Full Transcript for Using Agents for Long-Horizon Financial Work — Aman Singh, Arca

We're actually not a SaaS company. We are the firm ourselves. Agents prompt people more than people prompt agents. And it is a proactive kind of service that is running for them 24-7.

We're here at the AI Engineer New York Conference 2026, and I'm here with Aman Singh from ARCA. And ARCA's recently raised $64 million for an AI native wealth management firm. So first of all, Aman, can you tell us a bit about your role at ARCA and the financial services you provide and how you're using AI agents to run them? Yeah, for sure.

Thanks for having me. My role at Arca is I lead the AI platform team. So we're building the underlying sort of harness and our capabilities to kind of run the business with AI, which is our ultimate goal. In terms of the services that we provide to our clients, this is a broad spectrum of financial services. So that includes sort of financial advice, financial planning for their assets, and sort of

tax planning and insurance and estate planning as people get wealthier. Maybe you are someone who just sold a business, for example, and there's lots of complexities with all the different partners, et cetera, right? So we're going to help you think through that. We also have clients that are, you know, really large technology executives that have...

are trying to figure out a real plan for retiring early, right? And also small families that are trying to find their first home, for example. Yeah. So the clients that you have so far, do you have to kind of talk them through using agents and why you're using agents and tell them a little bit about the technology behind it? Yeah, so the role of AI at Arca is not to replace the advisor, it is to replace all of the work around the advisor.

So our clients don't really interface with AI directly. All they experience is a level of service that has not been possible in this industry before, delivered through the empathy and care of a human advisor. We're building the machinery behind every client that's constantly thinking about

what is the market doing and how does it impact Richard? What else is going on in your life? What are the textures of your life that impact your finances? We're able to be way more proactive, way more responsive, and just deliver a better level of client service using AI that does all of the back office stuff. So let's get into some of the technical aspects of it.

Which models are you using to power your agents? And how do you decide which model is best for which action? Yeah. So today we're using the Frontier models from the Frontier Labs, like Anthropic and OpenAI. Cloud is kind of our primary model has been, but we've gone through several iterations of models over the years. We used to be in Gemini way back when.

and then OpenAI, and then Anthropic. And what's guiding all of our decisions are our benchmarks that we have internally for all of the various capabilities of our general harness that it has to express in running our business. And so just recently, for example, despite the external benchmarks claiming great things for Luna, it didn't really quite work out for us as well as we had expected.

It was way too slow and it was costing a lot. And so our internal benchmarks kind of guide our model decisions. And as a principle... We want to be model agnostic and sort of not, you know, take a dependency on a certain provider or a certain harness from one of these labs and kind of keep that optionality open for us. Okay. So you just mentioned harnesses.

So you're using different harnesses depending on which model you're using? No, we have our own kind of built internally that is model agnostic. Okay. Okay. So when a financial advisor is doing something like a taxation report or something like that, how does the harness decide which model to use? Is that automated? Well, yes. So we have certain tiers of models based on different complexities of tasks.

So a task like assisting with a tax plan or doing a tax analysis would get our heaviest tier of models. Inside of that tier, it is a little bit flexible. So you could use an Opus tier model or a Sonar tier model or a heavy GPT model. But based on There's a lot of like background activity that our agents are participating in, right? That is using a lower tier of model based on the complexity of the task.

So that's kind of how we make decisions on which model serves which task. Okay. So is it the financial advisor that's actually making that decision while they're using the product? Not really. They're not aware of the happening. We've abstracted this away. Okay. from them entirely. They kind of just interact with our product as they would.

And those decisions are made internally by us. Okay. So in your presentation at the conference earlier today, you talked about a tax bill example. I just wondered if you could maybe walk us through an example of adjusting a client's portfolio, investment portfolio, You know, from identifying a need to maybe rebalance the portfolio to executing trades.

Can you talk us through, you know, what parts of that process the agent does and what parts the human advisor does? Right. So just like in the talk, this is a thing that will span 10 days. And so agents are ultimately responsible for delivering that outcome. But there are certain parts that they do and certain parts that they do not. So in this example, when the client emails us with this whole tax bill, there's a piece of the analysis of like, where is this client's money allocated today? And what is the most optimal way to liquidate some of that to produce $100,000? That is best suited for agents.

to take on as an analysis task. So they do exactly that. Do they have certain limits, though, that they can't execute a trade at X amount? So the analysis part is fully automated, but they're unable to actually execute any sort of money movement or liquidation automatically. Mm-hmm. We have a very deep integration with our custodian that actually gives us APIs to be able to do that.

