses (28:44)
single field, however frequently it gets so some some of them have a last updated field.

Jack BeVier (28:49)
So you just told

you just told the agent to hey, create a mirror in Mongo of this database. And it

David Moses (28:52)
Yeah. Yep.

Jack BeVier (28:53)
just sucked. It's like, okay, give me all the endpoints, create a schema, map start writing.

David Moses (28:58)
Yep. And it's an it it's an automation. It

just goes just literally flips through every single endpoint, looks for field like if it's a if it's a an endpoint that has a last updated date, it just look ha has it last updated, in the last five minutes, and there's it runs every two minutes, so it's like, there is a little bit of o overlap there. And if it's o if it's updated in the last five minutes, or an hour, depending on the database and what the API call limits are and whatever, it pulls

Pulls the data in, puts it into Mongo exactly the way it is in the system is if you were to make that API.

Jack BeVier (29:32)
So the agents are mostly well, I mean you don't know, but the ma the agents are analyzing the Mongo data primarily because it's all in one spot. And and it

David Moses (29:43)
Yeah, it's faster.

Jack BeVier (29:44)
and pattern recognition and is like, you know, really, really great. So it does that really, really well. And then you just decide when you tell it to write to the other ones to keep everything to keep everything updated.

David Moses (29:56)
So the when it r it's gonna read data typically typically it's gonna read data from Mongo. Sometimes it goes to the actual record because if the agent reasons that it needs up to the minute, like if it's gonna record if it knows that the end game is to record a transaction in QuickBooks, it doesn't bother going to Mongo to pull the information about that transaction. Because in QuickBooks it needs a sync token. And so

By grabbing that transaction from QuickBooks, it knows it's the freshest data and it knows the sync token is correct. So it's not it doesn't bother going into Mongo, right? But if it's hey, give me a report, or if it's giving a report, it knows it's read only. I'm gonna go to Mongo. It's faster. and it has it has more information. because it the automations that like we fill in the gaps. When we create the mirror database, we get smart.

We get smarter about filling in the gaps where Appfolio and Sync doesn't give us information that we actually want. the it it may tell us w it was what was last updated, right? But it doesn't tell us what the values were before. So we have now we're creating this logging, you know, that just tells all you know, tells us in every database what's changed. But there are some there were some fields and some I guess some information that was so key.

to what we were doing that we we needed to s we needed to start accumulating right within that record or that that yeah w right within that record itself, we needed to add more information that wasn't there before. Right. So add information that Appfolio wasn't giving us. And we essentially

Jack BeVier (31:35)
So you're never

you're never writing to Mongo. Mongo is always just pulling in and a r and a mirror. It's just always a mirror, but whenever you write, you write to the

David Moses (31:46)
Correct. It it yes. We th there's no it's not two way. Yeah, it's because

Jack BeVier (31:48)
To the database. Right.

David Moses (31:50)
the the connection w Mongo to the to the database is not two way. that's not to say we don't still write to Mongo directly for other things. we'll we'll have things that just don't live anywhere else that are in Mongo. like we write

Jack BeVier (32:01)
Are things like

are are things like property mailed and app folio connected so that when a maintenance ticket gets created or dispatched and resolved in in property mailed that app folio is automatically updated or that's already connected. Okay.

David Moses (32:13)
That's already connected between property meld and but we kind

ignore that connection. we don't really it's not helpful for us because we we don't the reason we don't like if if we

Jack BeVier (32:22)
Reason you don't think.

David Moses (32:23)
were satisfied with what was what Appfolio's capabilities were, and I d I say were because I I don't know what it is today. but if we had been happy with how it deals with work orders, we would have just used it.

We wouldn't have bothered using a third party. So there's no point to extract data from Appfolio about the work orders. But there is a connection there is a connection that's automatically made there.

Jack BeVier (32:50)
Okay, so then I gotta ask when because I I gotta think that the agents hallucinate sometimes. When they hallucinate, what do you do about it? Do you bump pump up the mo pump up the model strength and hope that they into until they don't hallucinate and just throw money, which is basically just like throw money at it until they don't

David Moses (33:07)
Yeah.

Jack BeVier (33:07)
hallucinate? Or are you like

Giving them additional context? If so, where is that context stored and how is it shared with every other agent so that the next agent doesn't do the same hallucination a month later? How do you manage hallucinations?

