YouTube Deep Summary

[Music] for a show of hands. How many people in this audience know who Circle is. What we do. Um, just just trying to gauge. Okay. Okay. Um, do you know anything about our developer tooling. Gotcha. Gotcha. So, nobody. Okay. So, this is good. All right. Um, first, you know, I just want to introduce myself. Uh, my name is Corey Cooper. I lead Devril at Circle. Uh, this talk is about the intersection of some exploratory work we've been doing internally between AI and programmable money. And um you know one of the things we noticed a trend in with USDC uh when Circle launched its digital dollar technology is that um it was an order of a magnitude better at doing ex escrow than traditional payment rails. And so, uh, combining USDC with AI gives you a way to do some type of verification of, uh, workflows that are, uh, happening that need to be met in order for escrow agreement to be, uh, honored. And then you get instant settlement with, uh, a stable coin that can settle um, faster than T plus2 around the world. So, in this presentation, what we'll do is I'll give you a background on Circle. I'll give you an overview of our developer tooling. Then we'll jump into our smart contract um that powers USDC, the technology that makes it a programmable dollar and uh and gives it features and attributes that you can't do with uh a digital representation of a dollar in traditional u payment rails. And then we'll end off with giving a live demo of our escrow agent application that we open sourced recently. and um allow you all to set up this in your environment if you want to locally. I can walk you through doing that today or we can just do a Q&A. You can ask some questions about um you know anything about you know our dev tooling and and where we see this marriage between agents and USDC going. So, just to give you a quick um background about Circle, um it's a fintech company um that issues stable coins. Um we were established in 2013. Um and some of our our backers are the pillars in the financial services industry like Black Rockck and Fidelity. The reason for that is because we've we've done uh a really good job of providing trust and transparency that the digital tokenized version of the US dollar or the euro that we deploy on different blockchain networks is backed one to one with fiat uh and short-term treasuries in a bank account. So it's fully reserved 100%. We also have led the charge in regulation around this industry and really helped um regulators around the world think about this as a ground breaking technology for payments and um as you see there's some things that are happening in the US and across the world where um laws are being passed to regulate stable coins which we're happy about because it's going to give businesses and individuals opportunity to take advantage of this technology. And so, um, another note is, um, you know, since inception, we've been able to, uh, be responsible for settling over 26 trillion of of transactions on, um, roughly we're on roughly 20 different blockchains and going right now. But um that that's a huge accomplishment for uh the amount of engineering resources, the product resources, marketing resources that the company has poured into to you know allowing businesses and individuals to be able to take advantage of this technology and build on top of it as a payment rail. So, here is a um a chart or not really a chart, it's an overview slide, a visual of the lay of the land of what we offer as a company. Like I mentioned earlier, um you know, we issue USDC and EURC. Um, we recently acquired a company called Hashnote where we now have a tokenized version of a money market fund. Um, which is going to give us the ability to do um, something with money markets that were never possible before. Uh, to be able to liquidate out of a money market into USDC 24/7, 365 days a week. Um and then we have our liquidity services for uh payment service providers, financial institutions uh where we enable them to be able to mint and redeem USDC um to a very secure enterprisegrade vault wallet on chain for uh performing different types of use cases that relate to payments um dollar access as well as uh capital markets. And on the far right we have our developer services. And this portion of um of what we offer is what will be wrapped into what we will demonstrate today with the sample app that I'll demo uh where comprises of wallets. So well a developer can embed wallets in their application programmatically. We also have uh circle contracts. So that's a smart contract platform that enables you to deploy uh contracts programmatically and read to those contracts as well as write. And then uh under that we have our circle pay master and CCTP. And if anybody knows anything about transacting on public blockchain networks, there is something called gas fees. And so what we've done is we've enabled um end users to be able to pay for gas fees within u USDC. So from the USDC balance. So it actually feels like a traditional payment transaction as opposed to having some native token that you always have to have in your wallet to be able to transact. And then since we're on all these blockchain networks, there is a lot of fragmentation that we were trying to unify. And the way we unify that is with our crosschain transfer protocol that allows for you to move USDC between different blockchain networks permissionlessly. And you as a developer can