AMBR

Good morning, and welcome to Amber International second quarter 2026 financial results. At this time, all participants are in a listen-only mode. A question and answer session will follow the formal presentation. At that time, if you would like to ask a question, please press star one on your telephone keypad. As a reminder, this conference is being recorded. It is now my pleasure to introduce your host, AMBR's AI Ambassador, MIA. You may begin.

Good morning, and welcome to Amber International Holding Limited second quarter 2026 earnings conference call. I am MIA, Amber's official AI agent moderator for today's call. Before we begin, please note that today's discussion will contain forward-looking statements under the Private Securities Litigation Reform Act of 1995. These statements involve risks and uncertainties that could cause actual results to differ materially from those projected.

For a more detailed discussion of these risks, please refer to the company's filings with the U.S. Securities and Exchange Commission, including our most recent annual report on Form 20-F. Joining us on today's call are Michael Wu, Chairman of the Board and CEO. Vicky Wang, President. Yi Bao, Chief Operating Officer. Josephine Ngai, Chief Financial Officer, and Steve Zhang, Co-Chief Financial Officer. Following their remarks, we will open the line for Q&A. With that, let me now turn the call over to Michael Wu, our Chairman of the Board and CEO.

Thank you all for joining us. The second quarter was a strong one for AMBR, and I will start with the numbers. Revenue was $13.9 million, up 39% from the first quarter. Gross margin expanded to 79.5%. Operating income was $1 million, and adjusted EBITDA was $1.9 million, both turning positive from losses last quarter. The revenue from our agentic and digital asset businesses from Amber Premium came in at $10.1 million, above the $9 million-$10 million outlook we gave you last quarter.

Under our $50 million repurchase program, we bought back approximately 2.6 million ADS for about $5.8 million through June 30, with roughly $44.2 million remaining. Those are the results. Today, though, I want to explain why they matter, because they are the first evidence that our new strategy is already taking hold.

Two days ago in Hong Kong, we introduced AMBR for what it is today, a company that builds specialized AI agents. This is a pivot, and I would rather say that plainly than dress it up as continuity. We built AMBR as a digital wealth management business. Now we are becoming a technology company. We are making that choice deliberately and from a position of strength backed by the numbers I just shared because we believe this is where the greater opportunity lies. For me, this is also a return to my original passion and my true ambition. We started in 2017 as Amber AI and spent the first nine years in markets learning exactly where capable models stop being useful to people making consequential decisions. In June, I stepped down as CEO of Amber Group to run AMBR full-time.

Building these AI agents is the only thing I plan to work on for the next decade. I said that publicly on Monday, and I will repeat that today to this audience because you are the ones who can hold me up to it. The strategy already has two products in market. Ambre is our consumer agent for personal finance. It does what Amber Premium's relationship managers have done for high-net-worth clients. Portfolio analysis across accounts and asset classes, a daily signal feed filtered to what a user actually holds and actually what matters. Monitoring and alerts. Ambre makes that available far more broadly. The two design choices matter for this audience. First, Ambre works across users' existing exchange and brokerage accounts. We are not asking anyone to move assets to use it. Second, Ambre does not place orders autonomously. Not yet.

When a user decides to act, they are handed to our expert team. These were people who were relationship managers, structurers, and traders in our financial services business. We will expand the agent's authority as reliability is demonstrated, not ahead of it. Ambre opened Monday by invitation, beginning with Amber Premium's verified client base. MIA, your host today, is also our marketing agent, and it is the proof that this model produces real revenue.

MIA was built inside iClick and CMRS, our wholly owned marketing businesses, where it runs a substantial share of day-to-day campaign operations for a base of more than 100 enterprise customers. As of Monday, MIA is also available directly. There is a product, not just embedded in our services anymore. That is the pattern you should expect from us. Operate a business, convert its expertise into an AI agent, and then take that AI agent to market.

Now let's move to the P&L logic, because the repositioning is only credible if the numbers eventually say the same thing as a strategy. Of the $13.9 million I mentioned, $7.4 million came from businesses we classify as agentic, including $3.5 million from A-MM in its first quarter of recognition. That classification reflects how these businesses genuinely run.

Operations executed on AI agent infrastructure, not a relabeling of old revenue. Yi will take you through the basics and the details. The reason it matters: agentic solutions have structurally higher gross margin than the businesses it is replacing, and that mix shift is most of why gross margin reached 79.5% this quarter. On the rest of the portfolio, as we focus the company on building AI agents, we are reviewing the shape and ownership of parts of our legacy financial services business. Some of what we operate today fits the strategy as infrastructure.

Some might serve clients and shareholders better in a different structure. We have nothing to announce, and we won't speculate on outcomes. But I'd rather tell you the review exists than have you learn of any outcome. I also want to emphasize that Ambre and MIA are the first two AI agents, not the whole portfolio. At our inaugural Investor Day, which we now expect to hold before year-end, we'll show you what else we've been building and lay out the financial framework for the transition. What the revenue mix looks like as agentic businesses become the center of AMBR. Until then, our job is simple. Execute on what we just launched, build AI agents. Done. With that, I'll hand over to Yi Bao.

Thank you, Michael. The message from my side is simple. The agent strategy is already operating, not just announced. A-MM went from operating system to $3.5 million of recognized revenue in a single quarter. MIA runs a substantial share of day-to-day campaign operations for more than 100 enterprise customers. Ambre is built on workflows our team have run for years. We build agents on infrastructure we have already proven, which is why we can move quickly without taking on the risk of building from scratch. What I would like to do this morning is make the pivot concrete from the operating point of view. Michael described the pattern we follow, which is that we operate the business, we convert its expertise into an agent, and then we take that agent to market.

Almost all of the real work happens in that middle step, and it's where I think are the vantage seats. So that's where I will spend my time. Let me pick up where I left off last quarter. I described A3S and A-MM as agent-native operating systems. A few of you asked afterwards why we were leading with infrastructure rather than with the agents themselves. The short answer is that intelligence on its own doesn't make an agent useful.

An agent needs access to the right data, tools it can operate, workflow it can follow, permissions that spell out what it's allowed to touch, and controls around execution, monitoring, risk, and compliance. More than any of that, it needs a precise purpose. By which I mean a defined problem, a defined user, and a real situation where the outcome matters to somebody.

The model supplies the intelligence, the operating environment lets that intelligence act, and the purpose determines what the action is worth. That's also why we are not competing at the foundation model layer, and don't plan to. We stay model neutral and use whatever intelligence works best for a given job, whether it comes from a proprietary model or an open source one. It's worth thinking about what that means for how you read the model risk. Because when the models get more capable and cheaper, it works in our favor rather than against us. Our costs come down, and our agents get better without us spending a dollar on training.

What we intend to own is the layer sitting above the model, which is where you will find deep understanding of a particular vertical, the connections into the right tools and the data, the design of the workflow and its controls, and the fairly unglamorous work of making general intelligence reliable enough that someone will trust it with a real job. A-MM is the clearest example of how that plays out.

Market making has always grown on a fragmented set of workflows, with clients' requirements sitting in one system, venues and counterparties in another. RFQs, contracts, execution, monitoring, settlement, and the reporting each carry their own tools and their own manual steps. Our first move was not to put an AI interface in front of all that, because an interface on top of a broken process just gives you a faster route to the same bottleneck.

We standardized the underlying workflow first, then connected the systems, structured the data, put monitoring and controls around it, and make the process machine operable one step at a time. That is the layer we described to you last quarter as the A-MM operating system. In the second quarter, A-MM contributed roughly $3.5 million of revenue in its first quarter of recognition, and I want to be careful about how I characterize it. What it tells you is that the infrastructure underneath our agent strategy can already generate economic value.

That is a meaningful distinction because most companies in this field are still asking investors to fund an operating layer that does not exist yet. Ours is built, already running, and fits our definition of agentic revenue. The work runs on agent infrastructure rather than through the manual processes it replaced. The part I want to be careful about is what comes next.

That revenue today still mostly reflects monetization of the operating platform and the capabilities running on top of it, rather than the agents getting paid directly for delivering the outcome. Our expectation that the specialized agents gradually becomes the primary interface to that capability, and that the outcome itself becomes what the customer pays for.

Think of the progression as three stages, starting with the manual workflow, then agents' operable infrastructure, and eventually a specialized vertical agent that simply delivers the result. A-MM is in the middle stage today. We will tell you when it moves, and we will show you what we measured before we say it moved. The rest of the portfolio is being built the same way. MIA came out of a working marketing operation. We had learned from real companies and real enterprise customers long before we sold it to anyone.

Ambre is being built on years of operating experience at Amber Premium, drawing on portfolio analysis, risk monitoring, product evaluation, and the accumulated judgment of relationship managers, traders, structurers, and the product teams. In both cases, we started inside an environment we already understood well, converted that operating knowledge into structured workflows and systems, and then let agents take on more of the work as it earns the right.

That is also how I would ask you to think about our legacy business inside the new AMBR. The customer relationships, the domain expertise, the regulatory infrastructure, the execution connectivity, the operating data, and the risk and the compliance experience all stay valuable. Most of it will be hard for the newer entrants to assemble from scratch. What does not have to stay the same is the way we have traditionally delivered those capabilities.

A business that grows by adding relationship managers, operation staff, and the manuals that grows in a fairly straight line with headcounts, and that is a different economic shape from the company we intend to build over the next decade. You can already see the difference showing up in this quarter's gross margin. As Michael mentioned, we are reviewing well each legacy business and the structure fees. Some of those capabilities will end up as infrastructure or agent-dependent, and some delivery model will become their central over time. The pivot is changing how we run AMBR internally as well. We want to be the first serious use of everything we build. There is a practical reason for that, which is that running our own agents in our own workflow is the cheapest way to find out well they fail before a customer does.

