This paper presents iAIML, a mechanism to treat intentional information based on AIML, a state-of-the-art technology in chatterbot development. Our main goal was to improve dialogues with AIML chatterbots. iAIML adds structure to AIML bases, incorporating intentions and rules used in sentence interpretation and generation. We adopted as linguistic base the Conversational Analysis Theory (CAT), which considers intentionality in adjacent pairs in dialogue, facilitating the establishment of consistent dialogues between chatterbots and users. Tests with the implemented solution showed feasibility of the proposed approach. This is an original work with several contributions, such as the innovative and effective use of CAT, and a consistent modular structure of the iAIML base, favoring reuse and maintenance.