build very seamless multi-chain experiences around this this protocol um so that you don't have fragmentation where someone is on one chain and they can't transact on another chain. So you can do crosschain transactions uh and things like that. And at the bottom layer are uh all the blockchains that we natively have USDC issued on. Uh this this list is getting longer. Um so but you know we are we are in a multi-chain world where we want USDC to be the uh premier digital dollar and so we are building all types of onchain uh utility around USDC as well as ERC to make uh this um you know support for multiple blockchains more unified. So there will be some other innovations that we're going to release in the next couple of weeks and months um that advance the unification of balances across multiple blockchain networks with our um stable coin technology. So let's let's dive into USDC um and and just really talk about the attributes that are really important to a developer. And so um one of the things is you know it is a dollar that is internet native. And so what that means is the ledger of that dollar is built into internet technology which is blockchain networks and smart contracts. And so it enhances the programmability, the transferability um to enable money to move in seconds globally. And so it's not constricted to some of the uh friction points we have in legacy payment rails. The other thing is because it's uh native to the internet, it's it's it has no borders. Um so it works like email or or text where you know you can send text or email around the world. We want to make money to be that seamless to be able to transact with. And so um because of it being issued on public blockchain networks, it gives it the borderless uh freedom to be able to transact globally. And then last, when you have a network that is permissionless and public and open, uh it makes it very easy for other companies, individuals to plug into this actual network of money um and transact with it. And so um it it's scaling very fast globally because of the openness of anybody being able to build on top of this protocol for sending and receiving and storing uh value. And so how does this work. you know, uh, how it works is how USDC gets issued in the ecosystem is a business gets approved by Circle to set up a business account and then they connect their bank account to our Circle Mint platform and they wire their fiat to our reserve bank account. After that that fiat settles as USD in our bank account, then we mint the corresponding amount of USDC and credit their circle mint account. And so that is how USDC gets issued in the ecosystem. Now the reverse process happens when the business wants to get out of USDC. they can redeem uh and there's a onetoone with um every USDC minted to a US dollar. So um when they want to get out um they get that onetoone parody and so that is the trust and transparency that we provide to our customers. Uh we also um do a little bit of extra things and you can go on our website where we have a USDC transparency page where you can go and see our monthly addestations. Um and we have various auditors um that are independent of the company that continue to audit and make sure that we are fully reserved and we you know make sure we ensure the trust and transparency around the actual issuance of a digital repres representation of the dollar on uh chain. So now we're going to jump into the USDC smart contract and really dive into like what makes this programmable, how does it work. So one thing is uh we have um you know very strict implementation requirements before we uh deploy USDC on a different blockchain network. And so, um, here are the things that we want to make sure that we can incorporate in the token contract before deploying it on a blockchain network just to make sure we have standardization across the board. um you know as we um expand to different blockchain ecosystems, but also too to make sure that there are safeties uh provisions that we have built into this actual smart contract for businesses and individuals to be able to trust and use our technology as a protocol for money movement globally. And so um here are some of the things I I'll jump into and and and provide a little bit more clarity around the implementation requirements. But um the first is um allow list and block list. And so this enables us to basically prot protect you know um people who use our token contract from bad actors. And so if we know someone's on a sanction list um you know and and they're a malicious actor, we have the ability to actually um stop them from transacting and protect other users from transacting with that actual user. And so um it's built in for for safety for businesses. And then we have um spend on behalf. And so that's a feature where you know say if you're a business and you wanted to create a financial workflow where you wanted to enable um you know somebody to spend uh a certain amount of money from a wallet balance uh and and give them a cap on that on a daily basis. Um there is functionality built into it where you can delegate for uh a user to be able to spend a certain amount of money from a actual wallet balance using USDC. Yeah. Like is a scenario with that like a corporate um you know corporate account or something like corporate business card. So say if you have u some some virtual debit cards that you're issuing to your actual uh employees and the actual