Heuristics have long been viewed as simple decision rules that sacrifice optimality for cognitive efficiency. However, this perspective fails to fully account for their effectiveness in complex, real-world environments. This paper proposes a novel framework that reinterprets heuristics as likelihood-free approximations to Bayesian inference, bridging the gap between heuristic and normative approaches to decision-making. We argue that many heuristics can be understood as implementations of Approximate Bayesian Computation (ABC), where observed data are compared to summary statistics of mental simulations (or prior experiences). This view situates heuristics within a probabilistic framework, explaining how they can represent uncertainty and adapt to environmental structure. Our approach addresses three key challenges in the field: It relaxes strong assumptions about cue-target relationships in heuristic models, accounts for implicit uncertainty representation in heuristic decision-making, and provides a more appropriate benchmark for evaluating heuristic performance. To demonstrate the practical applicability of our framework, we present a detailed case study reanalyzing data from a continuous-time causal learning experiment (Gong and Bramley, 2023). In this study, participants inferred causal relationships between components based on temporal patterns of activations. We show that an ABC model using simple count-based summary statistics can capture human judgments as well as, or better than, both normative Bayesian models and previous heuristic accounts. This case study illustrates how our framework can explain human performance in complex inference tasks using computationally tractable heuristics. By unifying heuristics and Bayesian inference through the lens of likelihood-free methods, this work provides a more nuanced understanding of human decision-making, and provides a bridge to the literature on inference-by-sampling.