Revolut Builds AI Trading Desk in 30 Minutes
Revolut engineers reportedly used Anthropic's Claude AI and their trading API to build a market-making system in just 30 minutes via prompt engineering. This signals a shift towards valuing candidates who can rapidly prototype and integrate AI agents on quant desks.
The Revolut engineers, Nikita Ivanov and Vlad Kaminski, leveraged Anthropic's Claude AI and Revolut's trading API to create the market-making system. The AI was connected to the Revolut X trading API using Anthropic's Model Context Protocol (MCP). MCP is an open standard developed by Anthropic that allows AI models to discover and use external tools through a standardized interface. Instead of building custom integrations for every API, MCP lets an AI agent connect to compatible systems and reason across them simultaneously. Revolut X is currently offering MCP access in beta. The system handles inventory management, dynamic quoting, position sizing, execution, monitoring, and Telegram alerts. Such a workflow would typically require a quant, a developer, backtesting infrastructure, and weeks of iteration. Revolut's API-first infrastructure across asset classes was crucial for this experiment. A 2024 partnership with CMC Markets Connect brought CFD trading via API, and a similar deal with GTN added bond trading for EEA customers. Revolut X targeted the $200 billion European crypto market, driven by Leonid Bashlykov. Anthropic has been expanding Claude's capabilities for financial services, including an Excel add-in and connectors to real-time market data. Claude can now perform tasks like building discounted cash flow models and initiating coverage reports. Revolut aims to become a leading market maker, competing with firms like Citadel Securities and Jane Street. CEO Nik Storonsky has trading floor experience, claiming a bonus of approximately £500k in his first year as a Lehman Brothers trader. Other firms are also integrating AI into trading; ATFX partnered with KX for an AI-driven MCP server, and LSEG connected market data feeds to ChatGPT. Goldman Sachs introduced a generative AI assistant for its bankers, traders, and asset managers in January 2026. This development raises questions about the role of traditional broker platforms if AI agents can manage entire trading workflows via prompts.