debit card is powered by a USDC balance in a wallet. You could design basically a workflow where you could put thresholds on how much they could spend from that corporate card. Would you realistically be able to run that to like thousands, tens of thousands, hundreds of thousands, or would that not be a proper use case. No, no, you could scale it up. Yeah. Oops, sorry. You you could you could definitely scale that that delegation of spending um for that fat wallet address with a virtual debit card uh to tens of thousands. Yeah. Yeah. Another is is mentor configuration. And so um you know we we have the ability to uh add um you know other uh entities to be able to uh mint from our token contract. This is something that we haven't done, but there could be a future where we could partner with financial institutions and they have a balance that they can mint from from the actual token contract. And then uh multi-IG transactions. Um this is this is for you know like if you're building some type of workflow where maybe you require the CEO, CFO and CFO to actually sign off on transactions that are above a certain threshold. you can design these type of um transactional experiences to protect from um you know a wallet being drained um based off of like one person having total control of you know the the transaction ability of that wallet coal storage support um a use case for this is where maybe you know that um you're running payroll uh on a monthly basis using USDC for your employees. You know the date and time that you're going to be sending money out. You know the amount. Um you have the ability to to put those transactions in a ready state that are offline. And so when that date and time comes, it's ready. The transaction object has already been approved and signed and then you can just broadcast that to the actual uh blockchain network to send that off. So it allows you to kind of prepare transactions offline. Is that proof of funds. um uh transactions so that it's ensure that the money is there when the time comes. It it could be designed for that. Uh but it's more it's more of you have a cadence of transactions that you know are going to happen on you know a bi-weekly or monthly basis and you want to make sure that that transaction is already ready to go uh and in a state where it's already been signed and approved for and then it can just be broadcasted at a late later date. So it doesn't necessarily prevent it from bouncing. Uh no no. Yeah. And then since this is a new concept of money um and we're constantly, you know, thinking about ways of how we can enhance the actual protocol of money movement, there are times where we need to pause the contract for upgrading it. And so this hasn't been done much, but the most recent one was uh um about two years ago, a year and a half to two years ago. And um you know it's USDC version 2.2. And the main thing that we did was we um made it more gas efficient. And so um knowing that we want to make this technology scalable, we want to make sure that gas fees never become an issue. And so we were able to design different uh functionality in the token contract to optimize for uh better gas performance across chains. And so now I'll jump into the um contract functions of USDC. And so these are uh basically the functions the core functions that a developer would plug into when um commonly transacting with USDC. And you have uh balance of total supply, allowance, transfer, transfer from, and approve. And so these are these are um you know functions that are built into the actual smart contract that powers USDC uh that you'll see actually later on when I do the demo that we'll be using to actually uh perform the actual escrow transaction. And so um one of the the the most commonly used uh functions from this actual contract list is uh transfer from. And so uh in that argument you see you put the uh from address and the to address and then amount and you pass that um and then that gets broadcasted to the actual block um blockchain network to be able to actually send that transaction and you're you're telling it to send basically money from this account to that account. and then the amount of USDC that you want to send. And so that that's the programmability that you get with USDC that that is not built into the digital representation of um fiat uh in a database. Um and so that's where the magic allows you as developers in the room to create these very innovative experiences that were not available to us. And so, um, you know, USDC is, you know, it's kind of funny, but, uh, it's designed for agents. Uh, basically how we've seen agents kind of proliferate over the last year or so, uh, it seems like it's just the perfect currency for an agent to use to transact. And so, um, some of the reasons why is, you know, one, you get near instant, uh, settlement, uh, and built-in verification of transactions. And so when an agent is transacting, it's not a human. Uh and so one thing um you know you want to do is you want to allow the agent to be able to to transact and those agents if they're doing agentto agent payments, they want near instant settlement because u these are robots transacting. Uh, another thing is you don't want robots to have to deal with chargebacks. And so that could be a nightmare because when agents start transacting with each other, money is going to flow very fast. And so a chargeback could be a catastrophic uh risk to running