cc2-research-framework

A structured research workflow applies a formal seven-function framework—OBSERVE, REASON, CREATE, ORCHESTRATE, LEARN, VERIFY, DEPLOY—to coordinate parallel streams, property-test assumptions, and integrate findings for reproducible inquiry.

Category theory in research workflows provides formal categorical laws to validate assumptions and guide meta-prompting. It structures reasoning and artifact creation to ensure property-tested, reproducible outcomes across multiple parallel streams.

Apply the research cycle by observing workspace state, reasoning to identify gaps, creating artifacts, orchestrating parallel streams, learning extracted patterns, verifying categorical laws, and deploying integrated findings into the broader workflow.

Yes, a categorical research framework requires a Python 3.x environment with standard libraries to execute the seven-function cycle, run property testing, and manage structured reasoning across parallel research streams.

The best way to verify categorical assumptions is applying property testing during the VERIFY phase, validating that categorical laws hold true before deploying findings into the broader research framework and downstream workflows.

Avoid a formal categorical framework for small-scale, ad-hoc AI tasks lacking structured reasoning or parallel streams. Its overhead suits complex, reproducible inquiry requiring coordinated orchestration and property-tested categorical assumptions.