SMU's business orchestration and automation is powered by agentic AI

- Over 1,500 files uploaded across multiple formats

- Nearly 10,000 pages ingested

- Over 90% reduction in document screening time

Staff from the Singapore Management University’s (SMU’s) admissions office used to spend hours scrolling, copying, pasting, and double-checking student applications to identify qualified candidates. Wanting to speed up these time-consuming manual processes, it turned to automation.

But instead of alleviating the situation, new problems emerged. Automations frequently broke down due to minor user interface changes, leading to high maintenance effort and frequent disruptions.

The problem with typical AI agents is that while they can understand and process simple templated documents, they struggle to read documents that come in varying formats, or which contains elements like embedded tables, graphs, and inferred values.

What SMU needed was intelligent document processing, where agents can operate effectively in unstructured environments, tackle complex problems, and support variable, multistep workflows.

Having used the UiPath Platform at her previous workplace, Cassandra Jenna Bibal, Business Analyst and Automation Developer at SMU, knew that it was the answer. In February 2026, UiPath and SMU embarked on a partnership that yielded tangible outcomes within months.

Initially, SMU focused on the extraction of finance reports used for financial reconciliation, automating the highly manual and repetitive process. This improved accuracy, reduced processing time, and minimised manual intervention.

Convinced by the benefits, SMU gradually transitioned to end-to-end process automation and adopted UiPath Orchestrator and additional UiPath products to power their new AI digital assistant, known internally as the Document Screener.

Users can upload various types of documents, define their own screening criteria, and customise outputs, ranging from a PDF to a tailored Excel file with user-defined columns. The system then processes the documents, applies the specified logic, and automatically delivers the results via email.

Besides extracting key information from invoices and receipts, Document Screener can also reduce the time it takes for administrative staff to answer queries about admission processes, bursary applications, and scholarship applications.

“This marks a shift from traditional automation to more intelligent, user-driven workflows. Document Screener can dynamically interpret inputs, adapt to different document types, and generate tailored outputs with minimal human intervention,” said Bibal.

Tasks that took hours can now be completed in minutes while human errors in data handling have decreased. The flexibility of being able to upload any document, customise outputs, and receive results automatically has made Document Screener intuitive and valuable across different teams. 

With more time to focus on more analytical and value-added activities, staff were quick to embrace the tool. 

Operational efficiency gains

Because manual and repetitive tasks such as finance report extraction now take minutes instead of hours, staff can redirect their time towards analytical and value-added work.

Scalable, intelligent automation

The evolution from task‑based automation to agentic AI solutions like the Document Screener allows SMU to transition to adaptive, user‑driven workflows. This means different teams can customise outputs and handle diverse document formats.

Rapid user adoption and future readiness

The intuitive design of the UiPath Platform led to faster-than-expected uptake. In the next phase of its journey, SMU aims to embed UiPath agentic AI capabilities into Copilot-style agents, which will allow users to interact with a bot in a more natural and intuitive way. 

For example, users of Document Screener would be able to instruct AI agents to execute follow-up actions like sending calendar invites or notifications without having to switch systems or manually initiate processes. 

The potential to move beyond rule-based automation into more context-aware and proactive systems is what truly excites the university about UiPath agentic AI capabilities. By combining conversational interfaces with automation workflows, users could retrieve insights and act on them instantly. 

“Ultimately, we see this as a step towards more intelligent, integrated automation ecosystems, where business users can interact with systems in a flexible, on-demand manner, while automations handle the complexity behind the scenes,” Bibal said. 

Comments

Post a Comment

Popular posts from this blog

NVIDIA brings secure agent workspaces and confidential computing to AI factories

As enterprise AI use cases move from chatbots to persistent, autonomous agents capable of reasoning, writing their own software tools, and executing complex cross-system workflows, demands on token generation fundamentally rewrite the enterprise model for security, compliance, infrastructure and cost.  To scale safely, organisations need AI factories  that are built for secure, trusted and efficient AI production. NVIDIA is supporting this trend with new reference architectures for  Secure Agent Workspaces ,  Confidential VMs and Confidential Containers .  Legacy IT security controls — static credentials, network allowlists and standard role-based access — were not designed for autonomous agents, NVIDIA said. Securing an AI factory requires a paradigm shift to runtime-enforced, policy-driven guardrails. Enterprises need secure agent workspaces — persistent, single-user environments accessed via enterprise single sign-on. Secure agent workspaces are governed by...
Read more

Fortinet enhances FortiRecon to align with CTEM framework

Fortinet, the global cybersecurity provider driving the convergence of networking and security, has turned the FortiRecon platform into a comprehensive solution aligned with the continuous threat exposure management (CTEM) framework. The latest release introduces expanded internal attack surface monitoring, adversary-centric dark web intelligence, and security orchestration, all in a unified platform. These enhancements help organisations proactively identify and prioritise real-world exposures, validate risks like an attacker would, and accelerate response. “CISOs and security teams are overwhelmed by growing attack surfaces and an endless stream of unprioritised alerts,” said Nirav Shah, Senior VP of Products and Solutions at Fortinet. “With the latest enhancements to FortiRecon , we’re giving organisations an attacker’s eye view of their internal and external exposures, backed by AI-powered threat intelligence from FortiGuard Labs, real-world validation, and automated response...
Read more

Agnes AI enters global top 10 AI lab rankings

- Agnes AI delivers globally-ranked agentic and image AI performance - Offers cost-efficient AI access for emerging markets - Supports national push to upskill tech professionals Agnes AI, a Singapore-headquartered AI model company that has built and trained its own multimodal foundation models entirely in-house, is now a top-10 lead across three independent AI benchmark rankings.  The company said its proprietary models have entered the global top 10 AI labs ranks. The latest rankings on Claw-Eval and Artificial Analysis follow a top-10 AI labs placement on PinchBench , a globally-recognised agentic model evaluation benchmark. According to the company, it is the first Singapore-born AI model company to enter the global top 10 across these international AI lab rankings. Agnes AI noted the benchmark results also provide independent validation that a Singapore-born AI lab can compete on the same global leaderboards as the world’s most-recognised AI companies. “Singapore’s ...
Read more