David Moses (33:22)
I don't. and I'll I'll I'll kind of explain why. I if it's important enough that like like the only things I use kind of cheap models on are things that are within a workflow that's running where the hallucination is not going to be where it's gonna be a subjective hallucination. Like

It may look at a picture, right? May process a picture and it may say, This is out of square, or this is, you know, there's there's I see rust accumulation here. You know, those are things that like that's so there are so many ways that it can like it's not likely

Jack BeVier (34:05)
Yeah, sure.

David Moses (34:06)
to say there's rust there unless somebody looks at the picture and says Right.

Jack BeVier (34:08)
Yeah, you could just ignore it. It gives you

some you know, it shortens your analysis cycle time, makes it lighter a lighter lift.

David Moses (34:11)
Yeah. That's right. Like it i it raises

the red flag, we look at it, yeah, yeah, I agree, no, I don't agree, that kinda th

Jack BeVier (34:16)
Yeah, yeah. If

it's really annoying you might go back and change the prompting, but usually it's fine.

David Moses (34:20)
That's it. Exactly right.

Yeah. I I we don't we don't account for him because everybody's agent is on GPT six Astra or GPT six soul. And they just don't hallucinate. They they f they they make a lot of mistakes, but they're not hallucinations. They're I don't have permission to do this. Yes, you have permission to do this. I you know, it it will not follow the steps. It will not complete the assignment. It'll just like say, Okay, I did the first part of it. What do I do now? And you're like

I why did you just do the first part of it? Dude finish it. and I I you know, I I I suspect

Jack BeVier (34:52)
Is that because the skills files? Is is that is that resolved through s through more robust skills file files?

David Moses (34:58)
I I suspect it's there's two things going on. Number one, the models only have so they they just there's only so much bandwidth out there. There's there's only so there's only so much and and I think in high volume times, they just open AI just throttles the long running tasks and you're gonna get this kind of like

It just goes to you. And then you just prompt it and it just keeps going. It picks up where it left off. and then the other thing is that we have inconsistent rules. So it's like when we're building a workflow, and this is really a challenge for us. When we're building a workflow and you're not using Fable, 'cause I say that because Fable's so good that it mo it one shots most you know, most things that you understand what you want really well, it will one shot.

Jack BeVier (35:43)
Yeah, I

agree.

David Moses (35:45)
but but when but when you're working in like you're building a workflow or tweaking a workflow using GPT, it will it'll build something and it'll keep going on tangents that it'll keep going down a road that's the wrong road. And you don't find that out in a super long running task until it's done. So we have checkpoints, we have milestones that the

when Carl, who's actually my brother, or when Jay, or when somebody else in my office is working on a workflow, it'll stop at milestones deliberately to say to check in with the human and say, Am I, am I doing this right? And then we'll, okay. Yeah, you're doing it right. So, but that spills over that programming spills over into how that main agent builds the

other agents that it builds for the for the individuals. And so some of these skills they wind up stopping at these milestones that really didn't need to stop. the skill is clear, it's very easy. It's not gonna mess it up. Just just just go.

Jack BeVier (36:51)
Hmm. What is the

David Moses (36:52)
And yeah.

Jack BeVier (36:54)
what is the con I'm gonna use the the Claude example. if you have a session in Claude and you've been working in that session for a long time, that entire session is context and is processed for each subsequent request that you have. And so it gets one expensive two worse at its job as you

reach a certain inflection point in the size of that session, the size of that context window. How does Hermes treat that? are these are all of these agents, everything that they've ever done, a context window? Or does it analyze context discreetly and then just r call the relevant skills? How how does it I would think that, you know, an employee, a human doesn't get worse at their job over time. They get better at their

job over time.

David Moses (37:41)
An an agent is not true. An agent that's not true.

Jack BeVier (37:41)
But frankly, what's that? Yeah, an agent

that's not true. They get worse at their job over time. The more and more instructions you give them, the more and more background they give them, it get it's laborious for them to process so much, right? So like and they actually get worse at it. How do you r resolve that or deal with that?

David Moses (38:01)
So we obviously we're really heavily reliant on Hermes memory structure, which is good and gets better. how it s

Jack BeVier (38:08)
because Hermes

its Hermes as a harness is building skills and context based off of those in an i in what we think is a an efficient way such that you as the user don't even have to worry about it. It's just happening.