It shows us where they come up short, where human judgment is still needed, what context or tooling they are missing, and how the workflow itself should be redesigned. We understand the workflow. We build the agent. We run it ourselves. We fix what breaks, and then we take it outside. That loop is our operating model, and it travels from one vertical to the next. So when you look at that $3.5 million from A-MM, I would ask you to read it as an early proof point rather than a destination. The operating system is the foundation.

The specialized agent is the product we are building towards, and the outcome is what the customer should eventually be paying for. We are still early in this transition, but we are not starting from zero. We are starting with business that operates users who use them, workflows that function, and the revenue that is already being recognized. The work in front of us now is turning those advantages into specialized agents and scaling the ones that prove they can deliver. With that, I will turn it over to Vicky.

Thank you, Yi. Earlier this week, on September 1st, we officially unveiled AMBR and introduced the next chapter of our company, focused on building specialized AI agents for high-value, high-stakes use cases. We have been very encouraged by the initial response. Since the launch of AMBR, we have seen strong interest from existing clients, prospective users, partners, and the broader markets.

While we are still at a very early stage, that response has reinforced our conviction that users are looking for something beyond another general-purpose AI interface. They want intelligence that understands their context, knows what matters to them, and can continuously help them to take action. This is where we believe AMBR has a differentiated foundation. The AMBR brand is new, but the capabilities behind it have been built over many years.

We bring deep domain expertise, trusted financial infrastructure, experience serving sophisticated users, and a detailed understanding of real-world high-stakes workflows. We believe these capabilities become increasingly valuable in an agentic AI world. Foundation models are becoming extremely powerful, but in our view, the most valuable specialist agents will require a deeper know-how of the underlying industry. This is where our domain expertise becomes particularly valuable.

Ambre, our flagship personal finance agent, is one of the first examples of how AMBR is combining frontier AI capabilities with deep financial expertise to build specialist agents. Over the years, we have built deep capabilities across digital wealth management, risk management, and financial infrastructure. Ambre brings these capabilities together in a much more scalable and intelligent form.

Rather than simply providing users with more information, Ambre is designed to understand their financial context, identify what matters most to them, and help turn their intentions into action. For example, Ambre can build a holistic view of a user's portfolio across different accounts and asset classes, identify concentration and correlation risks, surface the signals that are most relevant to their actual holdings, and continuously monitor specific conditions or tasks on their behalf. We launched the first version of Ambre on September 1st as well, and the early response from our existing clients, partners, and broader community has been very encouraging. This is still an early version, and we expect the product to evolve significantly as we validate user behavior and progressively unlock more agent capabilities.

Our long-term ambition is that Ambre make a level of personalized, always-on, professional financial intelligence that historically was only available through a high-touch private banking relationship, accessible to a much broader group of users. On the other hand, MIA solves the same shape of problems in a completely different market. Marketing teams run research in one tool, insight in another, content in a third, and distribution in a fourth, and nobody owns the seams between them. MIA is built to understand the objective and carry that workflow through end to end instead of handing it off four times. We sell it two ways now, embedded in the services our marketing businesses deliver and directly as a product. Having both gives us an unusually clear read on what a customer will pay for the agent on its own versus the services wrapped around it.

These two markets picked in the first batch have almost nothing in common. Personal finance and marketing operations share almost no customers, no regulations, and no workflows. If the same approach works in both, that is approach working and not luck. It is also how we will choose the third agent and the fourth. We go where we already operate, where the work is high stakes and fragmented, and where we hold context a newcomer would need years to assemble.

We are still at the beginning of this journey, and there is significant work ahead. But the launch of AMBR marks an important milestone for the company, and the early response we have seen has, again, strengthened our conviction in the direction we are taking. We look forward to sharing more as we expand the capabilities of Ambre and MIA and introduce additional specialized agents across AMBR platform. With that, I will turn it over to Josephine.

Thank you, Vicky, and good morning, everyone. Before I get into the numbers, let me start with the headline for the quarter. Revenue grew 39% essentially, and we moved from an operating loss of $3.2 million in Q1 to operating income of $1 million in Q2. Importantly, we did that while keeping operating expenses essentially flat at around $10 million. I think that's an important point for investors.

The strategy Michael Wu just described is not being driven by a significant increase in spending. What we are seeing instead is a change in the revenue mix, with higher-margin agentic revenue growing alongside continued improvement in our core business. Typically, when a company kind of repositioning, you would expect to see a higher cost base first and potentially a need for additional capital. So far, we are seeing the opposite.

We are growing revenue, improving margins, and moving into profitability without materially increasing expenses. That's the kind of financial discipline that we want to maintain as we execute this transition. Let me walk through the quarter in a little more detail. Starting with revenue, total revenue in Q2 was $13.9 million, up 38.8% from $10 million in Q1.

Beginning this quarter, we have reorganized how we present revenue into two categories, which we think better reflects how the business is evolving. The first is digital assets platform revenue, which was $6.6 million and includes wealth management, execution, and payment solutions. The second is agentic revenue, which was $7.4 million and reflects the initial contributions from A-MM, together with our marketing and enterprise solutions business. Within the digital assets platform, wealth management solutions generated $5.3 million, compared with $4.3 million last quarter.

That improvement was mainly driven by stronger demand for both our diversified products and several newly launched offerings. Agentic revenue was one of the key developments this quarter. A-MM contributed $3.5 million in its first quarter of revenue recognition, while marketing and enterprise solutions contributed $3.8 million. If you look at digital assets platform together with A-MM, revenue was $10.1 million.

That's slightly above the high end of the $9 million-$10 million outlook we previously communicated. Moving to gross profit, we saw a significant improvement. Gross profit increased to $11.1 million from $6.8 million in Q1, and gross margin expanded to 79.5% from 67.7%. The main driver here was the mix of the business. We are seeing a larger contribution from higher-margin activities, particularly A-MM and our core wealth management business. From our perspective, it's not just the revenue growth that's encouraging.

The quality of that revenue is also improving. On operating expenses, we remained at approximately $10 million, essentially flat with the prior quarter. That is particularly important given the growth we delivered during the quarter. We are starting to see the operating leverage we believe can come from deeper AI integrations across the business.

As a result, operating income was $1 million for the quarter, compared with an operating loss of $3.2 million in Q1. Looking at the bottom line, net income from continuing operations was $1.5 million, compared with a net loss of $3.7 million last quarter. Adjusted EBITDA from continuing operations improved to positive $1.9 million from -$3.2 million in Q1, and adjusted net income was $1.5 million. Turning briefly to the balance sheet, as of June 30, we had $34.2 million in cash equivalents, term deposits, and restricted cash.

Let me also address our outlook, because I know this will be an important question for investors. As Michael discussed, the company is going through a meaningful strategic transition toward becoming an agentic AI company. Given that transition, we do not believe our previously issued financial guidance is still the right framework for evaluating the company's future performance. We have therefore decided to withdraw that guidance while we build more operating history around these few new businesses and get better visibility into their financial contribution.

Once we have enough data and forecasting visibility, we intend to provide updated guidance. I want to emphasize that withdrawing the guidance does not change our confidence in the long-term opportunity. It is really about making sure that when we give investors a forward-looking framework, it is based on the business we are building now rather than the business we had before this transition.

Stepping back, I think Q2 gives you more early but meaningful evidence of what this new model can look like. Revenue growth, expenses stayed essentially flat, gross margin expanded significantly, and we moved from an operating loss to operating profit. For us, that is the pattern we want to continue seeing as we move toward a more agent-native, higher-margin business model. We are still early in this transition, and there is a lot of work ahead, but we are encouraged by the progress we are seeing, and we will continue to stay focused on disciplined execution and long-term value creation. With that, I will turn the call back to MIA. Thank you.

Thank you, Josephine. That concludes our remarks for today. We will now open the line for Q&A. Operator, please begin.

Thank you. As a reminder, if you'd like to join the question queue, please press star one on your telephone keypad. A confirmation tone will indicate your line is in the question queue. You may press star two if you'd like to remove your question from the queue. For participants using speaker equipment, it may be necessary to pick up your handset before pressing the star keys. We'll pause a moment to allow for questions. Once again, sorry, go ahead.

Yeah. I see some questions on screen. First question, what is proprietary about your AI agent, about AMBR's AI agent? This is actually a really good question, and I'd like to share with the audience our own AMBR's definition of what is even an AI agent. I think the industry sort of comes together to a definition for AI agent. This concept or this whole species is still fairly new in human history. The industry sort of defines AI agents as the model plus the harness. We do believe that definition is incomplete. Our AMBR's definition for AI agent is an agent is the model plus the harness plus the purpose. I think that will lead us back to the original question. Why do we believe that way?

Because the model is the intelligence, and that intelligence is increasing day by day as the model labs compete for better and better models of all sorts, proprietary or open source. Harness, fairly new concept, essentially means the environment or the tools or setup for that intelligence to do actual work. Best example is coding agents. The harness allows the model to code and write programs for programmers or even not programmers.

We call them vibe coders. We do think, like also Yi Bao said earlier in his remarks, the purpose is what makes that action from the model valuable to someone. The purpose is essentially what the model is doing for who, in what scenario, and why. If the model, highly intelligent and increasingly intelligent, acts without the purpose, it's unclear why the customers should pay for that, because it's unclear what the value the customer receives.