But we have strict guardrails around human in the loop for things that would either move money or liquidate assets or even directly communicate with our end clients because there's a level of service that exists. service and quality that we expect. So all of the internal analysis will be done by agents, but they will also pull in the right person to be able to execute the trade when needed.

And they'll give the person a plan that they're able to review and kind of adjust. And yeah, go from there. Yeah, so you mentioned that these processes tend to be 10 days or at least a longer sort of running time than most sort of agent stuff these days. So when an agent kind of resumes a task maybe days later than they started it, how do you restore, how do you check that the plan still fits the client's

needs? Yeah, so this is an interesting one to think about is We have tons of these signals like I described in the talk. Some are, for example, you can imagine there's an email thread that is receiving responses and there's chatter happening. You can imagine that any additional response to that goes to the same agent that's reading that email thread and reacting to it.

But a fresh signal, like a phone call that was made in the middle, that is a brand new signal that isn't attached with any other ongoing process. And so there's like a fresh agent that wakes up to figure out what this means, right? And the way they understand what is happening right now is our internal memory systems. So we have this persistence for every client.

What is happening right now? What are we trying to service? Who owns what? What has happened so far? What are we tracking for next? What needs to happen immediately in the next couple of days? What are we tracking for the long term? Which individual is responsible for which action? All of this is being tracked by our memory systems that our agents contribute to.

But also there is a kind of really sort of dreaming process that reflects on the state of the world as it relates to Richard, the client, and is able to kind of like update these memory systems to persist long horizon kind of tasks. So that agent that received a new signal quickly ramps up on what the situation is with the client. And he'll know, okay, we're actually executing a big tax bill.

And we'll be able to see, okay, my signal relates to that tax bill. So let me kind of contribute to the state of that world. Can you talk a little bit about the safety sort of aspects that you've maybe built into your product or harness to make sure, obviously, that no money is lost along the way? Yeah. So all of our safety restrictions are fully deterministic, and they take the decision-making off the agent's hands.

So, for example, certain tools let the agent kind of execute the tool itself. So if it's like a simple record-keeping kind of tool– it will execute it. We also, with every time a tool is called that writes data, we have LLM-based verification running on that action. These fast LLM calls that analyze every single write to our database. So that's another layer of verification we're running.

And then we also ingest a lot of external information. So there's emails coming in, documents coming in, phone calls being made, which are targets for prompt injection. So we run sort of verifications at the edges that detect presence of certain flavors of prompt injection. And then anytime there is a case where data leaves our system, for example, in like a web search in the most obvious case, but also if we're sending a calendar invite to Richard, right, that's an external kind of data where we have both deterministic checks on presence of certain information that we know is PII but also a consensus of small models that ensure that there isn't any kind of data exfil

being attempted. So we have tons of different kind of guardrails built into the harness with the principle that we want to kind of contain them at the edges of capability and not earlier than that. And because you're in the financial industry, are there certain kind of regulations that are required that you have to sort of keep to in terms of the technology that you're using? Or is it just more about outcomes and the way you sort of deal with clients? Yeah, the industry cares about outcomes, but compliance cares about auditability, right? And so

our system is such that auditability is by default. We have... Every single action that an agent takes produces a change log of what changed, who changed it, from which part of the system, and when. And this applies not just to agents, by the way. It applies to human actors as well. So if you change something in the UI that affects the client, we'll log that action.

So it lets us both get auditability by default, but it also powers some of our agentic capabilities where the same thing that tracks a UI change also could be used to inform the agent that that happened. So auditability has been a big part of our story, both for, obviously, compliance and regulation, but also for our agentic loop. Yes. In your presentation, you had a nice line, agents prompt people more than people prompt agents.

So how do the agents decide who to involve and how much of the context that they need to provide that person in order to do what they need to do? Yeah. Another interesting one, so this is similar to how humans work in our industry, is there is a process that we're tracking over 10 days. There's multiple actors involved. The actor at step seven may not need to know about this just yet, right? They're pulled in at the right time.