agent-to-ag payments, you know, on reversible rails. The other thing is um you know agents are are always on you know and so they need a payment rail that's always on uh 24/7 no banking hours. And so um you know the the great thing about you know this public blockchain infrastructure is you have this compute that's always on that enables settlement to happen 247 globally with no banking hours. And all of these transactions are verifiable um through private and public key um technology. And so the cryptography um and and the actual openness of these actual ecosystems make it a perfect um payment rail for for agents to transact because um there's there's no downtime. Oops. Let's go back. And then the last thing is I'll go back to the slide where I was showing the actual contract functions. It's the programmability. Um, you know, agents are going to need to be able to have a lot of programmability because there are going to be transactions where they'll need to be able to um, you know, perform some sort sort of logic uh, that they need to pass before they can actually make that transaction. And so that logic can actually be built into composable smart contracts uh that we'll show in this uh demo of of how like this is great for escrow because um you know you have the ability to perform value transfer with all this conditional conditional logic that you can actually program in and the agent can actually interact with that logic to be able to perform those transactions. So, uh, very powerful technology here. And so, um, now I'll jump into the sample app. And so, first I'll run through kind of the architecture, what we used, and how it works. And then we'll jump into a demo of it, and then um, everybody can have time to actually set it up in their own environment, and I can walk around and help you out if you have any issues. So the core building blocks from a dev tooling st stand standpoint of what we used to to build this actual escrow flow is uh we use circle wallets and so that enabled us to actually provision wallets for the agent the u and the two parties involved in the actual escrow process. Um and then also too we use circle contracts. So we were able to um actually we wrote a solidity contract um and then we uh deployed that using the circle contracts API. So um it was a repeatable um process of us deploying contracts for each actual um group of parties that are transacting. And so uh that API allowed for us to take you know this this template of a escrow contract in solidity and repeatedly deploy it and use it for different parties involved transacting amongst each other. And then lastly, USDC um being able to embed the uh USDC stable coin in the actual smart contract gave us the ability to um design basically um a smart contract that is running off of dollars um and interoperable with the actual fiat world as well because uh kind of the likely process of of some of this will be uh there's a onramping experience from fiat to USDC and then there's a off-ramping experience where the beneficiary wants to go back to actual fiat and using the actual smart contract in USDC gives both parties the trust that they have a tokenized version of the dollar that they know they can get in and out of anytime one to one. So here's kind of how the onboarding flow works. As you can see from this uh this design, you have a client which is the business and the freelancer and they both come to a platform and create an account. And so as they create an account in the background um there's an API call to the circle APIs that provisions a wallet for each of those actual parties. And then the next thing is the actual uh business will take basically a PDF version of an agreement that they have with that actual freelancer um that they probably negotiated outside of the the platform uh for this use case. uh and then they would upload that agreement and what would happen is once they upload that agreement to the platform it would pass it to the open a uh open AI's u API and run it through uh a multimodal model to actually parse out information about the actual agreement and so that information will be related to you know the the amount um uh that these two parties have agreed upon as far as the work is concerned and then the uh the summary of task has that need to be delivered in order for the actual um escrow to be um completed and payout to happen. And so after that happens, basically there's a listing on the platform uh that the uh AI agent generates and and lists and there's a human in the loop in this process where you know the actual business approves that hey this is the amount I'd agreed upon. This is the list of um you know things that need to be done in order to honor the agreement and receive payout and uh and this is a good summary of what the agreement is about. So I want to publish that listing to the platform and then after that happens then the actual business would need to um create a smart contract. And so since we've already got a template running in the background they're not designing that smart contract themselves. What it is doing is it's taking the information u that the agent has parsed out from the actual contractual agreement and initializing certain constructor variables uh for the actual smart contract to be in a ready state to be deployed on chain to govern the rules of the actual agreement. And so those things are is just simple things right now. It's just use USDC