Commonwealth Bank of Australia deploys agentic AI to detect scam patterns

It also creates new rules to intercept scams, approved by the bank’s fraud analytics team.

Commonwealth Bank of Australia (CBA) has deployed an agentic artificial intelligence (AI) system to detect emerging and scam patterns in transaction and payments data.

The system will also generate the rules needed to intercept these scams, CBA said in an online post.

“The agent operates around the clock, continuously monitoring activity and adapting to emerging threats,” said James Roberts, executive general manager of fraud and scams at CBA.

The new detection rules are reviewed and approved by CommBank’s fraud analytics team prior to implementation, a process known as human-in-the-loop oversight, Roberts said.

The agent has also contributed to developing or updating three quarters of CommBank’s card fraud rules.

“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 said.

CBA processes over 20 million payments on average every day, and sends more than 40,000 warning alerts on average to customers via the CommBank app.

Its current fraud detection technology has reportedly helped reduce its customers’ fraud losses by over 20% in the first half of the 2026 fiscal year, CBA said.

The investment is part of CBA’s A$1b annual commitment to safeguard customers from fraud, scams, cyber threats, and financial crime, the bank said.