Most Australian workers use AI tools in the workplace and half of them save at least three hours a week, a study has found.
But research from software firm Freshworks found many employees were trying artificial intelligence software without approval from their employers in a trend that could spark privacy and security concerns.
The findings come amid fears AI tools could collect and use confidential corporate data, and as an expert group considers rules for high-risk scenarios.
More than 7000 employees were surveyed on their use of artificial intelligence software for the global ROI of AI study, including 358 Australian office workers.
It found more than two-in-three local employees used AI tools at least once a week, which is more than US and UK workers, and half reported saving at least three hours per week by using AI software.
The research also found almost half of Australians workers were using unpaid AI tools such as ChatGPT to boost their productivity, despite the risk that sensitive business data could be used to train large language models or shared widely.
Freshworks senior vice-president Sandie Overtveld said he was surprised by the popularity of AI tools among Australian workers, warning it may be a result of businesses failing to set clear AI policies and standards quickly.
"If you don't make the decision as a company, employees will make the decision for you and that might not be the decision that you want," he said.
"Many companies would be surprised to find their conservative stalling is having employees use free tools that might be causing them more harm than good."
The study also found Australian workers were less effusive about the quality of content produced by generative AI, but Freshworks Australia and New Zealand vice-president Andrew Phillips said that could indicate the need for greater guidance and training from employers.
"Rules around which tools they can use and which tools they can't will help employees get the benefits of generative AI without getting the company into trouble," he said.
"Training and policies always play catch-up with new technologies."
Australia currently lacks regulations specifically targeting the use of generative AI technology, though the government appointed 12 experts to a national advisory body in February.
The Artificial Intelligence Expert Group, which was appointed until June 30, was tasked with creating mandatory rules for the use of AI in high-risk settings, as well as standards for watermarking AI-generated content.
