Rob Organ
Principal Engineer
Rob has worked at Synanetics for a total of 8 years and is a member of our commercial team. He is a full stack software engineer with over 25 years experience delivering integration, web, desktop, mobile and reporting solutions across both public and private sectors.
👉 Read Rob Organ's recent posts
More Than Just a Chat Bot
AI in healthcare is no longer just about chatbots. In this six-part series, we explore how AI, interoperability standards and healthcare applications can work together to create experiences that are trustworthy, accountable and built around the realities of clinical systems.Agents Are Users Too
AI in healthcare is no longer just about chatbots. In this six-part series, we explore how AI, interoperability standards and healthcare applications can work together to create experiences that are trustworthy, accountable and built around the realities of clinical systems.Citations Are Not Decoration
AI may help users find information more quickly, but it should not ask them to trust information blindly. This article explores how citations help connect AI-generated answers back to the patient record, enabling users to understand where information came from and verify it for themselves. As AI becomes increasingly integrated into healthcare applications, the ability to move seamlessly between generated answers and supporting evidence becomes ever more important. Citations are not simply a feature of the interface; they are an essential part of building trust in the information presented.The FHIR Knowledge Base
Healthcare organisations hold vast amounts of structured clinical information, but that does not necessarily mean it is easy to find, navigate or understand. As AI capabilities mature, there is growing interest in making healthcare records more accessible through natural language search and retrieval. This article explores the concept of a FHIR knowledge base: a semantic layer built upon healthcare interoperability standards that helps bridge the gap between structured clinical data and the questions people actually ask. It examines how AI and healthcare standards might complement one another, enabling richer search experiences while retaining the underlying record as the source of truth. Along the way, it considers some of the architectural, governance and user experience questions that emerge when healthcare data becomes searchable in new ways.Chunking Is The New Data Modelling
Traditional data modelling organises information into predefined structures. AI retrieval changes that assumption. This article explores why techniques such as chunking, embeddings and vector search are becoming equally important design considerations, and how healthcare organisations can combine them with standards like FHIR to create more effective AI-powered experiences.It Takes More Than One Agent
AI agents are often presented as autonomous assistants, but real-world healthcare workflows rarely fit neatly into a single agent model. This article explores why effective AI solutions depend on collaboration between specialised agents, orchestration services and governed workflows, and what this means for the design of healthcare applications.An Engineer's Perspective on Building AI-Ready Interoperability Platforms
In a previous post, I described how we created a semantic layer over FHIR to support AI-driven capabilities such as semantic search and risk stratification. The response prompted a number of follow-up questions, many of them less about AI itself and more about the architectural decisions behind it: Why use FHIR narratives? Why are embeddings useful? What role does retrieval play? Why does chunking matter? And what exactly changes when agents are introduced into the architecture?Structured Data Is Dead. Long Live Structured Data
There is no shortage of discussion about the opportunities that AI may create within health and social care. Modern language models appear increasingly capable of interpreting narrative, answering questions and identifying relationships across both structured and unstructured information. In a domain where information is often recorded and understood as a mixture of records, observations and stories, it is tempting to conclude that the way data is represented no longer matters. In other words, perhaps structured data is dead.Reflections on the Social Care Interoperability Platform Hack Day
The Social Care Interoperability Platform (SCIP) Hack Day brought together six digital social care record providers to test the practical realities of interoperability using a prototype federated integration platform deployed specifically to support the event. Working from a shared data model (MODS) and transforming to and from FHIR, teams were able to publish, retrieve, and consume synthetic data end-to-end within a single day.Announcements
We’re proud to introduce Symmetry, a new way to transform care planning into a strategic asset. 👉 Read more...
