A Bank Built Its Own Coding Agent. It Took Off — Felippe Felisola Caso & Francesco Galletta, Monzo

Uh, we are... Whoa, that was loud. Uh, we are Felippe and Francesco. Uh, we come to talk to you about the compound value of building Monzo's in-house agents using LLMs. Um, so what is Monzo? We are a bank, digital bank, trying to make money work for everyone. Uh, to give you a size of the problem for coding agents, uh, we have our teams of engineers maintaining over three thousand backend services, around thirteen

thousand, um, data warehouse models, and dozens and dozens of ML, uh, predictors. So we do all sorts of things like deciding on credit, deciding on financial crime, and doing very complex use cases both for the app, the backend, and data. Um, so I'm pretty sure by, even by today, but outside of the conference, you have heard a lot of, uh, success cases of companies adopting AI agents for coding. Uh, in fact,

uh, there was a conference a couple of weeks ago here in New York, and this article came out talking about the stake-- the state of the tech industry in twenty twenty-six. Uh, and there is this, hopefully, jokingly, uh, quote from X saying that, "If you're not building your own AI, uh, coding harness, are you even a serious tech company?" So some food for thought, right? Uh, then inside of Monzo, in January twenty, uh, twenty-six, this Slack channel went viral, Agent

Chip. And hopefully can... Oh, no, what happened?

Cannot do this.

It's all right. So hopefully I can bring your attention to this little emoji here. Really cute. We love it. Uh, this became really, really viral, uh, inside of the company for a really good reason. You can give it, uh, any prompt directly by just reacting with the little emoji to the message, and it will pick it up as a, you know, prompt. Uh, so that evolved. We doubled down, and that became an always available teammate inside our Slack and whole environment. Uh,

to give you a few examples, it does feel like a coworker. Uh, it's just there. You can always @Agent Chip and get it to do something for you, answer a question, find out something about some architecture, or just have a chat with you, but I don't, I don't think he likes it so much. Uh, it can also do code reviews. So like a very senior, uh, engineer, he will just tell you, "Looks good to me," and go on your merry way. And you can also assign, uh, Linear tasks as well. So you can give a

ticket, and it will just get into it. Um, so all of this is good and well. Uh, forward into today, Agent Chip authors over ten percent of all merged PRs across tech. So that's data, uh, machine learning, that's, uh, backend engineering app, et cetera. Also runs more than eighteen hundred, uh, tasks per day, which is a lot. Um, and it's being actively, uh, starting to

be adopted by business users as well. So it's not just coding and tech, it's also trying to answer business questions, writing queries, or self-serving anything that a business user may need.

So again, you've heard many success stories about companies adopting AI coding agents. But so what?

Why are we... What are we trying to share today? Are we saying that we want to brag that we built Claude Tag six months before Anthropic released it? We could be. That's not the focus of today's talk. Um, we want to share the secret sauce of what makes Agent Chip a successful product, and it's LLMs. But actually, LLMs, in this case, stands for lots of little multipliers. We believe

that what enabled us to build Agent Chip so quickly and so in a valuable way is a very strong platform at Monzo. Uh, so when we say that this went viral, and you could write a prompt, react, and profit, actually, this comes from a number of capabilities we already had. So alerting, monitoring, integrations with third parties, such as the ones Francesco mentioned, a staging environment that allows us to test easily, queuing

abstractions, easy deployment, database abstractions, and a number of other things I could be mentioning here. So first and foremost, what we have in our platform is what allowed Agent Chip to be successful. But this does not co-- stop there. We saw even before Agent Chip as a remote agent existed, we started to invest in supporting AI coding agents, even in local environments. So the-- one of the first things we

did was develop an MCP gateway that allowed easy access to a set of knowledge sources and internal tools and some of the, uh, services that Francesco mentioned. So this is roughly how the architecture looks like. Um, we have the things we want to connect as the internal services and knowledge sources. Um, we-- And we put that behind the MCP server that we built to get the deterministic behavior, choosing what are the things we want to expose to the agents, and then we manage

also authorization, authentication for the number of different agents. Again, this started in a world of local coding agents that wanted to connect, and by, by now, probably everyone has heard in multiple, uh, sessions that the more context and the more data we are able to give safely to our agents, the better. Um, after that, we built the agent orchestration system, which is exactly what powers Agent Chip behind the scenes and makes it work

in a sandbox and with very strict tools and permissions. So if we go back to our, um, diagram, the whole architecture for the MCP server basically condenses into this box. And this is where we connect the rest of the Agent Chip, um, architecture. So we have remote agents running inside the sandbox in an isolated namespace, and then the orchestration system triggers and then reads and gets this information from, from

that. The main idea here is, and again, this is coming across in a multiple of provi-- uh, multiple providers and labora-- labs and so on, is that we want to separate this from the rest of our infrastructure in production. Again, we are a bank. We live in a regulated environment, so we want to make sure that the non-determinism from the agents is controlled. Um, but at the same time, we want to have an environment where we can let it run loose and develop. And

again, if we explode this to give you a bit more under-the-hood visibility of what is going on. So in this isolated namespace, multiple pods come up with sandboxes that the agents are running on. Um, the agent image is where we define the exact tools the agents will have as, as access. So things like the environment, the CLIs, and the authentication and the authorization that again, we get from, um, the gateway itself. Um,

the proxy is what allows us to connect to both the exterior world. So that's how, for instance, Agent Chip is able to connect to our code, to our repositories, and work with that. Um, but of course, we only get the egress that we choose to do, choose to give it. Um, so that is how we make sure that it's very controlled and deliberately giving access to the things we want it to be able to see. And finally, the little, uh, blue green box there is where the

agent itself is running. So that box inside the box inside the box is where the non-determinism happens, and it's where the agent can perform everything that it wants. So this is how the whole diagram looks like when we are able to give our MCP server access to everything that we care about for the agent. We are able to safely give it access to our data, and the agent orchestration system handles everything that's around it.