Now, circling back to the original question, what is proprietary about AMBR's AI agents? I do think in the areas we started, Amber with wealth management, MIA with marketing, we understand the purpose, or at least we understand the purpose very well for the customers the original business have been serving for years, for many years. We understand what exactly they need, what are their demands, what are their pain points, and how they like to have these services delivered, how they like to have their problems solved.

That is proprietary because any other company with the same model or even the labs that created the model does not have that unless they have done years of servicing these customers like we did. Take a step back to harness. Nowadays, just like the models, you have increasingly an open-source culture around both the model and the harness.

You now have a lot of great open-source models, essentially free to use, free to deploy locally by AMBR or other companies. You now also have a lot of open-source harness. In fact, some of the most popular personal general agent harness, like the likes of Hermes Agent, OpenClaw, Tai agent, they are all open source, which means anyone, including AMBR, can use them, fine-tune them, review them according to our needs. Now, because we have, again, very deep understanding about the purpose, Ambre, we understand how these clients like to be serviced around their money, around their wealth management. MIA, we understand how these companies like to be serviced with their marketing.

We can then build harness that are special, that are proprietary to these clients, to these purpose, and provide them value in the ways they want, in the ways they actually find valuable, because the ones who pay, I believe, defines what is valuable. Also, a lot of our harness are also proprietary because they come from the system that has been running, battle-tested, servicing these clients for years. You cannot build these programs, and a lot of these are now LLM-included old-school programs. You cannot build these programs. You can vibe code them. They are not battle-tested. They are not the way clients have been serviced or like to be serviced.

Back to the original answer, I think, actually, other than the model, both the harness and the purpose are not only proprietary to the AMBR agents like Ambre and MIA, they are unique with moat that was built over years of servicing these real clients to perhaps one of the highest standards in the industry. I hope that answers the question, and I also hope that provides a bit more insights on how we understand building AI agents, given the field is so new. I do think as a public company doing that, we have sort of a responsibility educating the audience or even potentially, sort of sharing what we know about what building AI agents even means.

Operator, can we take questions on the line?

Once again, if you'd like to ask a question via the phone, please press star one on your telephone keypad. Were there any other web questions?

We'll take another question from the web. It's a fun one, and I think it can hopefully be insightful for the audience, too. The question reads, if investors give your one largest competitors $50 million tomorrow, what stops them from building Ambre and MIA? This is a great question because the answer is both simple, and I think, again, comes to how we understand about building AI agents. Frankly, the ones who can build, theoretically, Ambre and MIA, they do not need that $50 million. They are potentially the labs or the large internet companies that are already building models and the general agents. They do not need that $50 million tomorrow to build those. But why are they not building Ambre and MIA? Because that's not their focus. They're fighting different battles. They're trying to build the better model. They're competing very hard. They're best people.

Their billions or hundreds of billions of dollars are spent winning the model war, not winning the vertical agent war we are fighting. On the other hand, if you give $50 million to a competitor that wants to build Ambre and MIA tomorrow, also doesn't help that hypothetical competitor. Because first, they are unlikely to understand the purpose we do. And even if they do, they're in the same industry. They are unlikely to have built their harness the way that's agentic or principle, as we have done with the A-MM and with the harness around MIA, the harness around Ambre. Last but not least, I think likely they will be building their version of Ambre and MIA for the wrong purpose, and that matters.

Likely they will try to add an AI bot onto whatever they were selling, and that's not going to be the right purpose of servicing the users, the customers, like what Ambre and MIA are doing with our customers. So I think this is a great question. I actually think this $50 million doesn't help any hypothetical competitor of ours, because the ones who can do it, they don't need the $50 million, and they're not doing it, not for financial reasons. They're doing it because they're fighting different battles with their focus than us. And the ones who need $50 million, they probably cannot build what we built, or at least in a very, I think, extended period of time.

There are no phone questions at this time.

Okay. Then we will take one more web question. I do not want to be the only one talking from our team. We have very capable management, but I will start. Do you expect to take shares from existing competitors, or do you view the segment as open and untapped? This is a great question because I think it is a bit of both, and depends on the time horizon. The portion of where our growth or revenue come from essentially will differ. In the near term, take MIA as example. MIA is already making revenue from customers. Now, most of these customers probably do not care if they are serviced by MIA or iClick or another marketing company, maybe with or without AI. So in that sense, MIA is taking market shares from iClick competitors or even iClick itself.

Now, essentially, iClick is, you can think of it as a service arm or an additional layer on top of MIA. Now, at the same time, I do think customers being serviced directly by MIA are having a very different service experience. They essentially, and especially for a lot of smaller customers, this is essentially the first time they are being serviced and can afford to be serviced by a truly 24/7 complete marketing team. This is a clearly untapped market because these customers, their marketing needs existed before. A way for their marketing needs to be serviced this way did not exist before. Now, in the near term, I do think MIA or iClick and the CMRS with MIA behind is operating a lot better than many of its competitors, and it will take market share from competitors.

But over time, I think the most powerful thing to MIA's service model is will open up a lot of new customers that they did not think they can have this level of service. And same thing happens with Ambre. The level of services Amber Premium team provides to high net worth or billion-dollar family offices was not accessible by smaller investors or individuals in most of the time. It was just too expensive to do that. Now, not only that experience, that service can potentially be delivered better, they can be delivered in an affordable cost to a lot more customers. So back to that, before my teammates add more, I think over time it is a bit of both, but the later open market is a lot larger for us.

Thank you. That concludes today's conference. Sorry, that concludes the question and answer session. I'll turn the floor back to MIA for final comments.

Thank you all for joining us today. This quarter marked a clear step in Ambre's pivot from a digital wealth management business to a technology company that builds specialized AI agents. Ambre and MIA are the first two agents now in market, and the second quarter results are the first evidence that this direction is beginning to show through in the numbers. We sincerely appreciate your continued trust and support. We look forward to sharing more in the quarters ahead, including at our Investor Day, which we now expect to hold before year-end. This concludes today's call. Thank you and have a great day.

Thank you. This concludes today's conference call. You may disconnect your lines at this time. Thank you for your participation.

Good morning. Welcome to Amber International first quarter 2026 financial results. At this time, all participants are in a listen-only mode. A question-and-answer session will follow the formal presentation. If you would like to ask a question please press star one on your telephone keypad. As a reminder, this conference is being recorded. It is now my pleasure to introduce your host, MIA, Amber Premium official AgentFi Ambassador. MIA, you may begin.

Good morning, and welcome to Amber International Holding Limited's first quarter 2026 earnings call. I am MIA, Amber Premium's official AgentFi Ambassador, and your moderator today. Before we begin, please note that today's discussion may contain forward-looking statements within the meaning of U.S. federal securities laws. These statements involve risks and uncertainties that could cause actual results to differ materially. For a more detailed description of these and other risks and uncertainties, please refer to our filings with the Securities and Exchange Commission. Joining us on today's call are Michael Wu, Chairman of the Board and CEO, who will share a first quarter overview, strategic vision, and AI initiatives. Vicky Wang, President, who will focus on our core business updates, client platform performance, and future focuses. Yi Bao, Chief Product Officer, who will update us on our regulatory update and platform evolution.

Josephine Ngai, Chief Financial Officer, who will review our financial results and provide guidance, and Steve Zhang, Head of Capital Markets. Following their remarks, we will open the line for Q&A. With that, let me now turn the call over to Michael Wu, our Chairman of the Board and CEO.

Thank you, MIA, and thank you all for joining us today. The first quarter of 2026 was another temperate period for the crypto industry, continuing the downtrend we saw in the fourth quarter of 2025. Our total revenue for the quarter was $10 million compared to the $14.5 million in Q1 2025, and the $16.3 million last quarter. Despite the challenging environment, we see this as an opportunity to strengthen our foundation with clients and continuing advancing our strategic priorities. Our focus remains on how we serve our clients more efficiently and how we scale that capability through our agentic fintech capabilities. Through every cycle, what proves durable are Amber's most important assets, our ability to innovate, and our ability to build scalable, future-proof infrastructure. To that point, this quarter marks another step forward in the strategy we have been building towards.

As part of our broader agentic transformation, we introduced A-Suite as an agent-native operating system that abstracts the complexity of digital asset financial services, enabling them to be automated and operated by AI agents. This is similar to how AWS two decades ago abstracted the complexity of servers and enabled a whole generation of web apps to simply build on top. That is where finance is heading as the agentic economy arrives. Our vision is to be the foundational layer beneath it. We're moving from competing at the interface and the distribution layers to providing the rails for the agentic economy itself. This is not an aspiration. It is already on the way. Amber Premium has already proven itself as a strong distribution layer with established institutional relationships, a regulatory licensing footprint, and a demonstrated segment profitability as disclosed in our financial statements.

Building on that proven foundation, we are now creating the operating core beneath it. The greater efficiency and expanded addressable market unlocked by A-Suite are what will carry us towards the agentic future that I have always envisioned, spoken about, and built toward. This also marks the next step in how we define AMBR, not just as Amber Premium, the crypto platform anymore, but as Amber, a truly emerging agentic fintech. As I mentioned in previous earnings calls, Amber first began as Amber AI. The conviction that crypto and AI would converge to define the future of finance was not a strategy we adopted later, but rather it was a thesis we founded the company upon.

What you are seeing today, this quarter, across both our business and our innovation, is that this thesis is arriving in practice, and we intend to keep building it deliberately, one proven layer at a time. Building on Amber Premium's proven success, we launched the first of our three flagship agentic fintech operating systems within the A-Suite at the end of March. A-MM, which stands for Agentic Market Making, is an agent-native liquidity operating system for token projects and the designated market-making infrastructure. A-MM is designed to unify execution workflows, infrastructure, and transparency into a platform that can be orchestrated by agents with customized real-time performance and risk reporting and monitoring. We expect A-MM to begin contributing meaningful revenue in Q2, and then to scale from there.

