Cloze: An Open Research Platform for Studying Human-AI Conversations in Mental Health Contexts

2026-06-12

AI Summary

This study addresses critical limitations in current consumer-grade large language models—namely, insufficient experimental control, inconsistent data export capabilities, and the absence of standardized safety mechanisms—which hinder their utility in human–AI dialogue research for mental health applications. To overcome these challenges, the authors present an open-source web platform deployable on both cloud and local infrastructure, enabling unified access to multiple models, including those from OpenAI, Anthropic, Google, and locally hosted Ollama instances. The platform supports configurable system prompts, scheduling, and safety constraints, while ensuring end-to-end data provenance and complete contextual logging. This infrastructure establishes, for the first time, a highly controllable, privacy-preserving, and reproducible experimental environment tailored to empirical research on AI-mediated mental health interactions.

Abstract

Cloze is an open-source web platform for conducting controlled, monitored studies of human-AI conversation in mental health research contexts. Consumer large language model (LLM) products such as ChatGPT, Claude, and Gemini are built for individual productivity, and offer researchers little experimental control, inconsistent data export, and no shared safety scaffolding that holds across providers. Cloze gives research teams a single environment in which they configure which models participants converse with, how the AI is instructed, how conversations are scheduled over time, and which safety constraints apply unconditionally, while every message is captured with full provenance (model version, prompt configuration, timing). The platform currently supports OpenAI, Anthropic, Google, and locally hosted open-weight models served through Ollama behind a unified interface, and runs in the cloud or fully on premises so that participant data need never leave an institution. Cloze is research infrastructure for building an evidence base on human-AI interaction in mental health contexts. It is not a therapeutic product.

Problem

• human-AI conversation
• mental health research
• experimental control
• safety constraints
• research infrastructure

Innovation

• human-AI conversation
• mental health research
• controlled experimentation
• safety scaffolding
• open-source research platform