ING Groep employs vibe coding to enhance electronic trading tools

The Dutch banking giant is using natural language prompts to generate trading code in hours instead of weeks, and it expects the rest of Wall Street to follow within a year.

Share

Add us on Google by Editorial Team May. 26, 2026

A major European bank is now writing trading software the way most people write emails: by describing what they want in plain English and letting AI do the heavy lifting.

ING Groep, one of the largest financial institutions in the Netherlands, has integrated so-called “vibe coding” into its electronic trading operations for currencies and credit products. The bank’s quant desk started experimenting with the approach in February 2026 and, by mid-May, was using it daily to generate trading-side code and visualizations.

What vibe coding actually means

The term “vibe coding” was coined by AI researcher Andrej Karpathy in 2025. In English: instead of writing code line by line, developers describe what they want a program to do using natural language prompts, and a large language model generates the code for them.

Advertisement

At ING, the process runs under senior supervision. Experienced developers review and validate the output, which means the technology functions more like a force multiplier than a replacement.

The underlying system uses an in-house model developed by Anthropic, the AI safety company behind Claude. That architectural choice is deliberate: by keeping the model internal, ING ensures that sensitive client data and proprietary trading information never leave the bank’s walls.

Speed gains that are hard to ignore

ING says vibe coding compresses prototyping timelines from days or weeks to hours.

Simon Bevan, ING’s global head of e-trading, noted that the quality and speed of results from vibe coding have been surprisingly strong.

Junior developers can now create bespoke visualization tools that previously required either senior developer time or expensive third-party software licenses. Senior developers, meanwhile, get freed up to focus on higher-value problems instead of spending their days on routine code generation.

Why the rest of finance is watching

ING anticipates that vibe coding will see rapid adoption across the financial sector, potentially within a year.

That said, there’s a governance gap that the industry hasn’t fully addressed. Internal AI use regulations within trading operations are reportedly lagging behind the frameworks already in place for client-facing AI applications. The supervisory layer ING has implemented, where senior developers validate AI-generated code, is one answer to this problem.

Disclosure: This article was edited by Editorial Team. For more information on how we create and review content, see our Editorial Policy.