as the stable coin of choice for the currency that flows through. Um also too, um the agent will will be um given a a wallet uh that can only be used to actually release funds from the contract. And then who is the um you know depositor wallet and who is the beneficiary wallet. And so those rules will be will be um enforced within the smart contract um before it's deployed on chain. And so after um so so to deploy it on chain, we're using the circle APIs for this. And so um after that that is deployed on chain, there's a notification that comes on the screen telling the actual business that the contract has been deployed successfully. Um, and in the background, a developer can use uh the developer console that we have at Circle to track all this activity uh and to design web hook notifications uh as well around this activity. And so that's one of the powers of um our dev console. allow for you to do a lot with onchain data uh because we're indexing all this information and putting it in a nice format to allow you to design different programmable flows around that information that's happening on chain. And so once the actual contract has been deployed on chain, the next thing is you're going to have to the business will have to actually on-ramp into USDC or if they have pure USDC, then they can uh fund that that um actual contract from um some USDC they already have an external wallet. And so, um, you will deposit, you'll call the actual deposit, uh, function on the smart contract. And what that would do is that would basically um initiate an approval for a certain amount of USDC to be sweeped from your actual wallet address and transferred into the smart contract so that the smart contract can go into a ready state of letting the beneficiary know funds have been deposited in the smart contract. Now it's ready for you to do the work you need to do to honor the contract. And so that's that's one, you know, magical moment where you have now in this escrow experience a smart contract that's actually holding the money in code and there is some sort of transparency that you know the money actually is there because you're dealing with these public networks that have the ability to verify, you know, that information by just looking it up on the block explorer to be able to see that, okay, funds are actually in this smart contract. So I know this person's serious about paying me. So um after that then the actual um freelancer will and for for this actual experience we we use an image. Um they the the task at hand was to design basically um uh some marketing material in the format of an image um that had certain things within that image um that promoted the brand of the actual business. And so Freelancer uploads that image to the platform. It passes it off to uh OpenAI and the agent goes to work and it it looks and verifies. Okay, does this image have all the things in it that you know were required of it in the actual task agreement. If it does, then it'll go through a simple scoring system. uh and and if that system scores it as you know it's confidence level high that means okay yes release funds from the actual smart contract and then the agent uh can use its wallet to actually call a release uh funds function within the smart contract that will ultimately release funds to the beneficiaries wallet. And so this is where like the automation, the verification happens. Uh where in most escrow situations, there's a lot of convoluted back-end office work where manual review is being done and agents now are getting to the point where they're they're very good at uh reading, seeing, hearing, doing a lot of things. And so what what we think is u there could be a future where agents could be a major checkpoint in a lot of escrow transactions and coupled with USDC becoming a great way to settle es escrow transactions instantly when you combine all this together you can build some very um cool stuff together. Yeah. So I did a lot of talking. Let me uh show the demo because I I know people want to see that. Um so let me get out of here and open up my um app. Okay. All right. Let's see. All right. Can everyone see this. Okay. Okay. All right. Thanks. Okay. So, here's the escro agent app. I'm already logged in. Um, and I have some transactions that I've already set up because I wanted to show you what things look like in each state. And then I I'll kind of walk through certain transactions and and get to the actual cool part of actually um letting the agent actually release funds. But um here's a here's a transaction I've staged and right now it's in the initiated status. And so this status is someone has already uploaded a contract uh in PDF form to the platform. It's parsed out the information with the agent u using um the 40 mini model and then uh that human in the loop process of approving that hey this this is what you know the agreement should look like uh listed on the platform so that the beneficiary can receive that listing. And so this is the state of what it looks like after you get past that. So, it's showing you um the summary of the agreement. Uh obviously has the amount here of $10. And then here are some of the deliverables. Uh high quality image, you know, featuring Sparkle Fizzle. Uh so that's the brand fictitious company we created. And um and so this is what it'll look like before a smart contract is deployed to govern the rules of a actual agreement. Now in this state