Gradient Labs uses GPT‑4.1 and GPT‑5.4 mini and nano to run complex financial support workflows with high accuracy and low latency.

In banking, resolving a customer issue is rarely simple. Cases like fraud or blocked payments require strict adherence to complex procedures across multiple teams. When systems fall short, customers are passed between teams, wait in queues, and face delays at moments when the stakes are highest.

Gradient Labs⁠(opens in a new window) is built to handle this complexity. The London-based company is building AI agents that give every bank customer the experience of a dedicated account manager. Founded by a team that previously led AI and data efforts at Monzo, the company’s platform is built on OpenAI models and is now shifting production traffic onto GPT‑5.4 mini and nano.

“We’re seeing 500-millisecond latency with GPT‑5.4 mini and nano, which is exactly what we need for natural voice conversations,” says Danai Antoniou, Co-Founder and Chief Scientist at Gradient Labs. “We’re moving a significant portion of our workload over.”

In banking, customer interactions are governed by standard operating procedures (SOPs) that define what should happen at each step.

The system verifies their identity, handling corrections and interruptions in real time.

It answers follow-up questions, such as delivery timing, and suggests next steps.

Each step follows a defined procedure, with decisions made in real time based on user input, context, running guardrails, and both customer and agent responses to ensure compliance.

“The model needs to maintain procedure state across interruptions, backchannels, and topic switches while keeping response generation fast,” says Antoniou.

Source link