# Inside Arca’s long-horizon agents that run the business — Aman Singh — session 2026-10-13T15:05:00.000Z → 2026-10-13T15:23:00.000Z _46 transcript lines · 36 slides_ ## Transcript I was just doing it a little bit faster. The change that actually matters. Alright. Good morning, everybody. Thank you for joining us today. It is such an honor to be sharing this stage with so many great speakers. So, yeah, let's get right into it. My name is Aman. I lead AI at Arca, and today, I'm gonna talk to you about Arca's long horizon agents that run our business. Arca is an AI native services firm. We provide our clients with financial services like financial planning, tax planning, asset management, investment advice, and we serve a range of clients. Some of them are like technology executives. That, have amassed a lot of wealth and need a real plan to retire early, but also that family in New Hampshire that made their first million dollars and and want to buy that house finally. I said we were AI native. There's a lots of there's lots of definitions of this this term these days, very overused. What we mean by AI native is that agents run our business, not that they assist the business. From some co pilot corner. They they execute the decisions that shape the outcomes that our business has for our clients. Work in this industry, it's interesting to know what it looks like. In financial services, the work is more long horizon and less long running. And what I mean by that is this is less agents grinding tokens for, like, hours or days on end. Right? This is more one client goal that spans Ten days. It's very stop start. There's many actors in between, many decision points, many handoffs, and ultimately, that goal lands like ten days later. That is the kind of work that that we are working on. And so here's an example. Jane's our client, fairly wealthy, but has a big tax bill. Oh, has a big tax bill in April 15, right? So we're gonna help Jane figure out What is the most tax optimal way for this cash to be to be raised to pay the tax bill? So there's the adviser that will do all of the the statement analysis and the analysis of how to make this tax optimal. There's the the trader that would actually liquidate the the assets. They... The assets themselves will take, like, days to settle, and then the ops people will come in and kind of, like, trigger the ACH. That will itself take days, to land. So this is kind of the work I'm I'm talking about. This industry, which takes days to settle. And of course, if you do this at scale for several, several clients, the amount of time our firm takes to do this sort of work exponentiates. Right? So at Arca, we took a different approach. It's helpful to know that Arca is not a SaaS company. We are not selling software to other businesses, to other firms. We are the firm. We're an applied AI company that happens to be running a services business. In this industry. And so the approach we took was, alright, we're gonna have agents own this whole long horizon outcome end to end. And for that, we gave them a couple of key components. I'll give you a sneak peek of. We gave them signals from the external world that keeps them really aware of what is happening so that email will be read by agents. We gave them all of our operational context on what to do about that email. What does this industry do with the situation of taxes? Right? We gave them a Harness that gives them all the tools and the guardrails and more importantly, persistence of memory over the kind of long horizon period to carry that work out. And of course, we gave them the ability to collaborate with people. So that work with, with agents compresses a lot because all we did was we took humans out of the critical path of of this work. Nobody has to babysit this this This goal over days, agents are are on it. In this talk, I'd love to describe to you how we actually do that. Let's follow the journey of this email. Jane owes $100,000 for taxes. This email, much like many other signals in our in our platform, will be will be read by background agents. So there's, like, phone calls our firm is making. There's documents that are coming in. There's meetings being had. There's events coming in from our custodial. There's market movement that's happening. These are all signals that our background agents are continuously evaluating to progress work. So this email is one of those signals. And when the signal is ingested by agents, they actually get to the work, right? We have a harness that gives them the knowledge to know what to do about the situation. They have deep client memory so they know, hey, let's never touch Jane's Apple position because she said that in a call like eight months ago, right? We of course have A sandbox for all of the financial computation that needs to happen for this analysis. But largely, I think harnesses today are are coalescing on a standard shape. So, it's more interesting what happens outside of outside of this harness. So after they've done the work, they produce this plan. This plan by itself cannot be executed without people. So in our product, we build a space. Agents build a space where they put out