say I clicked deploy smart contract on chain. It has now built out the logic and the rules that will govern this um this agreement. Um the next thing is you know depositing funds in the smart contract. So the actual beneficiary knows that uh you know this person's serious. The money is there. It's time for me to go to work and and do the things so I can receive the money. Um this is what state will look like. Uh, and then if you hit this button, you can deposit funds and it will withdraw the $10 amount from your account balance and it'll deposit it in the actual smart contract and provide a notification of when that money has settled in the actual smart contract. And then once it's, you know, in the smart contract, the state will move to locked. And so that means the smart contract will lock itself. And and now the the next thing that can happen in that smart contract is basically the agent actually reviewing the work and interacting with it to either release the funds or um you know revert the actual funds back to the actual um depositor. uh if you know a period of time elapses where you know that person was never able to kind of meet the agreement. So um what I'll do now is let me um run through a test transaction. Okay. So let's see design. So, here's a PDF document. Going to upload it. Let's see. All right. So, in the background, the agent was running parsing out the information in the PDF document. Again, um it's it's parsed out the amount and the task. And so, if I hit continue, what it's going to do is it's going to generate that listing on the platform. So, we've got our web hook working. It's passing updates uh to make sure And let me do a refresh so that listing will show. Yeah. Okay. Yep. So that's the listing. Um and so now what we want to do is um we want to create a smart contract. So um because it has all the information that it needs to actually create this agreement now on chain. So we hit create smart contract. What it's doing now is calling the circle APIs to actually uh deploy that contract on chain. So may take a little time but uh it should work in a few minutes. Let's see. Yeah. Uh actually great question. Uh the network I'm using is base. Yeah. Yeah. Yeah. No, no, no. I mean is is a great partner. Um but um but we we support you know all the a lot of different chains. Yeah. Let me see taking a little time. I got a follow. Can you do an escro crosschain or does it have to be single. Um yeah, you actually can perform crosschain extra escrow experiences. Um you can use our crosschain transfer protocol to do that. So I'll give you example of how maybe that would look is it's more of uh maybe a crosschain deposit. So maybe someone comes to the platform and the contracts are on base but their USDC is on Salana and so they want to deposit from Salana USDC to base they can send it over the crosschain transfer protocol CCTP right and then it will deposit into that base contract and then if the beneficiary says hey you know like I'm not on base I'm on you know another chain Ethereum I want it on Ethereum then you can do crosschain, you know, payout from that contract. Oh, so it's not actually part of the contract. Right. Right. So, so usually what we've seen as developers who are building um crosschain experiences where they're dealing with smart contracts, escrow, uh a lot of them pick like one chain where the actual contracts will live and then they build interoperability between like deposit and payout flows. Yeah. Yeah. Uh let's see me go here to the oops wrong one. [Music] Let's see something. Okay. So, yeah, it's working. It's pending. It's just taking some time, little latency here to actually deploy the contract. Um so these are these are different contracts I deployed testing it. So this based upon your let's see actually what I'm going to do let me let me show this cool video so you all can see like end to end really quickly because there is you know some sort of uh latency around the internet in here. So, I'll play this video right quick so you guys can see it in the inflow of like how it works. And so another thing too um is you know you don't have to worry about gas with these uh with using our tooling because you can design these experiences and then we have built-in gas abstraction with our wallet uh as a service infra um and so it enables you to really abstract away kind dealing with, you know, holding native tokens for gas. And so we also uh make it very easy for, you know, as we're abstracting the gas away, obviously there's a cost there, but we make it easy for you to actually uh pay for your gas fees from fiat um directly from a debit card that you would or a credit card that you put on file. Um, but we we really have uh designed this for, you know, enterprises um that, you know, probably aren't web 3 native to be able to integrate our technology, take advantage of the near instance settlement that comes with public blockchain networks and manage wallets and transactions at a scalable level to be able to um, you know, expand their their actual footprint of of payments around in the world. So, um the last thing I have is um deploying the contracts. Yeah. Yeah. you you can actually deploy like a contract factory uh and then that'll allow you to kind of create iterations of that within the contract factory to be more efficient on the gas. Yeah. Yeah. Yeah. So in the mechanics of what you're doing is that first step basically taking the an