![\"Macquarie](\"https:\/\/www.newsbeep.com\/au\/wp-content\/uploads\/2026\/02\/1771435459_283_ImageResizer.ashx.png\")
<\/p>\nMacquarie\u2019s banking division is taking reliability cues from Google, adopting its site reliability engineering principles and using AI agents to enforce them.<\/p>\n
<\/p>\n
\n Macquarie Group’s Phillip Grasso-Nguyen.
\n <\/p>\n
The effort is being spearheaded by divisional director and head of engineering excellence and reliability Phillip Grasso-Nguyen, a former Googler and CBA engineering lead.<\/p>\n
Speaking at Dynatrace Perform 2026 at the end of last month, Grasso-Nguyen said that Macquarie had demonstrated that a bank can achieve \u201ctech company-level reliability\u201d.<\/p>\n
\u201cWe exceeded our targets and hit 99.98 percent availability and reliability for our customers, with a faster detection rate at 79 percent, with 59 percent fewer critical incidents,\u201d he said.<\/p>\n
Grasso-Nguyen said Macquarie set a goal to \u201cbecome the best tech company in financial services.\u201d<\/p>\n
\u201cI thought this would be easy coming from Google, but I was wrong,\u201d he said.<\/p>\n
\u201cTech companies treat their systems like cattle. They\u2019re uniform and they\u2019re replaceable, done at scale. Enterprises and banks treat their systems like pets, with a lot of care and support, a lot of complexity and a lot of personality.<\/p>\n
\u201cI had to shift my mindset from herding cattle to looking after pets. I had to embrace the complexity explosion that exists in enterprises; and I had to focus on one thing that mattered the most, which is our customers.\u201d<\/p>\n
Underpinning Macquarie\u2019s retail digital bank is a cloud- and Kubernetes-based stack comprising \u201cover 6000 services\u201d.<\/p>\n
Grasso-Nguyen said the bank typically deploys in excess of \u201c8000-plus changes and releases a year\u201d, with the work completed by 1500 engineers.<\/p>\n
\u201cWe have no appetite for customer disruption. So what does this mean? We\u2019re not allowed to have scheduled outages, ever.<\/p>\n
\u201cSo can you imagine how the core banking team felt and how much fun they had trying to replace parts of their core banking system last year,\u201d Grasso-Nguyen said.<\/p>\n
The bank ultimately needed to be both \u201creliable and innovative\u201d in its approach to engineering, and this ushered in a focus on site reliability engineering (SRE).<\/p>\n
Grasso-Nguyen said that the typical approach to having a reliability incident \u201cis to slow down\u201d and add process.<\/p>\n
\u201cSo, often that\u2019s done through CABs [change advisory boards],\u201d he said.\u00a0<\/p>\n
A change advisory board is a decision-making body that oversees change management in organisations.<\/p>\n
With a background at Google, however, Grasso-Nguyen sought to take a different approach.<\/p>\n
\u201cWe applied the Google SRE methodologies and principles, so that meant no CABs, no change boards, [and] smaller changes more often, with a lower blast radius,\u201d he said.<\/p>\n
\u201cBy adapting engineering ways of working from the tech companies, we managed to get 90 percent on-time project delivery, with 80 percent less defects.\u00a0<\/p>\n
\u201cWe proved that you don\u2019t have to trade off reliability for innovation.\u201d<\/p>\n
Macquarie supports its reliability, change and incident management using an application performance management (APM) and observability stack supplied by Dynatrace.<\/p>\n
This has helped the bank meet its reliability objectives. In Grasso-Nguyen\u2019s words, Macquarie is “not just looking for problems but making sure we\u2019re avoiding them getting into production.\u201d<\/p>\n
Macquarie is using SRE AI agents\u00a0\u2013 both Dynatrace\u2019s and its own\u00a0\u2013 to assist with all aspects of the capability.<\/p>\n
\u201cWe have AI agents that are doing automatic diagnostics [and] running runbooks. We\u2019re using the Dynatrace API to power our AI agents,\u201d Grasso-Nguyen said.<\/p>\n
\u201c[For example], we have an automated release verification agent that acts as an SRE gatekeeper, automatically catching problems and change failures.\u00a0<\/p>\n
\u201cNow, in every incident, we use AI agents.<\/p>\n
\u201cWhere previously we had a large number of teams in the triage, now we have operators with assisted AI agents that can get to problems in minutes. We only call in the relevant teams now so it means that we spend a lot less time diagnosing and repairing, and we don\u2019t waste as much time as we used to.\u201d<\/p>\n
While Macquarie has built its own agents where out-of-the-box capabilities do not exist, this is likely to change.<\/p>\n
At the conference where Grasso-Nguyen spoke, Dynatrace unveiled an agentic operations system called Dynatrace Intelligence.<\/p>\n
Grasso-Nguyen said Macquarie is now \u201choping to partner\u201d more closely with the vendor \u201cto evolve our capability.\u201d<\/p>\n
\u201cIf we don\u2019t need to build it, why build it ourselves?\u201d he said.<\/p>\n
Customer-facing agents<\/p>\n
Grasso-Nguyen said that Dynatrace is also helping the bank to deliver customer-facing AI experiences.<\/p>\n