David Moses (38:22)
Yep. That's exactly right. And then there's the other part of it, which is what the user can do. And so we have two things. We use Telegram and we use Discord. And we've talked about this a little bit before, but Telegram is like, hey, go add this to my calendar. Hey, what's my day look like tomorrow? Hey, can you go summarize this the last two phone calls I had with this guy? I've got to call him. those are the types of things that we would do in Telegram. They're like one off things.

But if you're if you've got a a job that you do re repeatedly, right? Like I'm reviewing statements, I'm analyzing complaints, I'm geez, w whatever whatever it happens. I'm I'm recording closings, right? Whatever it is that the agent is doing in Discord, you have a thread for it, right? You'll have a channel for the agent.

Or a chan you might have a channel that's just devoted to one overall overriding topic, and then you'll have channels under and you'll have sorry, you'll have threads underneath it. And so that helps because the because Hermes understands and has and we've actually built this into its structure, is that the primary context for whatever it is you're working on is gonna be in the same thread. Right? How you've done it before.

It's going to be in the same thread. So if you're unsure, you're going to go back and review that thread. And sometimes you have to tell it, go back and review this thread. We've already discussed this. And it and it will do that. But it's a very small amount of data to review for the agent. because it's all just this one topic. Kind of similar to how you create conversations in Cloud, where you've got like, but it's they're more, it's it's more per it has some more permanence to it.

Right. Like a conversation

Jack BeVier (40:08)
Mm-hmm.

David Moses (40:09)
is just, hey, something I'm working on right now. whereas this these would be like a permanent conversation where it's not just the conversation I'm gonna have about this one thing, but all of the conversations about all of the things related to that one thing. and I kinda I kinda wish Claude would do the same thing. It's kinda it's kinda silly that they don't, but they have projects and then they have conversations, but you know, it's projects are a little more robust.

Jack BeVier (40:30)
Right. Yeah, it's it's

yeah, the the that that harness is not intended to be an assistant. You know, it's very gatekeeped. It's meant to write code on big projects and one shot like, you know, software.

hey

David Moses (40:45)
Yeah. I I the legal

profession, by the way, is like like if I were if I were going to be in any position right now, any profession right now, where I would believe that I'm in trouble, I would probably say the legal profession has got to be right up there. because of the dollars involved. I mean, you have so

how many times do you call and have a conversation with the attorney about a contract that you want to tweak or a whatever it is, right? A a a demand you got or a lawsuit or you whatever doesn't matter what it is, Claude will give you such a better answer.

And s and and this is no offense, but your attorney's not gonna put eleven hours into figuring out, you know,

Jack BeVier (41:38)
Yeah. Well you don't want to. Yeah.

David Moses (41:40)
you don't want to it's too expensive. But if you go into Claude and you just say, Hey, I wanna tweak this contract, it's like, well, you're missing this clause that because of this law or da da da. and I wanna add this. And you're like, Well, can you just like from a practical sense, I really wanna understand why this clause is why why I need this clause written this way. Can you just go look at the case law on it? And it'll pull up and like

All of a sudden you'll be an expert in you know releases, like like security posit releases, whatever the hell it is. Right? You'll be an expert in that one

Jack BeVier (42:08)
Yeah.

David Moses (42:09)
thing because you'll know the case law and you'll write it in such a way where it has to be written exactly and it'll just do that. You know, instead of like what

Jack BeVier (42:16)
Yeah.

David Moses (42:17)
this attorney thought would would would fly, you know, now it's like, okay, the the Michigan Supreme Court, the, you know, w whatever it is.

whatever county court, they came to a specific conclusion and here was the actual wording. And so you'll just word it that way right in your clause. Because you know if

Jack BeVier (42:38)
Yeah.

David Moses (42:39)
it ever comes up and you say, Well, look, the clause says this, and this case is literally directly on point, it says exactly the same thing using exactly the same words that the appellate court used. And attorneys are like, fuck off. All right, fine.

Jack BeVier (42:52)
The the thing that I've s already seen over reliance on the legal side is like reviewing the thing is that the it does a phenomenal job of reviewing the legal document in the four corners of that document. But because it has no real world context until you've given it, like you tend not pe people tend not to go to their favorite L L

And start telling it the story of this business relationship and all the things that we've done together and all the emails that have ever transpired between the two parties. And so it freaking it misses that, like, hey, you've got exposure here because you did this and this says that, and like this could be interpreted as a violation of the four corners of the document because it has no idea. Whereas when you're talking to your attorney, a good one at least spends some reasonable amount of time.