unstructured document and you creating basically structured data to then feed to the circle API in terms of and I guess how does that piece work. Is it as as simple as like feeding the contract to open API and just doing a little prompting to kind of get the structured data you want as far as the JSON format. Yeah, I'll jump into this right quick for you. So, okay. So, yeah, that first um part is, you know, we've created a prompt to make sure it outputs it in JSON. So, it parses things out, outputs it in kind of a JSON format that looks like this. Uh and then uh that's how we're able to kind of feed it through to be able to um create basically that listing that adheres to uh a consistent format of of um showing the actual transaction um amount and task. I'm not super familiar with escrow contracts. Are they fairly standardized or they come in different forms. And I guess how uh robust has it been able to be in terms of handling different uh formats. Yeah. So um here's the actual solidity code. I'll show you uh for the actual escrow contract here. Uh and it this is a very simple one. Um it's only like a couple hundred lines uh and a few functions. they can get uh very robust. But if you're um for most for most escrow um you know experiences uh this could cover a lot you know for most escro experiences and there are a lot of templates out there um since escrow has been a big thing in the actual crypto ecosystem um that you can use. one um is is one that um our research team worked on. It's called the refund protocol. Uh I'll pull it up right now, but it's a it's an escrow template that kind of gives you all the robustness you would probably need to handle um any type of escrow scenario uh that that has been prevalent in the ecosystem. Let me pull it up right now. And um you could actually use that uh and as a template and and you know add to it if you want or just use it straight out of the box. So let me show you this one. [Music] Yeah, here it is. right here. So if you go to circle research, uh this is an article about it and it kind of explains, you know, the functionality built into it. But also too, we have a repo. Um it is where is this repo. Refund protocol. So yeah, this one right here. You could use this as a template. Yeah. Can you just wait for the microphone so everybody could hear you. Hold on one second. Thank you. Okay. Um so my my question here is uh towards the challenges of minimizing human intervention. Um I I find uh LM and agents um sometimes unreliably non deterministic right so there is always this pattern of um the LM or the agent builds like a plan and someone reviews to approve um given the nature of um your business right I I understand that Like I guess the question here is like what are for circle AI the biggest challenges when you talk about minimizing human interaction using yeah great great question. Um so the question here is you know what what is um the challenges with minimizing interactions with payments as it relates to circle. Um, so I think that um, our focus as our company is kind of like creating more of a frictionless exchange of value using public blockchain networks for settlement, right. But we started to see a huge trend uh over a year ago where u a lot of developers were building agentic workflows using USDC is the payment rail of choice to transact between agents and agents. And so um what we we think is um obviously there um the the one thing about you know um AI is it's not deterministic and payments are deterministic. Uh you want them to be deterministic but there is a lot of conditional logic that is happening before payments are being released in the world. And so um what what I think is right now the best safest way to design these experiences is with human in the loop built into it. Um and and and really kind of focus on it doing being just a pure review basically for a person in a actual um payment operation u job to be able to have just something else out there that is doing work 24/7 and saying hey here are a list of payments that are ready to go and this is what we've analyzed and why we believe it's ready to go but at the end end of the day like you're the final approver. Uh and so that's what we think um you know in the near future combining these technology together uh it can be a great combination but autonomously and just you know full automation of controlling um sending and receiving payments I'm not sure we're there right now. Uh but I will say that um you know the way this AI industry is moving um there could be a world you know 5 to 10 years from now where um people actually trust these agents to autonomously handle um payments um and procurement and things like that. So hopefully that answers your question. Yeah, but we're we're in the first inning of this and to be completely transparent, you know, there's people in this room who have a lot of experience building with agents. Um, this is designed to inspire you all to like test out the combination of this technology and and and and give us feedback, too. Uh, we're learning alongside. Oh. Oh. Um, I missed the first part, but what's the closest real life examples you have of this autonomous work evaluation and settlement. Do you have any kind of real life examples you can share. Yeah. Um, so we we haven't released any anything that's like in production doing this, but there are companies that are doing this right now in production. Um and that is you know