SmartState

SmartState was designed to improve the efficiency, quality, and impact of research studies involving human participants. It is a state-based system that acts as a personal agent for each participant, continuously managing and tracking their unique interactions. It consists of four main components: a messaging service, a state machine, a conversational AI, and a web-based platform.

Key Features

• Automated management of participant interactions, communications, and data collection reduces workload on researchers and prevents errors
• Finite state machines (FSMs) track participant progress and ensure adherence to study protocols — paths are fixed and cannot be deviated from
• Integration of a large language model (Meta Llama 3.1 Instruct) to facilitate natural language interactions with participants
• Web-based platform for researchers to access all functionality, participant logs, reports, and messaging utilities
• Increased scalability and efficiency for large studies
• Detailed auditing capabilities to trace a participant's exact path through a study
• NIST SP 800-53 and HIPAA-compliant data center, all data encrypted in transit and at rest
• Automatic state saving to stable storage every 15 minutes

How It Works

SmartState follows protocol-driven workflows that dynamically adapt based on user input. At its core, SmartState uses FSMs to track participants' progress. At each step, specific conditions must be met for a transition to occur. This process is automated using a web-based compiler called Umple, which generates FSM code and graphs. The LLM uses external functions via tool calling to check if a response is adequate and add additional context.