Featured research program
A two-phase research program investigating how persistent agent change can be governed through evidence lineage, deterministic advisory policy, append-only human adjudication, and explicit separation between recommendation and external-action authority.
Persistent agent change creates a governance problem: who controls the evidence, who judges the result, and who authorizes action?
Systems that propose changes should not automatically gain authority to select their evidence, certify success, erase contrary outcomes, or authorize external action. The research program therefore treats evidence lineage, adjudication, policy, and action authority as distinct governance surfaces.
Evidence boundary: Phase I defines the architecture and governance model. Whether the system improves reliably and safely over time is the subject of Phase II.
Two-phase program
Preliminary v0.11 observations will not be presented as Phase I evidence or completed empirical results.
Research resources