Being like, so tell me about your relationship with this person. You got, tell, give me the story as to everything that's happened. And they can figure out the moments to dive deeper into something that may res, you know, where where your answer may be like, there's that's what's gonna screw you here, right? They can like a good attorney can find,

David Moses (44:00)
They can sniff that out.

Jack BeVier (44:01)
can sniff that out. And Claude's just sitting there. I mean, maybe they'll build it to the place where they're just like.

They they have it interviews in the you interviews you in the same in the same way, and it's still a much cheaper, better version of that. But there's a human intuition aspect of a good attorney that smells where you're gonna get screwed because of their pattern recognition over time, as as we call that experience, right? that

David Moses (44:24)
Yeah.

Jack BeVier (44:25)
I've already seen people I've already seen I've seen I've like real life examples of people like screwing up through over reliance on

on LLMs for, you know, document review because the you know, the the the LLM gave it fantastic advice, just didn't have any idea as to what that human had done to get themselves in this particular position. And that was the only thing that mattered, you know, like that was the fatal flaw that Claude had no idea was happening. Or ChatGPT had no idea was happening. Anyway, yeah, it's gonna be super interesting, man.

David Moses (44:58)
Y yeah, the other the other side

of that is that it will

it will oversanitize the strength of your position as well. It will say, well, yeah, but but but this isn't, you're not in as strong of a position as you think you are because this and this and it's just can be flat out wrong 'cause you actually go through and you dig it dig a bit deeper and you don't know if it's just kind of trying to agree with you or if it's actually uncovering, you know, what it

I I I I have a really good example, but I I I don't I'm not gonna go go into it right now, but I really do think that it's about using it. That's why I'd be fearful if you're an attorney right now who's not using Claude, quit. Sell your practice. There's no point.

Jack BeVier (45:40)
Yeah, yeah. Yeah.

David Moses (45:43)
Right. But an attorney who understands kind of like you're gonna go through that conversation with Claude the way you would go through the conversation with your attorney. But Claude can see if you give it the tools to see it, it can see into

my claude can see Appfolio. It can see, you and ubiquitous. It can see everything. Everything in Apfolio, everything in property mailed, everything in every, it can see it can see my emails. It can see my documents. Right. Obviously that's a gargantuan amount of context. but it can start to ask those questions, right? And you you don't see it yet. Like it's not there yet, but it will get there.

It it's less than a year out, I would say. Whatever whatever

Jack BeVier (46:28)
I love the I

David Moses (46:29)
Fable six is, probably

Jack BeVier (46:31)
Well they'll never get yeah. As I as I've said as as I said in a previous episode, we'll we'll never get our hands on Fable Six. But we'll see. We'll see who that

David Moses (46:38)
'Cause you don't

think the you don't think they'll ever release it. They they're just gonna they're just gonna i if it can

Jack BeVier (46:41)
Yes, good boost.

David Moses (46:42)
cure cancer, why would you bother giving everyone the ability to cure cancer? Why not just cure cancer? Make make all the money yourself.

Jack BeVier (46:47)
Yeah. Yeah. And then

and then Fable five will be distilled and then I'll never pay for anything ever again in a business context. But anyway, the or back to

David Moses (46:56)
It's very

it's very possible you're correct. I mean I'm I'm definitely not gonna take the under on that.

Jack BeVier (47:00)
The

I I do love the idea of the general counsel agent who has access to all the transactions, everything that's happening, all the emails that are being written, all the transcripts. That is just constantly monitoring your entire organization and just surfacing hey, a little bit of exposure here, a little bit of exposure here. And you could then obvious things getting too uptight, dial it down a little bit, buddy, and tweak your general counsel to the place, to to the place where you want it to be where.

It is all seeing and all knowing and reporting to the owner areas of points of exposure such that you can manage out that risk or affirmatively mitigate that risk and not find out about it after the lawsuit hits you and discovery happens and you're like, you said what in an email six months ago? you're kidding me, right? so I do like that use case also. And the fact that that that agent would also have access to all the contracts. So it would have the context of like all of the all of the corporate.

you know, reps and warranties and affirm you know, affirmations that you've made as an entity and make sure that as you operate you're not violating those things or when you do violate

David Moses (48:04)
Yeah.