It is the first of the three A-Suite products we plan to bring to market this year. Yi will elaborate further on A-MM and our A-Suite positioning later. Beyond A-Suite, we are also embedding AI agent capabilities directly into our existing operations across all of our businesses. Within our iClick digital marketing business, we're transitioning toward an agent first and agent-native operating model by integrating MIA, our first in-house AI agent, who is also our host today for the earnings call, into iClick's core workflows, decision-making processes, and service delivery. This goes way beyond just using AI as a tool. We are making autonomous agentic workflows a central driver of how we operate, and that is already improving efficiency and the scalability across the businesses. This is a practical execution of our broader AI agent-driven strategy.

As we continue building towards this vision, I'm also pleased to announce our Crypto for AI vision. Crypto for AI, or C4AI, as we call it, is our view that crypto will become the financial and economic infrastructure for the agentic economy. To that end, our inaugural C4AI Investor Day, planned for October, will be an important milestone where we'll share our progress and showcase a whole fleet of Amber agents with the market. One final point on capital allocation, because it reflects how we view our own valuation. We continue to repurchase shares opportunistically through Q1, and remain focused on returning capital to our shareholders. Under our $50 million share repurchase program announced in November 2025, we repurchased approximately 2 million ADSs during the period. As of March 31st, 2026, approximately $45.5 million remain available under the program.

We continue to have significant flexibility for opportunistic repurchases while investing for growth. Ultimately, Q1 reflected a deliberate strategic decision on our part. Our strategy is advancing, and we are using this period to redefine the scope of AMBR and position the company for the next phase of the agentic economy. With that, I will now turn the call over to Yi, our Chief Product Officer, for a deeper look at our product roadmap and the launch of Amber's first agent-native operating system, A-MM.

Thank you, Michael. Our platform innovation is a natural continuation of how we have always built and delivered financial products. From the start, Amber Premium operated primarily as a distribution layer, a UI-driven platform focused on user acquisition and onboarding. We are now evolving into a full stack agent-native organization with a particular emphasis on building the service layer underneath that distribution layer. This is a natural next step beyond traditional UI-centric thinking, where products were defined by features, buttons, and screens in apps, and by branches, license, and the relationship managers in finance to an operating system approach. In the agent economy, competition will no longer be about who has a better interface, but who can seamlessly convert client intents into execution, settlements, monitoring, compliance, and reporting through intelligent automated workflows.

A truly agent-native operating system can deliver personalized and optimize the service at a scale no standalone platform, manual process, or single-purpose application can match. This quarter, we took a significant step towards with the launch of A-MM, the first flagship component of our A-Suite. A-MM is an agent-native liquidity operation system and designated market-making infrastructure platform. Its core value lies in creating a unified platform layer that abstracts complex execution workflows, operational infrastructure, and transparency requirements into standardized modular components. For token projects, liquidity is critical to price discovery, trading experience, exchange relationships, investor confidence, and ecosystem credibility. Yet, designated market-making has historically been manual, bilateral, and trust-based. A-MM is designed to turn this process into an automated and structured operating workflow.

Projects can define key requirements such as targets, values, service duration, spread, uptime, depths, settlement preference, and capital needs, while the platform supports RFQ submission, quote review, order management, contract administration, performance monitoring, and reporting. This gives projects a clear way to express demand and market makers a standardized way to deliver, and Amber a controlled system of record for onboarding KYC documentation, contracts, fees, and service data. This allows us to participate in the token liquidity value chain in a more scalable, infrastructure-driven, and agile way. A-MM is designed with a clear division of labor alongside traditional market makers. It is not a replacement, but an infrastructure layer that enables greater efficiency, transparency, and scalability.

In being able to offer different execution models combined with real-time visibility via our performance dashboards, which is soon to be launched, we are already seeing strong early adoption and positive feedback from token projects in our soft launch phase. From a business perspective, A-MM not only strengthens our own execution capabilities, but also creates a scalable revenue architecture. Revenue can come from recurring service and platform fees, value expansion as clients add more centralized or decentralized markets, market maker participation, and potentially premium data and analytics over time. We anticipate A-MM will begin generating meaningful revenue in Q2 and over time to serve as one of the A-Suite operating systems we plan to launch this year. More importantly, A-MM reflects the broader strategic direction of Amber, moving from distribution to service, from interface to infrastructure, and from manual financial workflows to agent-native operating systems.

Complementing our product programs, we continue to strengthen our regulatory licensing footprint. We have been granted the VARA license in Dubai and are making steady progress on our virtual asset service provider application in Hong Kong. These efforts reflect our strategic allocation of resources to better serve growing institutional demands, supported by an increasingly visible regulatory framework, including Hong Kong's stablecoin regime and developments such as the U.S. CLARITY Act. A stronger regulatory foundation is essential to building a sustainable, high-quality business in this evolving industry. This combination of technological innovation and regulatory advancements marks the natural continuation of our journey, extending Amber from a distribution layer financial service platform into a fuller picture of agent-native operating systems for agent crypto fintech. Next, I will hand it over to Vicky for a detailed review of our Q1 business performance.

Thank you, Yi. Before deep diving into our AMBR platform business, I would like to first build on Michael and Yi's earlier comments around how we have successfully scaled Amber Premium over the years, and how we believe we are now entering the next phase of scalable growth. As Michael mentioned, Amber Premium has evolved into a highly scalable institutional distribution platform supported by long-standing client relationships, a regulated operating footprint, and demonstrated segment profitability, as reflected in our financial statements. Importantly, what we are building extends well beyond a single initiative. This quarter, we announced A-MM, which, as Michael mentioned earlier, we expect will contribute meaningfully in the coming quarters. More importantly, A-MM represents only the first of the three A-Suite operational cores we plan to introduce this year as we continue building the infrastructure layer for scalable institutional automation.

The same automation and infrastructure capabilities that power our market-making businesses can now be extended across a broader range of institutional financial products and services, creating a more scalable and higher-quality earnings profile over time. Turning back to our core business and Q1 performance. The first quarter of 2026 reflected a familiar market environment across digital assets, including softer trading activity, lower risk appetite, and more selective institutional capital deployment. These broader market conditions were naturally reflected in our quarterly financial performance, particularly within our execution solutions and payment solution businesses. What continues to evolve meaningfully is the expansion of the digital asset opportunity set. We are no longer only seeing institutional interest around core crypto assets. Increasingly, we are seeing demand broaden towards tokenized financial products, on-chain yield strategies, tokenized real-world assets, and a wider range of digitally native financial products.

Alongside the trends, we are also seeing growing client appetite for more sophisticated and tailored structured products. Clients today are increasingly looking for customized yield opportunities, defined downside protection, and structure aligned with their specific risk-return objectives, rather than standardized off-the-shelf solutions. Our ability to offer customized structured products across different underlying assets, tenure, and payout profiles is a direct response to this evolving demand profile. Importantly, we believe this trend supports both deeper client engagement and a higher quality of revenue mix over time. As asset universe expands, we believe distribution becomes increasingly valuable. Institutions are looking not only for access to products, but also for trusted platforms that can help clients access and manage these opportunities within regulated frameworks.

This is where we believe Amber Premium is strategically well-positioned. At the same time, we are seeing increasing demand for financial institutions and platforms seeking embedded digital asset capabilities rather than building these capabilities internally. We believe this creates meaningful long-term B2B2C opportunities for us. Against this backdrop, our primary recurring revenue engine, wealth management solutions, contributed $4.3 million in Q1, accounting for 74.8% of Amber Premium segment revenue. This continues to reflect our intentional shift towards higher margin and more predictable revenue streams. To further strengthen our regulatory positioning, we also took proactive steps this quarter to optimize our client structure and align more closely with evolving regulatory requirements. As part of this process, we streamlined a portion of low-engagement clients' accounts while continuing to deepen relationships with our core institutional and focus client base.

Importantly, this optimization had minimal impact on overall asset on platform, where asset on platform per active client remains stable at $1.2 million. We believe this strengthens the long-term quality of the platform as the industry becomes more institutional. Ultimately, while market cycles may continue to impact short-term activity, we believe the long-term value of this platform lies in our client relationships, regulatory infrastructure, and ability to scale customized financial services through automation. In summary, Amber Premium is increasingly evolving from a client platform into an agent-native institutional layer for execution, coordination, and distribution of digital and tokenized assets. With that, I will hand over to Josephine, our Chief Financial Officer, for our financial results.

Thank you, Vicky, and good morning, everyone. I will now review our financial results for the first quarter of 2026 end March 21st and provide our guidance for the second quarter. Throughout my remarks, I will primarily reference the consolidated Amber International entity, providing additional context for the Amber Premium segment where relevant. Revenue for the first quarter was $10 million. This compares to $14.5 million in Q1 of 2025 and $16.3 million in the sequential fourth quarter of 2025. Our Q1 performance was primarily influenced by a materially softer digital assets market environment, which leads to a moderation in transactions volumes across the entire industry. Furthermore, our year-over-year comparisons was impacted by a non-recurring $2.9 million service fee that we recognized in the prior year period. Looking closer at Amber Premium, performance across our core solutions was quite balanced.

The wealth management solutions delivered $4.3 million. The execution solutions brought in $0.9 million. Payment solutions delivered $0.6 million, and iClick marketing and enterprise solutions contribute approximately $4.3 million. The gross profits for the quarter came in at $6.8 million, representing a 67.7% margin. This is a step down from the $12.1 million with gross profit and a 74.2% margins we recorded last quarter, reflecting shifts in our product mix as our new products represent a higher share of revenue this quarter. Despite these near-term shifts, we remain firmly focused on driving long-term, high-margin growth across all product lines. Moving down to the operating line, we record an operating loss of $3.2 million for Q1. Our total operating expenses improved to approximately $10 million, down from $11 million in Q4 2025.