you have crossmit is one company uh and then another company is um third web with Nebula uh their model. So those companies are kind of you know on the bleeding edge of of offering these experiences to developers but also kind of you know putting things out themselves. So I'd encourage you to check out those two companies. They're both uh Crossman's headquartered in New York, I think, and uh Third Webb is right down the street here in the Bay. Yeah. Yeah. Um hi. Um I have a question regarding like around the escro transactions. So I wanted to know how feasible uh is it to implement Jon proof um in this blockchain based escro transactions. Yeah. um that that is um that's something that is is pretty feasible with the advancements that we've seen with um proving TLS notary communications. Um those a little bit lighter weight to prove and you can generate a proof faster and pass that to a smart contract to be able to um perform uh escrow. Uh so there is a company called ZKP P2P that actually is experimenting with this and it's a live experiment that is working really well. So um there are different ways you could you could design these and integrate ZK proofs into them um that we've seen and and ZKP is one of them that has done it pretty well. Yeah, great question. Yeah, thank you. I have sorry I have another question as well. So uh could you go to the slide where the uh implementation thing is there for the cold storage support. Okay let's see so here I have a doubt like um so yes in this like transactions should not all uh always be instantaneous. So you should be like creating ahead of time and broadcast next month, right. So I'm not sure like I I haven't done like if is there a possibility if like uh there might be a double spending kind of attack if we like hold uh the transaction and it is not spontaneous. Um so the the question is could actually u generating an offline transaction that's approved create a double spending uh exploit is that that that the question. Um yes. Uh um I don't think it could could necessarily do that. Um, you know, from from my experience of of people actually kind of generating transactions offline to actually broadcast later, I haven't seen that that issue become uh a problem with double spending. Oh. Oh, no. And like uh could you like little bit uh explain me the scenario of like how transactions should not always be instantaneous like around this. So, so this this use case of me maybe if you are a company and you're running payroll on chain and um you know that um there is a transaction that you're going to make in the future um for a certain amount to do payroll and it's on a consistent cadence. You could actually uh generate that transaction, sign it and approve it offline and then broadcast it on the day of the actual transaction that needs to be sent out. Oh, got it. Thank you. Yeah. Okay. Hey, how's it going. Good. How you doing. I must have missed the first part where you mentioned multi-IG but um my question was just revolving around like some of the different use cases of multi-ig combining that with you know humans agents um you know for example in this um contract evaluation you could have like three different agents try to evaluate the same contract and criteria inside of multiig but what other what other use cases of multi-IG and AI do you see. Great question. Um, you know, I I think that um, you know, there could be a world where um, you like you you have multiple agents that may act as um, you know, in in kind of like a a financial uh, operations unit at a company, small company, and you may have um, you know, a CFO agent, a controller agent, accountant agent, and those agents are cross-checking each other's work and things like that. But then ultimately they need to do uh some sort of multi- signature process to be able to sign off on uh maybe transactions that are over like $25,000. Um so that that could be like a world that we see uh with with agents and um USDC. Great. Thank you. Yeah. Okay. So where you using that AI. um for reading the document and generating the like what the contract should be. So there is a human in the loop. Uh so for in order to the in order for the human to approve or reject it, he needs to go through that document himself as well, right. U so how exactly is that agent saving any effort because the human has to still go and read the document, right. Yeah. Yeah. So like you know right now like this is just a a a simple prototype, right. Um we could have gone the extra mile and started out with someone uh you know using NLP to like just create like a a simple prompt to say, "Hey, I want a contract between you know me and this other person that does these things." And then the agent goes out and writes it. And then the agent could actually, you know, um parse out the information that it wrote and then send a notification to the two parties that this is agreement for $100 and these are the things that need to be met. Um so that that's that's a world where we we could have done that but like we were just trying to put together a simple prototype to just showcase the combination of technology but this is not you know something we we feel like is you should you know deploy in production and use right now but it's in inspiration you know of combining these different technologies. Okay. Thanks. Yes. Yeah. So I guess um yeah uh we don't have any other questions. We can close it out. Thanks everyone. [Music].