Rainfed lowland rice production in lower Northeast Thailand is a complex and adaptive farming activity. Complexity arises from interconnections between multiple and intertwined processes, affected by harsh climatic and soil conditions, cropping practices and labor migrations. Having faced a spatially heterogeneous and dynamic environment for centuries, local rice farmers are very adaptive and are used to adjusting their behavior in unpredictable climatic and economic conditions. Better understanding is needed to manage the key interactions between labor, land and water use for rice production, especially when major investments in new water infrastructure are now being considered. Based on the principles of the iterative and evolving Companion Modeling (ComMod) approach, indigenous and academic knowledge was integrated in an Agent-Based Model (ABM) co-designed with farmers engaged in different types of farming practices over a period of three years to create a shared representation of the complex and adaptive social-agroecological system in Ban Mak Mai village, in the south of Ubon Ratchathani province. The ABM consists of three interacting modules: Water (hydro-climatic processes), Rice, and Household. "Household" is a rule-based agent; it makes daily decisions based on its available means of production, taking into account the stage of the rice crop, and water and labor availability. Key decisions made are related to: i) rice nursery establishment, ii) rice transplanting, iii) rice harvesting, and iv) migration of household members. The spatially explicit model interface represents a virtual rainfed lowland rice environment as an archetypical toposequence made of upper to lower paddies in a mini-catchment farmed by 4 different households, and also includes water bodies and human settlements. Thanks to intensive communication, the participating farmers, made sure that the ABM adequately represents their rice farming and labor migration management practices. They fou