And so our agents with our kind of like long memory persistence plus the daily reflection on what is happening

reflect on where the state of the world is now. at the moment. And they're able to pull in the right person at that time when there's a signal that implies that that person must be pulled in. And all of this is work that we have done to operationalize the context of how this industry works. But not just that, but how does ARCA want it to work? And what are our principles of how work happens in this industry? And that is another advantage of us being sort of a...

not just a SaaS company. We're actually not a SaaS company. We are the firm ourselves. So we can standardize the way this work even happens so that our agents can participate in standard ways that work must happen. So Earlier in the conference, Anthropic did a workshop about their managed agents infrastructure, and a lot of it, even the orchestration, is becoming more automated now.

So do you foresee kind of using that type of functionality? Because obviously it presents a danger in that the human is not necessarily always in the loop anymore. So have you had any thoughts about using that technology to automate even more of the process? I think we are very bullish on the models from Anthropic and labs like OpenAI, but less so on taking a dependency on a product like managed agents.

Because managed agents, one of their key things is how the models kind of persist and contribute memory as to what is happening in the world and all of the operational knowledge that they need to use to be successful. And so letting them own that part of the business is kind of like

a risk because owning your intelligence gives you the ability to impact the business. If you hand off the intelligence to another provider, you lose some of that control that you need to kind of like build something that is unique, and tailored to your business to such a great degree that it can actually impact your business. And just on Anthropic, they've also recently released financial services, so they're partnering with a whole bunch of different firms.

Do you think what they're doing is kind of competitive to what you're trying to do, or do you see them as different things? Yeah, I think Anthropic getting into our kind of industry is very validating for our industry. But the way I think about it is that it is very different to be a services firm that has access to AI tools versus a firm that was built to be AI native.

The firm with AI tools requires their users to prompt the agents to produce work or to do work. But here, like I said, at ARCA, agents prompt people more than people prompt agents. And it is a proactive kind of service that is running for them 24-7. And it's kind of like running the business in the most standard way that we expect at the level of service that we aspire to.

Which looks very different if you're a company with AI tools. Yes. Yes. Okay. So a little bit more about on the security side. So can you explain like what in your processes runs inside a sandbox and how do you verify like a change to a financial plan, you know, before anyone acts on it? Sure. Yeah. So

the way we use sandboxes is that the sandbox is one component of our harness. Our agent isn't actually inside of the sandbox. It uses the sandbox to offload computation. And we've built systems to make it safe for code inside of that sandbox to access sandboxes. our data. So we have this thing which translates the code it wrote into a strict format that we expect, throw away the code, and you instill guardrails on that format before it reaches your back end.

So we allow the agents to use code to query our data, which means that they can aggregate it, they can munch it, they can work with it as they see fit to produce such a thing like a financial plan. Inside of the same sandbox, they produce this, you know, beautiful artifact that we can share with clients that has, like, it's a PDF of, like, here's your financial plan and here's how we're planning to kind of, like, approach your life financially.

And once that is produced is where we run our verifiers. So it's a certain type of artifact that is produced from the sandbox. Yep. The moment that it's produced, we run a bunch of different verifications on it, some deterministic that check for presence of like, hey, did you just put a raw account number in there? You should not do that.

So deterministically, we can check that. But also fast models like the smaller models or Jev to analyze for presence of things that might make this artifact noncompliant. For example, you really should not be promising returns

in that artifact. That's another thing that we will check before it is publishable. The last thing I'll say on that is that doing this actually makes our compliance better than if humans were doing it because AI is tireless at finding even the smallest mention of a non-compliant piece of writing in there. We'll continue to invest in more of that and constrain at the capability edges.

Yeah, you mentioned Jeff there. So you've started to use decision models as part of your process. What other products other than Jeff are you sort of looking at? Yeah. So what we've noticed is when models are working with financial data, right, when they're answering questions that require financial knowledge, They are very confident in the knowledge that they have.