This reduction highlights our strategic efforts to streamline operational resources alongside early efficiency gains from our internal AI initiatives. I want to highlight an encouraging case here. Within our iClick marketing and enterprise solutions business, we deployed our AI agent, MIA, into the operation. These integrations helped reduce operating costs within that segment meaningfully this quarter alone as we are transitioning the digital marketing business toward an AI-driven operating model. The key takeaway for us is straightforward. AI is not just a forward-looking thesis for us. It is already actively absorbing operating expenses and improving the unit economics of our existing business. We expect this internal AI efficiency to continue compounding throughout 2026 as we extend MIA's capability to additional corporate functions. The net loss from continuing operations was $3.7 million, compared to a net income of $0.8 million last quarter.

Adjusted EBITDA for Q1 was a loss of $3.2 million, compared to a positive adjusted EBITDA of $50,000 in Q4 2025. Turning to the balance sheet, our financial positions remain strong and continues to improve. We closed the quarter with $36.5 million in cash and zero bank debt, giving us a highly resilient foundation. Looking ahead to the second quarter of 2026, we are issuing preliminary revenue guidelines for the Amber Premium segments of between $9 million-$10 million, representing a quarter-over-quarter increase of approximately 58.1%-75.7% from our Q1 2026 Amber Premium segments revenue of $5.7 million. Our guidance currently covers the Amber Premium segments only and does not include revenue from our iClick marketing and enterprise solutions to be consistent with peer risk guidance practice.

As we look to the rest of the year, alongside the external growth strategic we have previously outlined, internally, we are also enhancing our financial reporting system to provide transparent insight into our performance and maintaining strong liquidity and balance sheet flexibility in order to support our global expansions and strategic partnerships. We believe that this disciplined approach will create sustainable and long-term value for our shareholders. With that, I will turn the call back to MIA. Thank you.

Thank you, Josephine. That concludes our remarks for today. We will now open the line for Q&A. Operator, please begin.

Thank you. If you would like to ask a question please press star one on your telephone keypad. A confirmation tone will indicate your line is in the question queue. You may press star two if you would like to remove your line from the question queue. For participants using speaker speaker equipment it may be necessary to pick up your handset before pressing the star keys. Our first question comes from Brian Dobson with Clear Street. Please proceed.

Yeah, thanks very much. If we could just start with a big picture question. I suppose, two years from now, what do you think the business looks like, and how do you think investors should be contemplating your growth outlook at this point?

Thank you, Brian. This is actually a great question because fundamentally, I think starting from this quarter, we want the market, we want the investor to understand Amber International is truly emerging from the platform, Amber Premium, which is by itself a very solid, profitable digital wealth management platform to Amber International, which I define as a crypto-enabled agentic fintech. Two years from now on what the business should look like, I do think the agent-native operating systems we are launching today, the A-MM and the remaining A-Suite, and the agents that are operating them as of today, they will become a financial infrastructure for a lot more companies. They will hopefully, by that point, become the financial stack for the agentic economy.

How that will make our revenue model look like, I do think we have proven with our own platforms, with Amber Premium, that a already automated, already agent-native operating system can enable businesses in a scalable way. Two years from now on, I think that scalability point should have been proven by that point. There should be a lot of platforms, other than Amber Premium, a lot of platforms either owned, invested by Amber, or completely unrelated to Amber on an ownership basis, that are operating on this shared stack that we're building today. Yeah. I'm highly confident in the direction we are going. I'm highly confident in delivering or accomplishing that in a two-year framework. I do think the market will gradually understand Amber as an emerging crypto-enabled agentic fintech, as I mentioned.

Circling back to our Crypto for AI vision, I do think being crypto-enabled as an agentic fintech gives us a unique edge if we look a bit further into the future. I do believe a lot of financial services today will move onto the crypto rail, especially as the agentic economy arrives, as more of the services, more of the operations, more of the economy is done by AI agents rather than humans. Hopefully by that point, market will realize we not only have that vision way ahead of the curve, we are one of the first to actually deliver that vision.

Yeah. Thanks. I suppose just following up on that, do you think that leaning into that aspect of the business makes the overall business model more scalable as you're driving more agent-native systems, kind of similar to more like a software company?

There are similarities, I think, to software companies in the sense that, most of the company, as I always mention today, are engineers at the core. Amber International as a core is a technology-driven company. I do think the business model will look different from the software companies or especially the SaaS companies as we understand today. I don't think we are offering just a software, a tool, or an agentic tool even. What we are building, and we are increasingly offering to our own platforms and externally, is really more of an agentic capabilities. Take iClick as example, as we mentioned today. iClick was and maybe at this point still is a digital marketing business.

What MIA does and what our agentic staff does to iClick is offer the ability to offer the same services or even much better services to their clients with a much more agent-native way. In terms of operation, most of the operations now are being automated. The way the workflow, they are streamlined, it's agent first rather than human first. The ability itself, again, back to scalability point, is highly scalable. A different company or even a company with only similar business or different client base or similar client base can easily render the ability compared to the software example you mentioned, right? Today, if another company uses a software from a software company, they still need to use the tool themselves. They still need to have staff trained to operate with their own workflow using that tool. The agentic services, the agentic abilities we are offering is different.

It's actually end-to-end. It's actually result-driven. We do think companies will start to get used to paying for the actual results rather than paying for the tools that can hopefully get them the results. I think that's fundamentally different. I think the market will start to realize that. A lot of that understanding, I think, is becoming more talked about among the private investors, among the VC investors. Really in the public market, I do think Amber is one of the first companies that through our results, through our accomplishments this year, hopefully will also educate the public market investors about this new business model.

Yeah, excellent. Thanks very much.

Thank you.

Our next question is from Emily Wei with Symmetry Affluent. Please proceed.

Hello, management. I have two questions. Hello, management. Can you hear me?

Yes. Hi, Emily.

Hello. I actually have two questions. First of all, can you help us understand why we are pivoting towards an AI story? Secondly, on A-MM, what has actually been delivered so far, and when do we expect the A-Suite to start making money? Thank you.

Great questions. This is Michael again. First, I have to correct you. We are not pivoting to AI. First, Amber started as Amber AI. It is actually always been our DNA. Secondly, I have had this conviction, and I really think the company is putting that into reality as we speak, that crypto and AI are convergent. These two technologies well together define what the agentic economy looks like, especially in what I call agentic finance. Also this is already happening, as I mentioned about the MIA inside the iClick example. This is already transforming operating expenses through automation. It is already changing workflows from humans using tools to agents leading towards direct results with humans in the loop. It is already making a financial impact, and I think that is sort of related to your second question, which I will also get to.

If you look at Amber Premium itself, we really see Amber Premium as the proof case. It is a proof case because it is successful, right? It has a very strong reputation among, I think, the most highly demanding, highly sophisticated, and high valuable client base. It is a profitable business. We are just reviewing within Amber what enables this success of Amber Premium beyond, of course, our great sales team, our great relationship management team, and all the trust our clients putting into us. It's actually this operating layer, which now we are reviewing as A-Suite. It's actually this operating layer and this agent-native operating capability that makes Amber Premium, makes our platform successful, makes us able to deliver a very diverse priority of products and services within crypto.

The ability to deliver that not only to the highest standard, but deliver that with efficiency, with scalability. I really don't think we're talking about pivot. AI and the crypto has been in Amber's DNA since day one. I do understand why you ask this question or where does this confusion come from. I think over the last year or so, we are a new public company, and throughout most of 2025, people were still trying to understand Amber Premium itself, which again, is our first showcase, our first success. This year, of course, we are all on this call with all the investors, with all the friends, trying to educate the market about the broader Amber, which hopefully, starting from this earnings call, become more clear. To the second of your question about when does A-MM start to contribute revenues? It's actually already started.

As we mentioned, A-MM was launched at the end of March. It's an agent-native liquidity provision OS, operating systems. As Yi explained about the product, we really abstracted a fairly complex business into a very streamlined protocol. This protocol itself is agent-native, it's agent operable, and it's highly automated. Along with the workflow agents that operate A-MM, they've already been contributing revenue as we speak today. I do think we will start to see these increasingly significant revenue contribution from A-MM and the other A-suites as we launch them from the second quarter onwards.

Yep.

Thank you.

Thanks so much. I can add some points on Michael. Basically, as Michael has mentioned, the A-MM, actually, it adds extra scalable revenue streams to our future developments. Basically, I just want to make a similar analysis. Once the token projects or market makers onboarded to our Agentic Market Making or the platform, actually, they will be very sticky, and something like a middle to long-term agreement they will sign with us. Basically, the revenue itself will be recurring and scalable as they adding more values or maybe they adding more parameters, or they require more data service from our side. Basically, we do think that this revenue stream will be extremely scalable and start to contributing meaningful revenue from Q2 and onwards. Thank you.

There are no further phone questions. I would like to hand it back over to management for webcast questions.

Okay. Yeah, we have a few questions on the screen. I will read one of them out first. The question is, how do you expect AI strategy to influence margins, cash flow, balance sheet efficiency over time? Again, I think we touched upon some of that. The AI strategy is already influencing pretty much all of them, on cash flow, on expenses. As we mentioned with iClick example, MIA is already reducing OpEx of the iClick business segment as we speak. In terms of margin, A-MM is another good example. It used to be fairly bespoken kind of a business model of liquidity provision in crypto, in digital assets, into highly streamlined agent operable operating systems. That definitely increases not only the margin on the business, but also, again, how scalable the business can be.

