Macquarie Bank has stood up a centralised knowledge base of tightly governed enterprise data and code assets to support the development of agentic AI applications.<\/p>\n
<\/p>\n
Built on Google Cloud, the Knowledge Platform aggregates structured data from the bank\u2019s repositories alongside unstructured content such as PDFs, SharePoint files, Confluence pages and operational procedures.<\/p>\n
Data is funnelled through a \u201chighly curated pipeline\u201d into the platform, which then feeds into Google\u2019s Agentspace, where Macquarie Bank plans to develop an ecosystem of agentic AI applications.<\/p>\n
Speaking at Google Cloud Summit last month, Macquarie Bank chief data officer and executive director Ashwin Sinha called the platform “the most important layer\u201d of the envisioned ecosystem.<\/p>\n
\u201cYou can achieve a level of accuracy or consistency based on foundational models, so just large language models by default,\u201d he said.<\/p>\n
\u201cBut to really make it useful in a production-ready manner, you need the underlying knowledge repository [which is ] well curated, well maintained and [has] a very clear sense of ownership.<\/p>\n
\u201cThe curation of it becomes very important in terms of whether it is the latest version or whether there are multiple versions [of a data asset],\u201d he added.<\/p>\n
\u201cHow are you going to make sure that information is continuously maintained and current?\u201d<\/p>\n
Within Agentspace, the bank has enabled NotebookLM, Google\u2019s AI-powered assistant that helps summarise notes, along with enterprise-wide search capabilities across Macquarie\u2019s data repositories.<\/p>\n
According to Sinha, this search engine is already connected to several data sources via connectors, with plans to expand those integrations further.<\/p>\n
These initiatives support Macquarie Bank\u2019s ambition to develop a comprehensive ecosystem of AI agents, with several currently in pilot stages.<\/p>\n
According to a conceptual framework outlined by Sinha, these agents would start from personal assistants, which function as \u201csimple no-code automation of individual tasks\u201d.<\/p>\n
At the next level are enterprise agents, purpose-built specifically for Macquarie\u2019s Banking and Financial Services (BFS) division.<\/p>\n
Meanwhile, tools such as GitHub Copilot may be tapped to develop integrated development environment (IDE) agents that will “enhance software developer productivity”.<\/p>\n
\u201cWe have found these to be incredibly useful for our engineering team in terms of driving their productivity and their pace of delivery,\u201d Sinha said.<\/p>\n
To complement this, Sinha envisions adopting a set of \u201ccore\u201d or reusable agents, where \u201caspects of software engineering or software development could be automated or semi-automated”.<\/p>\n
A \u201cless mature\u201d idea in the works is to create a marketplace for third-party agents, which, according to Sinha, \u201cwill drive a lot of productivity or tasks in terms of things which have to be done here\u201d.<\/p>\n
A year of experiments<\/p>\n
These initiatives evolved through a concerted effort across the entire bank to explore and trial AI technologies over the past 12 months, from the top down.<\/p>\n
\u201cWe created a culture of experimentation and very rapidly learning about many of these technologies,\u201d Sinha said.<\/p>\n
\u201cWe also went on an extensive exercise of training all of our leadership, as well as all of our staff. We trained over 2,500 people in prompt engineering.<\/p>\n
“We trained the top 150 leaders across the bank on this topic, and that created a lot of good ideas.\u201d<\/p>\n
This training culminated in a session for Macquarie Bank\u2019s wider leadership team, which sparked ideas for \u201c130-plus agents, which can change how we are running our business\u201d, Sinha said.<\/p>\n
This employee and stakeholder engagement also reflected Macquarie Bank\u2019s strategic view of AI as a \u201cwhole-of-business change\u201d.<\/p>\n
\u201cThe way we see generative AI is that it\u2019s more of a general-purpose technology, which means a lot of people who are outside technology areas are still able to use it, make really productive use of it and come up with very good ideas that can drive productivity and better customer outcomes,\u201d Sinha said.<\/p>\n","protected":false},"excerpt":{"rendered":"Macquarie Bank has stood up a centralised knowledge base of tightly governed enterprise data and code assets to…\n","protected":false},"author":2,"featured_media":110980,"comment_status":"","ping_status":"","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[20],"tags":[256,254,255,64,63,105],"class_list":{"0":"post-110979","1":"post","2":"type-post","3":"status-publish","4":"format-standard","5":"has-post-thumbnail","7":"category-artificial-intelligence","8":"tag-ai","9":"tag-artificial-intelligence","10":"tag-artificialintelligence","11":"tag-au","12":"tag-australia","13":"tag-technology"},"_links":{"self":[{"href":"https:\/\/www.newsbeep.com\/au\/wp-json\/wp\/v2\/posts\/110979","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.newsbeep.com\/au\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.newsbeep.com\/au\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.newsbeep.com\/au\/wp-json\/wp\/v2\/users\/2"}],"replies":[{"embeddable":true,"href":"https:\/\/www.newsbeep.com\/au\/wp-json\/wp\/v2\/comments?post=110979"}],"version-history":[{"count":0,"href":"https:\/\/www.newsbeep.com\/au\/wp-json\/wp\/v2\/posts\/110979\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/www.newsbeep.com\/au\/wp-json\/wp\/v2\/media\/110980"}],"wp:attachment":[{"href":"https:\/\/www.newsbeep.com\/au\/wp-json\/wp\/v2\/media?parent=110979"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.newsbeep.com\/au\/wp-json\/wp\/v2\/categories?post=110979"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.newsbeep.com\/au\/wp-json\/wp\/v2\/tags?post=110979"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}