this plan and there's - you can chat with the agent. To, like, kind of know what's happening with the plan. There's multiple people that can be chatting with the agent. And more importantly, this space is where also they pull people in when they need people to execute some work. So here in this case, we would approve the plan and email out to Jane. And then there's this whole dance of has Jane replied? What does her answer mean for the plan that we had, Right? And then all of these other questions that will have to be answered throughout this whole, like Long horizon work. At Arca, we were like, of course, we're not gonna have people babysitting it. So we let our agents watch the world so people don't have to. Right? So we give them tools to be able to register interest in anything happening in our world. So they're able able to say, let me know when Jane responds. Let me know when that ACH lands, right? And this is powered by our signal system in in the background where agents are routing signals to That are interested in it. And of course, if the signal never lands, agents can, like, wake themselves up on on a schedule as well to keep track of work. But then, of course, the real world is very messy, right? People are waiting for that email, but Jane never responds to that email. Say we we meet her in person and we learn some information that affects the plan. So the person goes in and they they add this Into our UI. But this act of adding information or doing work in our UI is also a signal that will wake up an agent. In fact, when people work in our in our product, when they reschedule a calendar event, you know, that's a signal. When they mark a task complete, that is a signal. So this system lets us be both aware of everything happening in the external world and the internal world as work is progressing so our agents can participate in work. And of course, agents are communicating with each other as well. So this signal read by a background agent, we let it notify another agent about this so that it can update the space to say, hey, we just need $80,000 instead of the $100,000 So the work has changed because of these signals. And the last piece of the story is that agents are able to pull in the right people at the right time. So the agent on the left had As a better operational context to be like, Okay. This... The next step here is to pull in the the person that trades these, these assets. And so that person now gets a task and gets pulled in to participate in this long horizon work. What we've done overall, if you take a step back, is we've given our agents the primitives for driving longer as work. What do people do at work, right? They they need to stay aware of what is happening, so we've built this very intense, like, signal system for our agents to be aware. They need to know what to do next, so we've given them all of this operational context. They need to do the work, so it's our harness that lets them actually perform the work and keep track of it, right? It's long persistence, memory systems that hold the state and bring in the right people at the right time. This is a pretty simple idea on the face of it, but there's a lot of emergent complexity. You can imagine at any point there's hundreds of these signals Coming in and they are, you know, tax... Tasks are being added on people's plates. They're being pulled in. Background agents are communicating with each other. Right? So over the last six months, we've we've been working on getting this system to be really good. We've been closing all of our context gaps so that agents are fully aware. We have been working on the precision of tasks, so pulling in the right person at the right time. Work that needs to be tracked for the future is tracked in the agent's memory. Work that is doable now becomes a task, right? So we've been working on, on our ability to hold state over long horizons as well. And because we are the firm and not just a SaaS company, we've been changing and standardizing how work happens in the firm in the first place and operationalizing that context into, our agent state. And because these are our colleagues that use our product, we collect rich reasoning from them that become evals for for our system to improve. So I guess there's there's a question to be asked here, like, why do this? Right? What does this unlock? What is the takeaway here? Right? For for us, this is our whole thesis is that we want our platform to be so AI native that agents drive the business. Agents run the business. They they are making the decisions that shape our outcomes. And so at Arca, when people log in, right, they see a list The tasks that have been prepared for them by agents. They've already read that email. They've, like, looked at the document that came in. They've done, like, 90% of the work, and they're pulling you in just when it's time for you to act. So building the system lets us get to a point where at Arca, agents prompt people more than people are prompting agents, which lets our agents drive the work that our our firm does. And because As agents are driving the work the firm does, agents can drive the business. Let me give you an