In terms of balance sheet efficiency, I think that will also show the impact over time, especially as we launch the other two products within A-Suite in the coming months.

Yeah. Just to add to that point, I think compared to current margins, we do expect, obviously, higher capital efficiency coming out of the agentic AI services, and will have a positive impact on operating margins in the long run. Given that this is a relatively scalable business, the balance sheet efficiency will also start to improve in the coming quarters.

We also have another question that's from Kelly. The question is, what LLM is being deployed to enable the AI solution for Amber? Are there any proprietary components to your agentic infrastructure? This is very interesting to have a more technical question on this earnings call. In short, the way we build what we call the intelligence layer of our agentic stack is we are very open to use whatever LLM model or whatever intelligence source that's actually helpful, that's productive, that actually enables our business and our clients' businesses to be better. We, of course, have integrated either both the leading private models and the leading open source models. We have also in-house deployed our fine-tuned versions of open source models where it fits both.

There are, of course, areas within our agentic workflows that are smaller, maybe less intelligent, but cheaper and more customizable open source models are suitable. We have done that. In a way, we have our own fine-tuned smaller models, I guess, in the workflow. Are there proprietary components to the agentic infrastructure? This is also a very interesting question. I think we touched upon the models, the intelligence layer, right? I do think there are companies, there are gigantic AI labs that provide all these intelligence layers, and I don't think it is Amber's position today, at least to compete on that front.

I do think in terms of building more vertical agentic services or vertical agentic service stacks, that's where our edge lies, whether specifically in fintech or in financial services, especially digital asset financial services, which I think are actually more complex, but also more digital native form of financial services. There's a lot of harness you need to build. There's a lot of sort of specified datasets that our agents need to be comfortable with or be trained with. The short answer is yes. I do think there are a lot of proprietary components to our agentic infrastructure, even though that on the intelligence layer, we integrate most of the advanced, either private or open source models.

Thank you all for joining us today. This quarter marks a defining moment as we continue to advance our agent-native operating system build-out while maintaining a resilient foundation in a challenging market. We remain fully committed to delivering institutional-grade excellence and long-term value for our shareholders. We sincerely appreciate your continued trust and support, and we look forward to sharing further updates with you in the upcoming quarter. This concludes today's call. Thank you and have a great day.

Thank you. You may now disconnect.

Good morning, and welcome to Amber International Fiscal Year 2025 financial results. At this time, all participants are in a listen-only mode. A question and answer session will follow the formal presentation. If anyone should require operator assistance during the call, please press star zero on your telephone keypad. As a reminder, this conference is being recorded. It is now my pleasure to introduce your host, MIA, Amber Premium's official AgentFi ambassador. MIA, you may begin.

Good morning, and welcome to Amber International Holding Limited's fourth quarter and full year 2025 earnings call. I am MIA, Amber Premium's official AgentFi ambassador and your moderator today. Before we begin, please note that today's discussion may contain forward-looking statements within the meaning of U.S. Federal Securities laws. These statements involve risks and uncertainties that could cause actual results to differ materially. For a more detailed description of these and other risks and uncertainties, please refer to our filings with the Securities and Exchange Commission. Joining us on today's call are Michael Wu, Chairman of the Board and Chief Executive Officer, who will share our full-year overview, strategic vision, and AI initiatives. Vicky Wang, President, who will focus on our core business updates, client platform performance, and future focuses. Yi Bao, Chief Product Officer, who will update us on our regulatory update and platform evolution.

Josephine Ngai, Chief Financial Officer, who will review our financial results and provide guidance, and Steve Zhang, our Head of Capital Markets. Following their remarks, we will open the line for Q&A. With that, let me now turn the call over to Michael Wu, our Chairman of the Board and Chief Executive Officer.

Thank you, MIA, and thank you all for joining us today. The full year 2025 marked a pivotal chapter for Amber International, a year in which we proved the durability and the scalability of our business model against a challenging macroeconomic backdrop. First, I want to address the broader macroeconomic landscape and what we have achieved amid this environment. We clearly acknowledge the industry headwinds. The total market cap of crypto decreased by approximately 25% in the fourth quarter alone, cooling to approximately $3 trillion by year-end, after briefly approaching $4 trillion in October. However, we are highly encouraged by the financial resilience of our business has demonstrated despite this volatility. We generated $66.1 million in full year 2025 revenue.

Our Amber Premium segment generated $50.2 million in revenue, has successfully achieved our annual segment revenue guidance. This also represents a 572.1% increase compared to the $7.5 million Amber Premium segment revenue in 2024. In Q4 alone, we recorded $16.3 million in consolidated revenue, maintaining a stable quarter-over-quarter top line despite the broader crypto market suffering a significant contraction during the same period. This is a definitive validation of our resilient institutionalized platform. On an adjusted EBITDA basis, we achieved positive $4.7 million for the full year, which was a swing of $9.9 million from the $5.2 million loss in 2024. Amber International improved profitability against a challenging market backdrop.

That is the financial story of 2025. Our financial results demonstrate the strength of our core. Amber Premium is Asia's leading digital wealth management platform. It serves the region's most sophisticated clients with a private banking experience built on technology and unmatched access to digital asset opportunities. This business has proven to be profitable, resilient, and scalable, and it continues to set the foundation for our long-term strategy. On business development side, I'm proud to share a major regulatory milestone. Our Dubai subsidiary, Amber Premium FZE, received a Virtual Asset Service Provider license from VARA on April 2nd, 2026, which formally authorized it to offer regulated virtual asset broker-dealer, asset management, investment, borrow and lending services to institutional and qualified investors in and from the Emirate of Dubai and the broader United Arab Emirates. Built upon this progress, we continue to actively advance our licensing efforts in Hong Kong.

Yi will elaborate further on this achievement later. Turning to our long-term vision and initiatives. As many of you may know, Amber's roots in AI date back to our founding days as Amber AI in 2017. We believe the convergence of crypto and AI to transformative technologies of our time will fundamentally reshape finance, not only for humans, but also for the numerous AI agents that are arriving. In this emerging AI agent economy, digital assets become the economic and financial rails, and the financial services evolve from platforms into agent-native operating systems. My ambition as Amber's founder Chief Executive Officer is not to add AI onto yesterday's products. It is rather to build the financial stack for what comes next.

For that, we are actively developing a product suite called the A-Suite, which is a cohesive architecture of three AI-native operating systems that will not only power businesses like Amber Premium, but are engineered to intelligently coordinate liquidity, asset management, and asset distribution at scale. In Q1 2026, we'll officially announce the first of these three operating systems, which will be an AI-native autonomous workflow engine for digital asset liquidity management. Over time, we anticipate this suite, the A-Suite, will unlock new scalable revenue streams and significantly enhance our operating leverage in the quarters that will follow its launch. We are also executing a comprehensive AI rollout within our businesses today. We have begun integrating MIA, our first in-house developed AI agent, and also your host today, into our marketing and enterprise solution segment, or what was known externally as our iClick business.

Externally, MIA manages content generation, social media consistency, and investor engagement. Internally, MIA has lived in our Slack workspace as a proactive teammate, accelerating workflows via a proprietary skill hub, and secure internal database. These are much more than just productivity gains or cost-cutting initiatives. We want to use MIA's AI rollout success on iClick as a proof case that our in-house technology and innovation abilities can fundamentally upgrade traditional businesses, improve client experience, reduce unit cost, and sharpen our competitive edge in ways that cannot easily be replicated. Finally, as part of our commitment to maximizing shareholder value, our board authorized the purchase of up to $50 million of eight of our Amber ADS over a 12-month period commencing December 1st, 2025. Our approach is disciplined, measured, and also opportunistic.

We try to balance shareholder returns with capital requirements for A-Suite development and a platform expansion. I'm pleased to report that during fiscal year 2025, the company repurchased 516,703 ADS under the program, and approximately $49.1 million remain available for future purchases, providing significant capacity for opportunistic repurchases alongside continued growth investments. We're committed to executing our transition toward higher-margin, predictable platform revenue, and in the long term, building the financial stack for this AI agent economy. We believe our capital allocation strategy, including the repurchase program, reflects that long-term commitment. 2025 was a year that validated our strategy through the success case of Amber Premium. 2026 is the year we scale it and propel forward with both technology and innovations. Thank you. I will now pass to Vicky.

Thank you, Michael. 2025 marked a year of strong and profitable growth for our core business. As Michael highlighted, we remain resilient despite a major correction in the broader crypto market in Q4. Let me frame our performance through the lens of platform economics, as its measures really highlight what's driving the value we are creating. First, our primary recurring revenue engine, Wealth Management Solutions, delivered $34.9 million for the full year. This is a massive 463.6% increase from the $6.2 million we generated in 2024. Second, Wealth Management now contributes a major part, around 69.5%, of our total Amber Premium segment revenue. We believe this gives Amber a recurring revenue mix that is truly differentiated among digital asset platforms. Third, our unit economics have undergone a meaningful step change.

Our platform growth margin reached 74.8% in 2025, up from just 33.4% a year ago. That is an expansion of over 4,100 basis points, meaning our profitability profile is now approaching that of an institutional-grade wealth management platform. The ultimate proof of our differentiated positioning is our client profile. Our asset on platform per active client end of the year at $1.3 million. We compare that to the $5,000-$10,000 range commonly cited for typical retail crypto exchanges based on publicly available industry data. The contrast is clear. We are building an institutional-grade platform serving a growing long-term wealth allocation into crypto. We observe across industry, Q4 2025 reflected lower digital asset prices, softer sentiment, and a 25% broader market contraction in crypto market capitalization.