Jack BeVier (48:04)
those things, at least you get a heads up that you did. I really like that idea.

David Moses (48:08)
Yeah, 'cause you're gonna look, every you you create as a business owner, you create exposure every single day. Right? Every single day you create exposure.

Jack BeVier (48:14)
Right. Yeah, of course. Yeah. You ca you cannot do business

without getting sued at some point. You can't. Like I mean not a bit no, not at

David Moses (48:19)
No. But but and it's just kinda like it

Jack BeVier (48:22)
scale.

David Moses (48:23)
it it's like the criminal that gets caught, right? that's not the first time they did that. That's not the second time. That's probably not the fifth time they did that, right?

Jack BeVier (48:27)
Yeah. Yeah.

David Moses (48:31)
But they got caught eventually, right? Because they got complacent, because it wasn't big and scary when they did think of it that way in that fr from not from a nefarious standpoint, but when you make a mistake, when your people make a mistake in business, they're gonna get away with it many, many more times.

Then they get caught by it. But then when they get caught, that's where class action lawsuits come from. Right? They come from I made the mistake lots and lots of times, but you add in that nefarious component to it, right? Then it becomes a class action lawsuit. But you take out the you you take out the intent, right? You take out the I've you know, malintent, and they're just honest mistakes that you're making that exposing that that are exposing your company. That's that 360-degree view that.

that I've talked about before. It's just understanding where your exposure is and and then and then training around it, right? 'Cause these conversations, this is why your agent should be writing every email. This is why your agent should be sending the text for you. Why? Maybe it's not going to be perfect in protecting you and disclosing everything and do maybe it's not going to be like that now, but it's going to be a hell of a lot better than

It's like having your attorney on your shoulder before you write that email to say, Hey, maybe we shouldn't say this or maybe we should say this, right?

Jack BeVier (49:49)
hear you. I'm gonna take the other side of that coin in terms of the communication. I think that the I think that I don't think people talking to a computer like in any context. I think everyone it's always pissed something up. It's always pissed us off as humans at some at some level. Now is there a trigger in my Outbooks send protocol that before the email leaves the Outbook out outbox, it gets reviewed by an agent that is a that that is, you know, the attorney sitting on your shoulder.

And a little pop up happens and is like, you might not want to say it this way. Think about tweaking it to more something like this. And then the human has to override before the send happens. I yeah, I I'd be I'd be excited about that feature.

David Moses (50:31)
That's actually that's that'd be fairly easy to do. Right? Like that little the little paper clip from Microsoft Word, like way back in the day.

Jack BeVier (50:34)
Yeah, it would be fairly easy to do, I think. Yeah. Yeah. Yeah, yeah. The little stupid paperclip. Yeah.

David Moses (50:40)
My my favorite one was like somebody's like, Yeah, you know, that paper clip popped up. I see you're writing a ransom note. Would you like some help with this?

Jack BeVier (50:51)
That's hilarious. Well, Dave, hey, I

apologize. I got a I got a slammed one today. I gotta cut us off short. we got some good content in here, man. This was I think this is one of the more content-packed. I mean, you know, you've gotten to a very exciting point that I think a lot of business owners are really interested in in getting to. And you know, you've had it was not a straight line by any stretch of the imagination. So to like to have you distill where

David Moses (51:13)
Depending on how drunk you are. Yeah.

Jack BeVier (51:15)
you landed.

and how you're dealing with a bunch of issues that you have obviously put a tremendous amount of thought into, I just think is incredibly valuable. So man, I r really appreciate this conversation. I'm excited to hear how it goes. And thanks, man. Much appreciated.

David Moses (51:28)
We'll see you in a week.

Jack BeVier (51:31)
Yeah, sounds good, man. So hope everyone enjoyed that episode of Fork.ai. yeah, Dave, I'll see you next week at Shar in Charlotte at Real Investor Roundtable. if anyone's interested in we'll be talking about this and many other real estate investing topics at that at that mastermind. So if anyone's interested, thinks they would get value out of that and could add value to the room, don't hesitate to reach out to us. I'm Jack at thedominion group.com.

and otherwise I hope everyone has a great week. Have a good one.

David Moses (52:01)
Take care.