example. Remember that email that Jane sent us? This is a bit of a failure, right, because we should have just been proactive about this in the first place, right? So Jane should never have to send this email. So say at, you know, our AI native business, we take on this new goal. Our new goal is proactivity. Every January, prepare each client's Tax situation and proactively reach out to them before anyone even asks. This is a new business goal for our business to drive. And in an AI native firm, all we have to do is make this goal part of our agents' set of goals. And because they have the primitives to be able to drive work through people for the business, they start driving this goal and just like that, you have you have these analyses being done in January and these these one click approval emails with the full plan for every client showing up on our users plates. And because they're aligned with the goal of proactivity, they can one click approve and drive the business towards this this new outcome. So this is sort of, I think, the key difference between a a company that uses AI tools versus a A company that is AI native. In an AI native company, you know you've built one when you can steer your business by steering your agents. And that is our ambition at at Arca, and we are, we're hiring. So please, please check out our website. Please reach out to me if this is something that you're interested in working on, these sorts of problems. And, thank you for listening. ## Slides ### 00:00:19 # AI Engineer NEW YORK ## WE'LL BE RIGHT BACK View Full Schedule at [ai.engineer/nyc/2026/schedule](ai.engineer/nyc/2026/schedule) [Silhouette of the New York City skyline at night, including One World Trade Center, the Empire State Building, and the Statue of Liberty] ### 00:00:43 # AI Engineer NEW YORK ### 00:01:24 # AI Engineer Europe 2027 Europe's flagship technical AI conference returns to ExCeL London for three days, February 17-19, 2027 — ### 00:01:43 ### Presented by arize View Full Schedule at [ai.engineer/nyc/2026/schedule](ai.engineer/nyc/2026/schedule) [Arize AI logo, featuring a pink stylized 'A' shape next to the word "arize"] ### 00:02:23 # AI Engineer Europe 2027 ## ExCeL London ### 02.17 - 02.19, 2027 Europe's flagship technical AI conference returns to ExCeL London for three days, February 17-19, 2027 — bringing the world's leading AI labs, platforms, and tools to Europe's builders. 3 DAYS - LONDON, UK ai.engineer/europe [Black and white image of a classical building in London] [Black and white image of Big Ben and Westminster Bridge] [Black and white image of the London Eye] ### 00:02:50 ## SILVER SPONSORS - Anchor - apify - AXO CAPITAL - Chainguard - CLOUDFLARE - DE Shaw & Co - Expo - extend - FLOX - Gravitee - Judgment Labs - Kimchi - MINIMAX - NIMBLE - Pydantic - RELAI - SENTRY - specific ai - supabase - SurrealDB - tetrate - UNION View Full Schedule at [ai.engineer/nyc/2026/schedule](ai.engineer/nyc/2026/schedule) ### 00:03:20 # Stay in the Loop Scan the QR code or view the schedule at ai.engineer/schedule [https://ai.engineer/schedule](https://ai.engineer/schedule) [QR code linking to https://ai.engineer/schedule] ### 00:03:49 # ARCA Arca is an AI-native financial services firm. ## Inside Arca's long-horizon agents that run the business Aman Singh / Lead AI Engineer ARCA ### 00:04:21 # What do we mean by “AI native”? ### 00:04:49 ## What work looks like in this industry # Long-horizon, not long-running ### Inside Arca's long-horizon agents that run the business Aman Singh // Lead AI Engineer ARCA ### 00:05:21 # Jane owes $100K by April 15 1. Work out which accounts to draw from 2. Make it tax-efficient 3. Get Jane's approval 4. Raise the cash 5. Let the sales settle 6. Send the ACH and wait for it to land 7. Confirm with Jane ### 00:05:51 # Long-horizon work [Timeline diagram illustrating a 12-day financial transaction process. The top row, labeled "Jane and the world," shows "Jane (1 day)" adjusting the ### 00:06:23 # Long-horizon work at scale ## Process Flow: Adjusts the plan - **Jane and the world:** - Jane (1 day) - Settling (2 days) - ACH in transit (3 days) - **The firm:** - Advisor (3 days) - Plans the sale - Trader (2 days) - Raises cash - Ops (4 days) - Verifies, sends the ACH - Advisor (2 days) - Confirms with Jane **Timeline:** Day 1, Day 4, Day 5, Day 7, Day 9, Day ### 00:06:49 # Agents own outcomes end to end ## Signals Every email, call, document and event, from inside the firm and out. ### Inside Arca's long-horizon agents that run the business Aman Singh / Lead AI Engineer ARCA ### 00:07:24 # Agents own outcomes end to end ### Signals Every email, call, document and event, from inside the firm and out. ### Operational context The firm's knowledge and ### 00:07:52 ### April taxes Hi, my CPA just told me I owe $100K in taxes by April 15. Can you help me figure out the best way to cover it? ### 00:08:23 # Agents do the work - **Knowledge base** - Tax-aware investing principles - **Client memory** - "Never sell her Apple position." - **Tools** - Act anywhere in the platform ## Agent (working on a new email) > From: Jane Whitaker > Subject: April taxes, Mon 9:12 am > > Hi, my CPA just