This paper introduces Automated Institutional Discovery (AID), a novel computational framework that conceptualizes economic institutional design as a high-dimensional combinatorial search problem. Traditional institutional design relies heavily on human intuition, historical evolution, or analytically constrained mechanism design, which often fails in complex, adaptive multi-agent environments. AID transcends these limitations by framing institutions as tuples i = (r_1, r_2, ..., r_K) within an expansive institutional space and utilizing advanced search and optimization algorithms to discover configurations that maximize global objective functions F(i). By combining multi-agent simulation modeling with metaheuristic search strategies, AID evaluates allocative efficiency, incentive compatibility, resilience, and distributional equity without requiring empirical laboratory experiments. The framework establishes a paradigm shift from manual rule-making to automated machine discovery, offering robust applications for digital economies, decentralized finance, and economic governance.
Consumers facing home-renovation quotes operate in a classic credence-goods market: they cannot readily verify whether a quoted price is fair, and general-purpose large language models (LLMs) are now a zero-cost place to ask. Whether LLM answers are actionable for this purpose is untested. Demand-side benchmarks exist for medical, legal, and financial advice, but not for construction costs. We present, to our knowledge, the first consumer-question benchmark for construction costs. Forty Japanese renovation-price questions were posed to frontier LLMs, with repeated-trial sets measuring output stability. A matched re-run at bare provider defaults with a current frontier model (gpt-5.5) was added to remove a settings confound present in the original configuration. Two findings are robust across models, generations, and settings: no LLM answer contained an explicit over-charge decision threshold, and repeated runs of the same question returned materially different price figures. Within-answer price spans are also wide, with a median of 10x under bare defaults. A deterministic structured engine over an open cost database is included as an existence proof that a citable reference layer is constructible. Its consistency is a design property and its accuracy is not validated here; validating it against completed real-world quotations is the next study. All questions, raw outputs, harness, and scoring code are public.