![\"\"\/](\"https:\/\/www.newsbeep.com\/au\/wp-content\/uploads\/2026\/06\/1782128720_713_ImageResizer.ashx.jpeg\")
<\/a><\/p>\nTwo of the five agents work in the first stage of the claim being initiated – in insurance parlance, the FNOL or first notice of loss stage, where a customer reports an incident has occurred.<\/p>\n
The agents are targeted at capturing and validating the report, and then classifying and routing it internally.<\/p>\n
It appears at least one of these agents is voice-based.<\/p>\n
\u201cWe have got voice agents which went into production very recently,\u201d Nekkalapu said.<\/p>\n
\u201cThey do the initial intake of the claim in some cases, and if it becomes more complex, then pass on to humans.\u00a0<\/p>\n
\u201cThere are multiple channels in which we intake claims.\u201d<\/p>\n
A \u201csystem of agents\u201d is then specified to perform a \u201ccoverage check\u201d as part of triage and assessment of the claim.<\/p>\n
Agents are also to be used for \u201cvendor dispatch\u201d – presumably, engaging a party to conduct a repair – and to handle any settlement calculation.<\/p>\n
In the reference design, the entire claims processing workflow is mapped out using business process model and notation (BPMN) and orchestrated with UiPath.<\/p>\n
\u201cSo, at a high level, we are talking about \u2026 a BPMN workflow, [with] multiple tasks within that and each task could itself be done by an agent or a system of agents or workflows themselves,\u201d Nekkalapu said.<\/p>\n
With a number of agents in the claims process, Nekkalapu said that Suncorp had worked closely to ensure their work \u201cis properly monitored\u201d, governed and meets customer and operational expectations, as well as that of regulators.<\/p>\n
\u201cObservability is really, really key here,\u201d he said.<\/p>\n
\u201cWe may have a very fancy system, but if we do not have control over the risk, if we are not able to observe whether our controls are working or not, [then] it counts [for] nothing.\u00a0<\/p>\n
\u201cThere could be severe issues in the system and things may be broken or there may be some sort of attack on these agents by external parties. So how exactly are we going to monitor this?\u00a0<\/p>\n
\u201cThat is done through a central observability platform that we have built on Databricks.\u201d<\/p>\n
The observability platform is ingesting OpenTelemetry (OTel)-based data feeds from the various agents and technologies used in the claims processing workflow.<\/p>\n
\u201cWe’re bringing in traces by having an OTel collector on Databricks, so all the traces from agents and workflows across all those platforms will be sent to Databricks in real time,\u201d he said.<\/p>\n
Suncorp has also assembled \u201ca controls library of about 100 different controls across different types of AI applications and for different types of risks.\u201d<\/p>\n
While parts of the claims process are becoming automated and agentic, humans remain involved, from where intake of a claim becomes too complex for an agent to handle, to reviewing claims that an agent determines should be rejected.<\/p>\n
\u201cWe do want a human gate there, where all the rejected claims may have to go through a mandatory human review,\u201d Nekkalapu said.<\/p>\n
Claim coverage<\/p>\n
Nekkalapu said that Suncorp is working on \u201ccomplex agents\u201d that can \u201cdetermine whether a claim should be covered or not.\u201d<\/p>\n
It\u2019s not clear if this is the \u201csystem of agents\u201d referred to in the reference design or not.<\/p>\n
\u201cThere could be a claim where there was a storm last night and a tree fell on the retaining wall, damaging a pipe that’s running next to the wall, so that water seeped into a garage and damaged all the carpets and rugs in the garage,\u201d he said.<\/p>\n
\u201cThat is a contents insurance claim. But if you are looking at coverage, you need to identify what the loss cause is for that event, and based on that, you determine coverage.\u00a0<\/p>\n
\u201cIt could be the storm, it could be water leakage, or it could be the impact of the tree falling. It’s not an easy problem [to solve]\u00a0<\/p>\n
\u201cOur claims handlers spend a lot of time [on this], and it could be complex.\u201d<\/p>\n
He added: \u201cWe’ve developed a workflow with agents in there which can do all these jobs with 99 percent accuracy.\u201d<\/p>\n
Observing agentic performance<\/p>\n
Nekkalapu added that the Databricks-based observability platform that Suncorp has built is intended to produce different views of agentic workflow performance for different types of internal users.<\/p>\n
\u201cWe may have senior leadership and executives who are interested in how the whole program is running, so there are certain metrics that they want \u2026 and they would be able to get those insights through the dashboard,\u201d he said.<\/p>\n
\u201cOur safety team wants to see whether [the application of risk] controls are effective or not.\u00a0<\/p>\n
\u201cBusiness users want to see why a certain decision was made on the claim, and engineers want to see pretty much everything, but at the same time, they also want to debug it when something goes wrong, and it should not take very long.\u00a0<\/p>\n
\u201cSo, we built a dashboard and added [Databricks] Genie Code to that so that it can provide insights at different levels based on who is asking the question.\u201d<\/p>\n
Nekkalapu said that teams building agentic workflows within Suncorp would have access to the dashboard that \u201cshows how the program is running, how a use case is running, how an agent is running with little different levels of detail\u201d, and a chatbot to interrogate an observation of an issue.<\/p>\n
\u201cA chatbot could be the first level [of support] where they would ask questions, and they would get the answers and all the analysis in real time,\u201d he said.<\/p>\n
Ry Crozier attended the Databricks Data+AI Summit in San Francisco as a guest of Databricks.<\/p>\n","protected":false},"excerpt":{"rendered":"Suncorp will have five AI agents handling various tasks or \u201csub-processes\u201d in insurance claim processing as soon as…\n","protected":false},"author":2,"featured_media":752780,"comment_status":"","ping_status":"","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[20],"tags":[256,254,255,64,63,105],"class_list":["post-752779","post","type-post","status-publish","format-standard","has-post-thumbnail","category-artificial-intelligence","tag-ai","tag-artificial-intelligence","tag-artificialintelligence","tag-au","tag-australia","tag-technology"],"_links":{"self":[{"href":"https:\/\/www.newsbeep.com\/au\/wp-json\/wp\/v2\/posts\/752779","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=752779"}],"version-history":[{"count":0,"href":"https:\/\/www.newsbeep.com\/au\/wp-json\/wp\/v2\/posts\/752779\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/www.newsbeep.com\/au\/wp-json\/wp\/v2\/media\/752780"}],"wp:attachment":[{"href":"https:\/\/www.newsbeep.com\/au\/wp-json\/wp\/v2\/media?parent=752779"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.newsbeep.com\/au\/wp-json\/wp\/v2\/categories?post=752779"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.newsbeep.com\/au\/wp-json\/wp\/v2\/tags?post=752779"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}
![\"Suncorp](\"https:\/\/www.newsbeep.com\/au\/wp-content\/uploads\/2026\/06\/1782128718_340_ImageResizer.ashx.jpeg\")
<\/p>\n![\"\"\/](\"https:\/\/i.nextmedia.com.au\/News\/Suncorp_ref_design.jpg\")
<\/a><\/p>\n