An important area in the field of digital financial services is the use of AI-driven banking chatbots. The growing integration of AI-driven chatbots in banking has transformed customer interaction, yet the factors influencing users’ adoption intention remain underexplored, specifically understanding how post-adoptionbeliefs and user experiences shape behavioural intention. This study proposes a comprehensive research model which is grounded in the Unified Theory of Acceptance and Use of Technology (UTAUT) and the Expectation-Confirmation Model (ECM), and which is uniquely extended with the constructs of trust and perceived security, both crucial in high-risk, technology-mediated financial environments. The research examines the role of the mediating variables of perceived usefulness, satisfaction and trust with respect to each influencing adoption intention by utilizing the Partial Least Squares Structural Equation Modeling (PLS-SEM). Findings include that perceived usefulness mediates the effects of confirmation of expectations and perceived ease of use on adoption intention, while trust mediates the influence of confirmation of expectations, perceived usefulness, perceived security and facilitating conditions. By providing a nuanced understanding of chatbot adoption dynamics, the study advances both theory and practice. Financial institutions can successfully implement intelligent banking technologies by using the actionable insights it offers to increase user acceptance of conversational AI tools.