Coming off a record Q3, that shift was mathematically pronounced in our headline dollar amounts. The most important client story of Q4 is not what our asset on platform number looked like on December 31st. It is what our clients did during this correction. They stayed. Well, total platform asset ended the year at $1.3 billion, down from our Q3 peak at $1.8 billion. This was primarily a mark-to-market reflection of digital asset price decline. Underneath the headline, the engagement picture is steady. Active clients held at 988, essentially flat year-over-year across our in-institution and high net worth base. In the quarter where market test conviction, our platform retained its clients and kept them active, evidenced by the relations we are building are durable through cycles.

As we navigate involving market conditions in coming quarters, our high-value engaged client base provides a strong foundation for us to continue optimizing the business with a long-term focus. As we look to 2026, we're accelerating our growth through three definitive strategies. First, product innovation. We continue to expand our institutional suite with advanced offerings such as crypto-native FCNs, on-chain commodities, and quantitative strategies while exploring tokenized traditional assets. This expands the range of solutions available to our clients, allowing them to allocate capital more actively across a broader set of investment opportunities on our platform. At the same time, our payment solution business grew 325% year-over-year in 2025, reflecting increasing client engagement and more frequent capital movement on platform.

Together, these capabilities enable us to capture a greater share of client wallet, while positioning us to meet accelerating demand for regulated institutional-grade access to on-chain assets. Second, OTC market share and margin expansion. As one of Asia's longest-running institutional OTC desks, our execution reliability represents a difficult-to-replicate moat. In 2026, we are focused on automating workflows and enhancing pricing precision to improve competitiveness, reduce latency, and capture a larger share of institutional flow, driving margin expansion in our execution solution segment through higher volumes and greater operation efficiency. Third, geographical expansion. Our newly secured VARA VASP license marks an important milestone, unlocking access to the UAE, a key and rapidly growing hub for private and institutional wealth. Yi Bao will elaborate further on our broader regulatory moat shortly.

Ultimately, the combination of a broader product suite, a more automated execution engine, and expanded regulatory access positions us well for accelerated high-quality growth in 2026 and beyond. With that, I will hand over to our Chief Product Officer, Yi Bao.

Thank you, Vicky. I would like to update you on mainly two areas. First, our regulatory updates across our three licensed jurisdictions and the evolution of our platform and product suite. One of our defining themes of 2025 is our regulatory position, which is now a genuine competitive moat. In the fourth quarter of 2025, our Dubai subsidiary, Amber Premium FZE, successfully secured its in-principle approval from VARA. Today, I'm incredibly proud to announce that on April second, 2026, we officially received our VASP license. This formally authorized us to provide virtual assets broker-dealer, virtual assets management and investments, and virtual assets lending and borrowing service to institutional and qualified investors. By securing our license from VARA, Dubai's dedicated virtual assets regulator, we are strengthening our presence in the region's rapidly expanding digital assets ecosystem. The strategic magnitude of this license cannot be overstated.

Upon the SCA and VARA cooperation framework, this single approval further enables us to operate in and from the entire UAE, not just Dubai. This expands our access to one of the fastest-growing private wealth markets in the world. We are, of course, closely monitoring regional geopolitical developments. While the recent geopolitical tensions in the Middle East may introduce near-term complexities and impact the broader MENA markets, our long-term thesis remains completely unchanged. MENA remains a deeply strategic and a rapid growing market. To put opportunity in perspective, according to third-party industry research, the MENA wealth management sector is forecast to reach $1.4 trillion by 2031, with the estimated CAGR of 6.7%, driven by a combination of local wealth growth and intergenerational wealth transfer expected in the Middle East by 2030.

That concentration of wealth is precisely the client base our platform is built for. Since establishing our Dubai presence, we have engaged actively with local institutional prospects. Our VARA license, alongside our Singapore Major Payment Institution license and our ongoing efforts together with broader Amber Group to secure a Hong Kong VATP license, positions Amber Premium, in our view, as one of the few regulated pan-Asian digital asset wealth platforms serving its client base at institutional standards. This is what a regulatory mode looks like. On the platform and the product front, our starting points remains consistent. Crypto markets are structural cyclical, and our product roadmap is designed to serve clients through both down and up cycles. What changes each quarter is our ability to serve them better. In 2025, we made concrete programs across three areas. First, OTC platform integration.

Our institutional execution infrastructure was meaningfully upgraded, delivering tighter workflows and faster settlements for block trades. Second, AI copilot development. We have embedded AI capabilities directly into our OTC workflow, reducing manual processing time and improving trade execution analytics for our coverage team. Third, structured product expansion. We launched and scaled our crypto-denominated Fixed Coupon Note and accumulator, decumulator product suites, giving clients yield-generating structures that operates across market environments. Alongside these core upgrades, we successfully built the foundation for our real-world assets tokenization platform. By converting strong institutional inbound interest into an end-to-end internal solution from structuring to custody, we are now positioned to seamlessly integrate diversified yields from traditional assets directly into our clients' digital wealth portfolios. These improvements compound. A more capable platform with AI support allow our team to serve more clients without proportional headcount growth. This is a unique economics implementation.

Each product enhancements increases the revenue potential per active client relationship, a metric analogous to net revenue retention in enterprise software businesses. Crucially, these platform upgrades and AI integrations are not just the standalone features. They serve as the technological stepping stones for much larger scalable architecture we are building. They have successfully laid the operational foundation for A-Suite, the cohesive AI-native operating system that Michael touched upon earlier. As we prepare to introduce the first of these operational system in Q1 2026, we are actively transitioning to fundamentally running our service on an AI-native core. With the regulatory modes and upcoming A-Suite architecture we are fully committed to building, I'm very encouraged by the momentum entering 2026, and I look forward to reporting tangible milestones in the quarters ahead. Next, I will hand it over to Josephine.

Thank you, Yi. Good morning, everyone. I will now review our financial results for quarter four, 2025, and for the full year ending December 31st, 2025, and provide guidance for Q1, 2026. I will primarily reference the consolidated Amber International entity and where relevant, provide context at the Amber Premium segment level. Revenue for Q4, 2025 was $16.3 million, around 240% increase from $4.8 million in Q4, 2024. Within Amber Premium, wealth management solutions delivered approximately $5.9 million, execution solutions contribute $3.4 million, payment solutions contribute $1.2 million, and the marketing and enterprise solutions contribute approximately $5.8 million following this merger's consolidation.

The gross profits of $12.1 million at the 74.2% margin represents over 8x improvement versus Q4 2024 of $1.4 million at 28.9% margin. This margin quality is the most important structural indicator in our P&L as it validates the premium positioning of our wealth management-driven business model. At the operating line, Q4 2025 record an operating income of $1.2 million. The total operating expenses of $11 million reflect continued platform investment, including front office headcount to support AOP and client growth. The net income from continuing operations was $0.8 million in Q4, which significantly improved from a net loss of $12.1 million in Q4 2024.

The improvement was contributed by the continued growth of higher margin service and reductions in other losses related to year-end digital asset revaluation. The adjusted EBITDA for Q4 2025 was $50,000, making a return to positive adjusted EBITDA from a loss of $1.6 million in the same period of 2024. We are now turning to our annual financial performance. The full year story is one of the exceptional transformation. The full year revenue record $66.1 million, which represents over 7x increase from last year. It was driven by the first full year consolidations of Amber Premium following the merger. At the gross profit level, we delivered $49.4 million at a 74.8% margin, comparing to $2.5 million at 33.4% in 2024.

The total operating expenses record $46.9 million. It include approximately $444,000 of one-time merger costs and $0.6 million of share-based compensation. Both of them are non-recurring or non-cash. Stripping this, the recurring operating cost base was largely absorbed by gross profit, which producing an operating income of $2.6 million, which significantly improved from $5.3 million loss last year. From continuing operations, we generated net income of $4.7 million, which was completely reversing the $23.3 million loss in 2024. The net income attributable to the ordinary shareholders was $3.8 million after reflecting a restatement of discontinued operations. Our balance sheet is significantly stronger following the merger. The total equity growth 270% to $110.3 million.

The cash of $33.9 million provides a meaningful operational runway with zero bank debt. Our total liquid digital assets positions are $46 million, which comprising $33.5 million in crypto assets and $12.5 million in USDC. Based on current market conditions and our preliminary estimates, we are issuing Q1 2026 guidance on the Amber Premium segment with projected revenue of $5.1 million-$5.6 million. While the broader market downtrend we navigated in the fourth quarter of 2025 has continued into the first quarter of 2026, we are utilizing this period of purposeful strategic optimization. We continue to strategically streamline our resources and fulfill strengthened regulatory requirements across our active jurisdictions. With the milestone receipt of our license in Dubai, we are proactively refining our client base to focus exclusively on high-value compliance relationship.

This intentional contractions prioritize the depth and profitability of our network over share volume. Ensuring we continue to enhance our competitiveness as a sustainable institutional-grade digital wealth management platform through 2026 and beyond. Looking ahead, in addition to the external business strategy that we mentioned before, internally, we're implementing disciplined cost management to drive continued improvement in operating leverage as we scale. We're also enhancing our financial reporting systems to provide transparent insights into our performance as we integrate the operations following our merger. We also maintain strong liquidity and balance sheet flexibility in order to support our global expansion and strategic partnerships. The improved profitability demonstrate that our institutional approach is resonating with clients and creating values for shareholders. With that, I'll turn the call back to MIA. Thank you.

Thank you, Josephine. That concludes our remarks for today. We will now open the line for Q&A. Operator, please begin.

