Systems Correctness Practices at AWS: Leveraging Formal and Semi-Formal Methods

I've noticed that the formalization of methods described by AWS parallels what we need in technical documentation. Complex systems require not just formal verification but also structured documentation following MECE principles (Mutually Exclusive, Collectively Exhaustive).

In my experience, the interfaces between components (where most errors occur) are exactly where fragmented documentation fails. I implemented a hierarchical documentation system for my team that organizes knowledge as a conceptual tree, and the accuracy of code generation with AI assistants improved notably.

Formal verification tools and structured documentation are complementary: verification ensures algorithmic correctness while MECE documentation guarantees conceptual and contextual correctness. I wonder if AWS has experimented with structured documentation systems specifically for AI, or if this remains an area to explore.

Could you explain how your "hierarchical documentation system" works? Does the tree parallel the code? Is there a particular tool that you use?

The hierarchical system I've developed organizes knowledge in nested MECE categories (Mutually Exclusive, Collectively Exhaustive). Rather than paralleling code exactly, it creates a conceptual tree that represents the mental model behind the system.

For example, in an e-commerce API: - Level 1: Core domains (Products, Orders, Users) - Level 2: Sub-domains (Product variants, Order fulfillment, User authentication) - Level 3: Implementation details (Variant pricing logic, Fulfillment status transitions)

I'm currently using plain Markdown with a specific folder structure, making it friendly to version control and AI tools. The key innovation is the organization pattern rather than the tooling - ensuring each concept belongs in exactly one place (mutually exclusive) while collectively covering all needed context (collectively exhaustive).

I should note that this is a work in progress - I've documented the vision and principles, but the implementation is still evolving. The early results are promising though: AI assistants navigating this conceptual tree find the context needed for specific coding tasks more effectively, significantly improving the quality of generated code.