told me I owe $100K in taxes by April 15. Can you help me figure out the best way to cover it? > > Thanks, > Jane - **Sandbox** - `project_tax(100_000)` - **Live portfolio** - Her accounts, lots, and cost basis - **Research** - Market and tax context The harness: context, memory and tools to do the work. ### Inside Arca's long-horizon agents that run the business Aman Singh / Lead AI Engineer ARCA [Diagram showing an Agent in the center, connected to Knowledge ### 00:08:52 # Agents do the work ## Space - Raise $100K for Jane's April taxes ### Agents' plan - Trim the S&P 500 index fund $4,500 - **Total** $4,400 ## Chat ### 00:09:23 # Agents do the work and pull people in ### Financial Planning Interface - **Space: Raise $100K for Jane's April taxes** - **Agents' plan:** ### 00:09:50 # Agents watch the world, so people don't have to ### Wake on an event ```python notify_me(when="Jane responds to this email thread") ``` ## Inside Arca's long-horizon agents that run the business Aman Singh / Lead AI Engineer ARCA ### 00:10:23 # Work happens in unpredictable ways Jane never emails us back ### 00:10:52 # People's work is a signal, too ## Client Profile - **Jane Whitaker** - Client since 2019 ### Notes - **Dana Lee, advisor** ### 00:11:24 # Agents communicate with each other - **Background agent** - working on a new note - Dana Lee, advisor - Note on Jane's record, Thu ### 00:11:48 # Primitives for long-horizon work - People - Arca agents ### 00:12:25 # Primitives for long-horizon work - **People**: Stay aware of what's happening - **Arca agents**: **Signals** (Every email, call, edit and event) ### 00:12:50 # Simple idea, emergent complexity ## Signals (134 fired) - Reminder due (Whitaker) - Advisor note (Nguyen) - Market move (S&P 500) - Form signed (Chen) - Meeting booked (Okator) - Email (Okator) ## Agents (6 working) ## People (8 open) - **Dana Lee** Advisor - Call the Okafor's - Review Chen tax plan - Review Kim RMD plan - Approve Jane's email - **Marcus Hill** Advisor - Approve Nguyen email - Review Q1 estimates - Review Alvarez plan - Approve call notes - **Peter** Portfolio Mgmt --- ### Closing every context gap Agents stay aware of every piece of work, wherever it happens. ### Routing tasks precisely The right work to the right person, at the right time. ### Holding state over long horizons Persistence and memory that keep work in flight for days or weeks. --- ### Inside Arca's long-horizon agents that run the business Aman Singh / Lead AI Engineer ARCA [Screenshot of a dashboard showing "Signals" as a list of events, "Agents" as a network diagram of interconnected circles, and "People" as a list of advisors with their tasks, some completed and some pending.] ### 00:13:23 # Simple idea, emergent complexity ## Signals (320 fired) - Meeting booked - Nguyen - Email - Kim - Reminder due - Patel - Meeting booked - Whitaker - ### 00:13:49 ## So what does this unlock? ### Inside Arca's long-horizon agents that run the business Aman Singh / Lead AI Engineer ARCA ### 00:14:23 # Agents drive the firm's work ## Tasks Prepared by agents - **Approve the Kims' first RMD** He turned 73 last year, so the ### 00:14:51 # Inside Arca's long-horizon agents that run the business ## What if Jane never had to ask? **Message from Jane Whitaker to her Arca advisor** Mon, 9 ### 00:15:23 # A new business goal: proactivity - Every January, prepare each client for tax season before anyone asks. ### Agent goals - Answer client emails within a day - Keep portfolios on target allocation - Raise cash before known withdrawals - **New goal**: Prepare every client for tax season each January Agents drive the goal ### 00:15:52 # A new business goal: proactivity Every January, prepare each client for tax season before anyone asks. ## Agent goals - Answer client emails within a day - Keep portfolios ### 00:16:19 # Thanks! (pssst, we're hiring) Aman, Lead AI engineer at Arca ### Inside Arca's long-horizon agents that run the business Aman Singh / Lead AI Engineer ARCA [QR code for @multivitamin] [ ### 00:16:51 ## AI Engineer # The Highest-Signal Technical AI Conferences AI Engineer hosts AI developer conferences around the world for engineers, breakout startup founders, and AI architects advancing AI engineering at the world's leading technology companies. --- ## Find Out What's Next Scan the QR code or visit [https://ai.engineer](https://ai.engineer) to subscribe to our newsletter and stay up to date with the latest news and events. [QR code linking to https://ai.engineer] ### 00:17:17 # AI Engineer Europe 2027 ## ExCeL London ### 02.17 - 02.19 2027 Europe's flagship technical AI conference returns to ExCeL London for three days, February 17-19, 2027 — bringing the world's leading AI labs, platforms, and tools to Europe's builders. [ai.engineer/europe](ai.engineer/europe) [Black and white photo of an ornate building in London] [Black and white photo of Big Ben and Westminster Bridge] [Black and white photo of the London Eye] ### 00:17:54 # PRESENTED BY ## arize View Full Schedule at [ai.engineer/nyc/2026/schedule](ai.engineer/nyc/2026/schedule) [Arize AI logo, a stylized pink caret symbol] [Abstract background with subtle light curved lines]