First Live AI-Agent Driven Digital Asset Transactions by a Regulated Swiss Bank

• Thomas Frei
  Head of AI and Data Analytics and AI@Sygnum lead
  Sygnum Bank

In a first for Swiss banking, client-issued plain text instructions have been used to execute multi-step live transactions on a blockchain Mainnet. The Sygnum AI agent used these instructions and independently planned and prepared each step, reviewed the relevant smart contracts, and flagged potential transaction risks before presenting each transaction to the client for approval. Transactions are only signed through the client’s self-custodial wallet on their own device, ensuring private keys do not leave client control at any time. Sygnum’s AI agent can be used to execute multi-step on-chain transactions for stablecoin transfers, asset swaps, on-chain lending positions, token wrapping and liquidity provisioning.

The pilot was built using a Model Context Protocol (MCP) server built in-house by the AI@Sygnum team using Anthropic’s Claude as the underlying AI model. MCP is a new open standard enabling AI and financial platforms to share context and data, streamlining transactions while maintaining client control and security safeguards. The MCP-based architecture is model- and asset-class agnostic, allowing the infrastructure to scale as the ecosystem develops.

Connecting AI agents to wallets is foundational to where finance is heading. The next decade will see agents transacting, settling and interacting with markets on behalf of clients. The key challenge is doing this in a way that preserves – and even enhances – bank-grade consent, custody and trust. That is what we set out to solve, and what this pilot demonstrates: that a regulated Swiss bank can provide clients with the speed, convenience and accessibility of agent-driven execution, without ever giving up control of their assets.

Unlike architectures where AI agents with their own wallets transact autonomously, Sygnum’s approach enables clients to own, hold and fully control their own wallets and assets at all times. This reflects a core principle of the AI@Sygnum program, where AI augments and enhances, but does not replace, human decision making or trusted personal relationships. This will benefit clients by enabling them to directly execute on-chain actions and access live market infrastructure, compose multi-step workflows without code and use their wallets natively.

This “human-in-the-loop” design is central to Sygnum’s integration of its agentic AI roadmap into all areas of the group’s global operations. The four key pillars of Sygnum’s organisational AI strategy are:

• Client experience – always‑on AI augments existing personal relationships with our experts
• Regulated innovation – leveraging AI to deliver smarter, more intuitive products and solutions for clients in a trusted,
  regulated environment
• Organisational efficiency – reclaim manual effort to focus effort on high-value work serving our valued clients 
• Operational excellence – continually raise the bar on quality, security, governance, and organisational resilience 

Sygnum’s human-led, AI-augmented approach comes at a time when regulators increasingly view the potential for AI agents to act beyond the client’s intended scope as a risk for financial institutions^[i]. Sygnum’s AI governance on data, risk management, transparency and accountability is designed to fully meet the highest regulatory, bank-grade standards. It also reinforces the values that Sygnum private and institutional clients value most: trust, personal relationships and the vision to shape Future Finance.

Sygnum’s MCP AI agent is not currently available to clients. Production deployment will be subject to full regulatory, compliance and security reviews and approvals.