Almas Hilman Muhtadi

This project sits at the intersection of software engineering, state-of-the-art AI agent  

technology, and healthcare, addressing key industrial and clinical challenges in hospital report  

automation. Through close collaboration among clinical, product, and technical stakeholders,  

we are developing ARCi (Agentic Rule Creation System). This AI agent framework empowers  

clinical application specialists to generate clinical rules directly from clinical specifications,  

turning a complex rule-creation process into a streamlined process.

The main challenges I solved in this project were that general AI models aren't trained on  

building clinical rules using domain-specific language, and that each hospital uses its own  

terminology and guidelines. So the main challenge was steering AI agents to write technically  

correct, consistent clinical rules in a precise format amid changing context. The workflow  

therefore had to let the agents check and fix their own output. We also had to monitor output  

quality each time we tuned the agents.

The project delivered ARCi as an early-stage proof of concept. Agent skills hold the technical  

expertise, and the agents base each rule on a hospital-specific clinical guideline and a tool that  

resolves each hospital's terminology. Through a UI, the application specialists keep control of  

the result. To monitor quality, an evaluation pipeline scores agent performance and how closely  

its generated code matches a human reference rule. This score tracks agent performance over  

time.

The final result is ARCi, which can produce clinical rules at least 6 times faster and 30 times  

cheaper than the manual process. This removes rule-customization bottlenecks and enables  

scalable automated reporting across hospitals. This lets clinicians produce higher-quality  

reports faster, directly improving overall patient care.