In an age of life-long learning, it is important that adult learners can effectively use their motivation and resources to reach their learning goals. In conversation, coaches can intervene to promote learning goal attainment by using behavioural change techniques (BCTs). In a coaching chatbot, such techniques can be ordered in an established, structured way to good effect. With recent technological advances, chatbot responses can be generated adaptively; this means that BCTs can be applied in an adaptive but less structured way. It is yet unclear whether this latter form of configuring coaching interventions is viable, how they compare to more established structured interventions, and whether both methods can be combined. For the purpose of answering this, we propose a 2x2 experimental design with the two intervention types as factors and goal attainment as the dependent variable. Results will indicate avenues for automating skilled conversation including choice of technology.