With this as building blocks, any use cases that come after it are much, much easier to be built on top of. So as Francesco mentioned, this we can connect Slack to, and then we can connect GitHub, and then we connect Linear. And then I just use a different color to show this is the more than three thousand services that we can be connecting to, to this as a building block. So in the same fashion that we had multiple things in our platform that enabled us to

build Agent Chip and get value out of it, now that Agent Chip is also a building block, the multiple parts of our bank can also leverage it to create other use cases. So we start to see these building blocks enabled us to not only get more, um, product features internally, but to drive concrete business outcomes. Um, we observed a higher breadth and volume of tasks that engineers are able to run, as you can expect, because then we don't need

people to be babysitting their agents all the time. They can use their coding assistant for, um, specific tasks, but they can also delegate to remote agents. We can automate routine processes much better. So that allows humans to focus on the higher value problems where the ambiguity lies, particularly. Some examples of these that we are able to do. Um, this is Agent Chip working in incident mode and leveraging the MCP to get very relevant

data. So what happens here is whenever we identify and trigger a new incident, Agent Chip joins the channel and is able to start an investigation, understanding logs, understanding traces, being able to connect to that exact service, and of course, the code itself to see what's going on and to help the human with a very high signal. We don't want the agent to be saying a lot of things during an incident and testing hypothesis live. We want it to maintain high signal, and we give the humans also

control of how much Agent Chip will be able to support there. We can continue to use it on Slack, but not only by triggering it, by mentioning it, uh, but also in what we call ask channels. It's basically squad-to-squad interaction inside Monzo. A squad needs to have some context on a backend service, on a product development, on the roadmap. And Agent Chip can also, since it can connect to our knowledge sources, it's able to draft a response for the

human in the loop to get as reference and support there. Maybe the response will be enough, and Agent Chip can just solve that ask ticket by itself. Sometimes it will ask for more context, and the human in the loop can be tagged, um, and come in to support more. Um, something that we're doing very recently that's been, uh, creating a lot of value is also triaging data quality alerts and checking for backend changes that can create problems. So

basically, we call it Agent Chip on call, and it observes the failures that we have and triggers an investigation automatically. This is the reactive version of it. But what if the errors never happened in the first place? We created based on this, the proactive version that monitors, uh, backend changes and identifies which are the potential, um, outcomes that that can have for our data even before the data is processed in the next batch execution.

So again, all of these are examples of how our technology team is using it. But m-- even better than that, we've observed a lower barrier for non-specialists in the company to contribute to our systems. With a very quick entry point for Agent Chip on Slack, non-specialists can, based on product feedback, based on ideas, based on discussions they are having, just call Agent Chip, get a draft that works, that is already tested in staging, and then, and

only then, involve an engineer to make sure we get the changes reviewed and deployed properly. So this doesn't change the rigor to which we develop software at Monzo, uh, but this does allow a number of non-specialists to also start contributing more closely to the team.

You can be thinking now, um, the market is moving fast. We are hearing a lot of exciting, um, developments and new products and new features coming from multiple companies here in the conference and otherwise. What makes us believe that Agent Chip continues to be a valuable thing at this point in twenty twenty-six and moving forward? Um, as I said, and I, uh, like to, to reiterate, Agent Chip being, uh, composable,

it is now a new building block that we have in our platform. So it very quickly enables new use cases for agentic, um, implementation at Monzo now that we can connect it very safely with all our security requirements and all our backend and platform requirements at the same time. Our platform is plat-- provider agnostic by definition. So if we come back to the diagram, the little blue/green agent box there can be very easily swapped by

any-- for any model. We can dynamically choose which model best fits, um, the purposes that we have. So we are not specifically tied to any provider by definition, and that gives us, uh, flexibility to understand which ones will fit Monzo's needs, uh, the best. Um, and finally, we are continued to move to cover a bigger development window. So if we-- even if we stop development today, this would already be valuable, um, but we can cover a much

broader sense in terms of we draft changes in the backend, we draft changes in the app, we can test these changes in a staging environment, cover the data tests, who knows, maybe even predictors on the other side. So when remote agents are able to do this end-to-end, we can understand, uh, and integrate our systems much better. So again, the market is moving, doesn't mean that we, uh, are necessarily, uh, married to Agent Chip, um,

until, until the end. But these and other aspects of it make us, uh, strongly believe that is-- it is a very strong part of our, um, internal platform now. And the key takeaway that I want to, I want you all to take from is: How can you benefit from LLMs but not the traditional LLMs, but the lots of little multipliers that you and your team can use to leverage value? Thank you.