Thank you. Our first question comes from the line of Brian Dobson with Clear Street. Please proceed with your question.

Yeah, thanks very much. Do you think we could just take a step back first and perhaps you could describe the competitive environment in some of the markets that you operate in, and then perhaps we can take a closer look at some of your call it customer numbers from last year and how you expect those to evolve through next year?

Thank you, Brian. I can take a stab at this first, and then I think my colleagues will join me in providing more perspective. I think overall the competitive landscape of not only crypto, but broadly digital assets or even the fintech industry, continue to evolve. There are new entrants. You know, this is an industry where, you know, startups come out left and right every day. They're also, you know, changing of the top of the rank. We do see, you know, larger platforms undergoing their own changes, players catching up. We also see a more regionalized or a diversification of different players in different regions.

The way we look at the landscape is, one, you know, we accept the changes are constant, and therefore constantly want to evolve our business, evolve our business strategy, evolve our product suite. Secondly, we want to capture modes or competitive advantages that are more long-term, more permanent. For example, that's why on our regulatory land strategy, we continue to make progress on being, you know, one of the more complete Asian regulated platforms. We do think that will give us not only unique access to these client bases, but also, you know, more, more long-term positioning when it comes to competition.

Also in terms of product, services, and technology itself, given our investment and our DNA in AI-related technologies, we do think that will bring a lot of efficiency, a lot of scalability, and in the end, better product services for, to follow clients, which, in the long run should be giving us further competitive advantages.

Yeah. Hey, Brian, this is Steve. Just to add to what Michael has mentioned. Obviously we are a very comprehensive platform, and the important thing is that we can stay nimble to try to capture the market opportunities as they present themselves. For example, in the fourth quarter, there was a lot of volatility in the market that impacted, you know, whether it's clients' sentiment, especially in the retail and high net worth market, but institutional demand still stayed pretty strong, so our execution revenues were pretty strong, I think, despite the, you know, the downturn in the market. Also, we captured the structural change in adoption in stablecoins, right? Payment revenues and volumes were also very strong.

Just having a holistic, and comprehensive capabilities to capture all these markets and different end markets is very important for us. We just try to remain very nimble, every quarter try to capture these opportunities.

Yeah. Thanks very much for that color. I appreciate it. You know, in the press release, you talk about proactively refining your client base, to focus on high-value compliant relationships. I suppose just as a follow-up to that, can you give us a rough idea of how many clients are being off-boarded? I guess what was your thinking around that? Was it, was this a voluntary choice or is this something, you know, call it tied to your license applications in various regions?

Hi, hi Brian. This is Yi. Just to give you update on the like off-boarding. As I understand you may ask in Q1, maybe our movements. First is like our purposeful optimization. As mentioned, we are choosing to focus on the high-profile clients. The second, definitely I think we, as I mentioned, we are together with Amber Group. We are applying for the local license locally. I think we would definitely need to have like a more stringent standards for the clients to onboard to our platform.

Then the, we can maybe just to have a better ROI in terms of the sharing, to sharing the service, to providing the service to them. If you want some numbers, I suppose, we will disclose in Q1's the earnings release. Yeah.

All right. Thanks very much.

Thank you. Once again, if you'd like to ask a question, please press star one on your telephone keypad. Our next question comes from line of Jade Luo with Leslie Capital. Please proceed with your question.

Hi. Hi. I saw that Amber recently received a Virtual Asset Service Provider license from Dubai VARA. What's the revenue opportunity from the United Arab Emirates? Another question is that our marketing and enterprise solutions generated a good revenue in 2025. Is this segment contributing positively to the gross margin? Given the iClick held for sale pieces, should we expect the marketing and enterprise business to be the next? Thank you.

Yeah. Thanks for your question. I will take the first one. As we reported in the earnings release, we received the VASP license in Dubai. Although I suppose the short-term tensions are geopolitical tensions will introduce near-term complexities. We're still very confident that the MENA region is the obviously strategically rapid growing markets. Just give you a number on we're tapping the MENA region where we previously with Seven Touch a pump. According to the third party industry reports, it is forecast to reach $1.4 trillion of the total wealth transfer. I think the concentration of this wealth is precisely the clients who have our platforms built for.

Now our license portfolio combined with our Singapore Major Payment Institution and the ongoing Hong Kong license, I think Amber now definitely a Pan Asian like the multi-region platform. We advanced the client conversations on the way, and our commercial activity is expanding in the coming quarters.

Yeah. Regarding your second question, thank you for bringing that up. I do think it's a very interesting and exciting opportunity for us at Amber to look at what iClick is today or has been, right? It has, like you said, you know, it is still a high-quality business. It has a very high-quality client base. The tremendous room and the tremendous opportunity for us to improve not only how the business is run today, but also in what kind of services, what kind of products can provide to our client base, our existing and potentially in the future, more scalable client base with our AI rollout strategy.

As mentioned, we have already began the integration of MIA, who was also hosting our earnings call today, as per past few quarters, with the iClick business. From product ops to how we deliver the products to our clients, to how we service them, how we run this digital marketing business. We already see MIA and the in-house AI capabilities behind it making significant changes and significant upgrades. I hope, within the coming quarters, we will also see a lot of these progress reflecting in our numbers. As the management, as the founder Chief Executive Officer of Amber, to me, this is another, not only another exciting opportunity, but also similar to Amber Premium, another potential success proof case of how our technology can transform businesses and open up new opportunities.

Thank you. Ladies and gentlemen, once again, if you'd like to ask a question, please press star one on your telephone keypad. Our next question comes from line of Jonathan Lam with Canada's asset management. Please proceed with your question.

Hi. Thank you, management. On my end, I have three questions. The first one is around the quarterly performance, 'cause I'm looking at the quarter four and overall increase, there's an increase in overall revenue, the revenue from wealth management solutions and asset on platform, there's a decline. I just wanna check it up exactly what happened in the fourth quarter. The second question is around A-Suite architecture. You mentioned about it, but can you offer us a little bit more color on what exactly that is and how is it different from the other AI buzzwords? The third question is about AI agents, 'cause I know you mentioned your strategy around AI agents.

Could you elaborate a little bit more on your approach, and how is it different from the broader AI narrative in the market? Thank you.

Okay. Thanks, Jonathan. This is Steve. I'll take the first question, and my colleagues will probably answer the remaining ones. Yeah, in regards to the quarterly performance, I think, you know, obviously the market was quite soft in fourth quarter. That was the biggest contributor to why asset on platform fell. In addition to that, I'm sure most people are aware that. Actually, I'm not sure if most people are aware, but there was a big crash event in the fourth quarter on October 10th. I think it was the largest liquidation event in the history of crypto. After that, you know, there was a very different risk-reward dynamic in the market.

We were very selective in trying to structure products that offer favorable risk rewards to our clients. We, we were actively managing risk at that point. We decided to not be aggressive in terms of pushing out new products during the quarter. That, that caused, you know, a little bit of slowdown in AOP. That, that goes back to what Michael and everyone else said, that we do focus on high quality revenue and, and assets, right? We're not gonna be pushing for asset growth at all times. We will, we will do it opportunistically as Vicky mentioned, that we have very sticky clients. They will always come back when we offer products that, that make sense for them.

Thank you, Jonathan. Michael here. I will answer your second and third question about what is A-Suite and what are our agent strategy and why are they different, using your words from other AI buzzwords. I think these two questions are actually highly related. The way we see not only our business, but also how financial services are going to be run is perhaps a bit different from a lot of our peers. I think a lot of our peers in finance or in fintech are still thinking about, Okay, how do we apply AI here? How do we apply AI there? How will AI help us cut costs here? How will AI help us, you know, automate a bit of there. We fundamentally see that differently.

I think the right question to ask is rather what financial services should look like in this increasingly agentic world. Starting from answering that question, the conclusion we arrive is that agents will operate a lot of workflows today automatically by themselves. For that, they will need agent native or even agent-first operating systems for them to do that. Today, finance are operated mostly by human teams. Human teams operate in human-centric workflows, or they operate on system softwares that are designed that way. As agents are becoming more capable day by day, they are no longer just assistants, they're no longer just tools. They are capable of running entire workflows by themselves. To do that, they will need agent native systems that are specific to the industry or to the domain they operate in.

Amber has always been in the industry of fintech. We understand how financial services is done. In fact, being a digital asset financial service provider, we understand how financial services is done at the frontier of innovation. That experience and that ability give us insights of building what these systems look like as agents become more capable, as agents are already highly capable. Back to what is A-Suite? Again, A-Suite is three AI-native operating systems that are mapped to our business units. Also they are designed from day one to be operatable by agents, by autonomous workflows themselves.

We do believe not only through this year, through the coming quarters, we'll prove how that fundamentally increases our ability to service our clients, with our existing client base to more seamlessly provide new products and better products, and to increase our unit economics, increase our profitability. Therefore, these three operating systems, along with the agents we built to operate them together, will be what we believe the financial stack that fit for this future AgentFi economy and how financial services will be done that way. Hope that answers your question.

Yeah. Thank you for the insight. I appreciate it. Thank you.

Thank you. Ladies and gentlemen, that concludes our question and answer session. I'll turn the floor back to MIA for final comments.

Thank you all for joining us today. This year represents a pivotal step as we accelerate our AI-driven transformation and reinforce our commitment to institutional excellence, reaffirming Amber International's position as a global leading digital wealth management platform. We sincerely appreciate your continued trust and support, and we look forward to sharing further updates with you in the upcoming quarter. This concludes today's call. Thank you and have a great day.

Thank you. This call has been concluded. You may disconnect your lines at this time. Thank you for your participation.