Show HN: Requirements Engineering with Formal Verification
Fizzbee.ai is a new open-source app that uses formal verification for requirements engineering. It asks follow-up questions, converts prompts into formal specifications to uncover gaps, generates validation scenarios, and produces a specification document for coding agents, aiming to produce working code in fewer iterations.
Background
Fizzbee is an open-source formal methods system. Formal methods are mathematically rigorous techniques used to specify, design, and verify software/hardware systems — they can prove that a system behaves correctly under all conditions, unlike testing, which only checks specific cases.
This new app (fizzbee.ai) applies formal verification to the requirements engineering phase: the process of defining what a system should do before building it. Instead of developers writing ambiguous natural-language specs that coding agents (AI code generators like GitHub Copilot, Cursor, etc.) interpret inconsistently, it turns requirements into precise formal specifications and validation scenarios.
The payoff: fewer iterations to working code, because the AI agent receives unambiguous, mathematically checked instructions. This sits at the intersection of two trends: the rise of AI coding agents (which are powerful but struggle with vague requirements) and a renewed interest in formal methods as a complement to LLM-based development.