ANZ taps generative AI for code testing

ANZ Banking Group has “formally sanctioned” a team to explore generative AI to augment its code testing capabilities as well as to explore deeper potential use cases.

The bank has roughly 4000 software engineers, with sees opportunities to use generative AI to improve the efficiency, reliability and performance of its code.

“Generative AI has a range of potential benefits for ANZ and the broader industry, and we’re in the early days in our exploration of the technology,” ANZ chief technology officer Tim Hogarth told iTnews.

He added its experimentation does not use “any private or confidential data” as “every technology implementation at ANZ is subject to strict controls.”

While ANZ chief technology officer Tim Hogarth previously told iTnews it was “too early to speculate on use cases” for the technology, the bank has since begun exploring various applications.

Discussing generative AI in a recent ANZ Bluenotes post Hogarth said that “ChatGPT’s conversational AI also helps software engineers deepen their comprehension”.

“We’ve formally sanctioned one team in ANZ to explore generative AI for software engineering to improve our testing. Writing test cases – normally also written in code – is an important, if somewhat tiresome, task," he said.

“Generative AI is really powerful at reading code and proposing the complete test case to properly exercise that code.

"This will dramatically improve unit testing and, I think, give us a step change in identifying bugs and errors earlier in the development process."

He added ANZ is “also looking to improve how we validate code [against] strict standards and rules".

“We have comprehensive policies at ANZ but it still requires a human to read and understand a policy and recall the key elements while completing a code review," Hogarth said.

He said the team sees the new capability as “an augmentation tool" and "not a final arbiter" of compliance.

Hogarth said ANZ will be "able to make our engineers far more efficient through the use of AI technology” while keeping its controls and checks in place.

“All new technologies present challenges and opportunities and this will be true of using generative AI in software engineering," he said.

"There will be concerns around reliability, repeatability and risks of these tools. There will need to be checks and balances for some time yet. 

“We are not yet ready to use this outside of centrally managed, executive approved experiments.”

Despite its cautious approach, Hogarth said ANZ had a “long history of embracing technology in the adoption life cycle”.

“ANZ is, and always will be, an early adopter of critical new technologies and generative AI is the next major wave," he said.

"But we will do it with rigour and discipline.”