So a small example is that models will very happily use the tax brackets from 2025 to come up with an analysis and be like, all right, that is it. But that is obviously incorrect. And so that is one of the ways in which we're using decision models in our harness is to check models. when the model is about to make a financial recommendation or any action that requires financial rigor will detect and will nudge the model to kind of use our knowledge base of verified facts about the world that is true today and or use their kind of web search.

So it kind of makes it, this is kind of a point about the harness and owning the harness that lets you do things like this that help your models be accurate where it matters. And do you use decision models in, for example, recovery if a trade fails to execute? Is there a decision model involved there or is there another path to get the agent back on track? No, not today.

That is not a use case that we're exploring today. Okay. So if a trade does fail, for example, how does the agent recover at the moment?

At the moment, we are not doing autonomous trading with agents. The agents will propose that we make trades and it is fully up to our experts to figure out if that is the right trade to be making and to execute the trade.

So on the same sort of line of that, your slides say that every staff edit or cancellation comes with a Y and it becomes an eval. So how does that feedback get turned back into the system as a measurable improvement? Yeah, that is another one of the advantages of us being the business and not a SaaS company is that we have the ability to require them to give us feedback.

And yeah, the way that we loop the feedback back into improvements is something that you would expect is all of that feedback gets piped into a data store that couples that feedback with the trace of the agent that produced it. And so we were able to take that trace, put it next to the feedback, and every night we run this process where we collect traces from the real world, from our agents in the wild, and run a meta agent on top that suggests changes to our harness.

So maybe tools that were misleading or things that were errored or there's missing knowledge in our knowledge base. And they'll surface this information to us and then we'll be able to kind of improve it. Today we still have a human, like a human engineer in the loop before we actually ship a prompt change. I've noticed that agents will make really nasty prompt changes if you leave them to it.

Every little fix becomes the whole prompt. And they're unable to stay meta and kind of generalize the fix into a prompt that generalizes. But yeah, we have feedback loops from our product that we collect directly as first-class product features to collect evals into improvements.

And you also mentioned in your presentation about turning knowledge of how a firm works into agent context, which is actually something a lot of forward deployed engineers do try to do is turn an organization's kind of internal knowledge into actionable things for agents. What does that look like for your company technically and how do you sort of keep it up to date? Yeah.

So we have a knowledge base of files that is represented as files. And

the way we keep that up to date is we've handed it to our experts to curate and update. So it is a first-class feature in our product. So on the left-hand side, there's a tab called Knowledge, which has the full operational context that our agents are using. And as they work

on things, they're able to cite knowledge. And so it kind of like creates this loop of like, oh, we notice that the knowledge is incorrect. and that gets surfaced to us in our trace analyses. And because it is a part of the product itself, people are able to go in and edit the scale directly. That's how it kind of works. All right, okay. So, you know, you mentioned you're actually offering these services to clients through, you know, I presume you have a staff of financial advisors in your firm.

So can you maybe give us an example of some, you know, a client that you've had that's had a measurable improvement in their investments or taxation or whatever through the agent system and maybe some sort of details about that? What in the agent architecture kind of helped that client get such a good return? Yeah. I'll give you a recent example.

This person wasn't a client yet, but they were at the point of becoming a client. So we had all of their documents, their statements, their current investments, et cetera. And this person was already working with an advisor. And so they meet with us. They tell us that, hey, I have this advisor already. They're charging me $1,500 for their services.

And they're not very responsive to me. So I'm chatting with you. And so our agents have kind of like, you know, read through all of those documents. They've analyzed them. They've analyzed what the person's goals are that they state, right? They've also analyzed the statement of, like, who this current advisor is, right, and how much they're charging them.

And they discover that there are fees that this person was charging them that they weren't aware of and surfaces it to them and kind of, like, makes them not only aware of– of the fact that they're being overcharged, but also aware that that person wasn't even fiduciary. So they're not obligated to act in their interests. So this is the sort of like attention to detail that our agents bring about when they're analyzing a financial picture that sort of would not have been possible if we didn't have have these.

There's several examples of proactivity that our agents kind of like produce of like someone has a deadline coming up or they're at risk of missing their RMD or that kind of thing. And so this is difficult at scale for humans to keep track of, but it is the default behavior of our agents at ARCA. Yeah. Wonderful. Well, that's probably a good point to stop at.

So thank you very much, Aman, for joining us. Thank you for having me.