Strata-K lets AI write rules, then checks them before use
Strata-K is a logic language where an AI model turns an English policy into rules, and a compiler plus a checks and runs those rules. For example, a policy like “do not clear a trade if any owner within two hops is sanctioned” can be translated into rules, then checked for mistakes such as using a name that was never defined. The checker returns stable , the exact source location, and sometimes a fix that another program can apply automatically.
After the rules pass checking, the engine runs them in a predictable way and can return the full reason why a result is true. The current code is a CPU reference in Rust. It supports stratified Datalog, negation, aggregates, stable models, and exact .
The planned feature that treats AI models as predicates inside the type system is designed but not built yet. The code uses MIT/Apache licensing.
Key points
- An AI model drafts rules from plain English policies, then a compiler checks them.
- Errors include stable codes and source locations, which can help automated repair loops.
- Checked rules run through a , so results are predictable.
- The engine can show the full reasoning behind a result for audits.
- The Rust supports Datalog and today.