Abstract Objective We aim to describe the development of a conversational agent (CA) for parenting, termed PAT (Parenting Assistant platform), to demonstrate how artificial intelligence (AI) can enhance parenting skills. Background Behavioral problems are the most common issues in childhood mental health. Developing and disseminating scalable interventions to address early‐stage behavioral problems are of high priority. Artificial intelligence (AI)‐based CAs can offer innovative methods to deliver parenting interventions to reduce behavioral problems. CAs have the capability to interact through text or voice conversations and can undergo training using evidence‐based parenting programs. However, research on CAs for parenting and behavioral problems is limited. Experience The development of PAT consisted of three phases: Phase 1 was purely rule‐based, Phase 2 was hybrid (rule‐based format plus large language models), and Phase 3 featured an agentic architecture. The latest version of PAT includes prompt engineering, guardrails, retrieval‐augmented generation, few‐shots learning, context, and memory management through agentic architecture. Although comprehensive empirical results are pending, the iterative development and enhancement of PAT indicate the potential for effective digital intervention. The agentic architecture of the latest version of PAT aims to provide robust, context‐aware interactions to support parenting challenges. Implications CAs have the potential to reach a broader population of parents and deliver personalized interventions tailored to their specific needs. Moreover, CAs are structured to provide timely support, which can enhance family dynamics and contribute to improved long‐term outcomes for both parents and children. Conclusion AI‐based CAs can be used as alternatives to waitlists; as digital cotherapists; and implemented in health care, mental health, and school settings. The potential benefits and risks of the different types of CA and features are discussed.
Stored only when both papers are in the corpus — 12 citations exist upstream.