CommBank Develops AI Agent That Spots New Fraud And Helps Build Defences

Commonwealth Bank has deployed an agentic AI system designed to detect emerging fraud and scam patterns in transaction and payments data and automatically generate the rules needed to help intercept them.

The system represents a shift from traditional AI-based fraud detection, which identifies known threats, to a model that can identify new patterns and propose ways to disrupt them. CommBank’s in-house data science and engineering teams built the system in three months.

The investment sits within CommBank’s $1 billion annual commitment to safeguarding customers from fraud, scams, cyber threats and financial crime.

James Roberts, Executive General Manager of Fraud and Scams at CommBank, explained how the agent operates.

“When suspicious patterns are identified, the system quickly assesses their severity, analyses context, and proposes new detection rules to help intercept them,” Roberts noted. “The new agent goes beyond traditional AI by not only rapidly identifying new threats but also determining how it can seek to disrupt them.”

“The agent operates around the clock, continuously monitoring activity and adapting to emerging threats,” he added.

Human oversight remains in place

While the AI agent generates proposed detection rules autonomously, those rules are reviewed and approved by CommBank’s fraud analytics team before they are implemented. The bank describes this process as human-in-the-loop oversight.

AI models used across the bank are governed by CommBank’s risk management frameworks and policies, with clear human accountability for outcomes.

Scale of operations

CommBank has a range of AI capabilities embedded in its fraud protection systems, which monitor more than 80 million signals each day. Those signals include transactions, card and online payments and interactions with digital banking channels.

The bank processes more than 20 million payments on average each day and sends more than 40,000 proactive warning alerts on average to customers via the CommBank app.

The agent has contributed to developing or updating three quarters of CommBank’s card fraud rules, which are used to identify potential fraud.

“The technology allows us to identify unusual events in highly complex patterns of activity at far greater speed and scale, helping us detect emerging threats sooner and update our controls faster,” Roberts commented.

Measurable impact on fraud losses

CommBank’s fraud detection technology has played a role in helping to reduce fraud losses by more than 20 per cent in the first half of the 2026 financial year compared to the first half of the 2025 financial year.

Ongoing testing of the agentic system has demonstrated strong fraud detection outcomes, according to the bank.

Built on cloud infrastructure

The system is built on Snowflake’s data cloud and powered by CommBank’s cloud-based core banking platform, enabling access to real-time data to support the AI capabilities.

The initiative is part of CommBank’s broader strategy to embed AI into core operations. The bank was ranked among the top four banks globally for AI maturity in the 2025 Evident AI Index.

Last Updated on April 24, 2026 by Nick Ross