Variational Information Pursuit (V-IP) is an interpretable-by-design framework that makes predictions by sequentially selecting a short chain of task-relevant, user-defined interpretable queries about the data that are most informative for the task. The selected query-answer chain serves as an explanation for the prediction. Applying the framework to any task requires (i) specification of a query set, and (ii) densely annotated data with query answers to train classifiers to answer queries at test time. This limits V-IP's application to small-scale tasks where manual data annotation is feasible. In this work, we focus on image classification tasks and propose to relieve this bottleneck by leveraging Foundation Models. Specifically, following recent work, we propose to use GPT, a Large Language Model, to propose semantic concepts as queries for a given classification task. To answer these queries, we propose a Concept Question-Answering network (Concept-QA) which learns to answer binary queries about semantic concepts in images. We design pseudo-labels to train our Concept-QA model using GPT and CLIP (a Vision-Language Model). Empirically, we find our Concept-QA model to be competitive with state-of-the-art VQA models in terms of answering accuracy but with an order of magnitude fewer parameters. This allows for seamless integration of Concept-QA into the V-IP framework as a fast-answering mechanism. We name this method Concept-QA+V-IP. Finally, we show on several datasets that Concept-QA+V-IP produces shorter query chains which are more interpretable and accurate than V-IP trained with a baseline CLIP-based answering mechanism.