Workstream 01
Scoped receipts, evidence levels, review, and dissent
AI Labs FutureWorks Research profile
Turning reviewed outcomes into scoped, challengeable lessons and executable controls.
A Compacitas research initiative
Precedent EngineInstitutional learning
Precedent Engine research examines the transition from an observed event to a reusable institutional lesson. The design preserves evidence, applicability, dissent, known failure modes, review, expiry, and reversal so a retained lesson can be challenged rather than treated as permanent truth. A proposed compiler turns accepted precedent into test cases, skills, policies, routing constraints, or escalation rules. The research tests whether this process reduces repeated failures and false inheritance compared with unreviewed reflection or consensus alone.
The research question
Research workstreams
Scoped receipts, evidence levels, review, and dissent
Compilation into tests, skills, policies, and routing constraints
Expiry, reversal, replay, and repeated-failure evaluation
Evidence priorities
The initiative is framed around testable questions. Its research direction should be assessed against observed evidence and the limits of each experiment.
Research goals and proposed mechanisms are not established findings. Product-linked tracks describe the research behind a capability, rather than a claim that its hypotheses have been validated.
Associated company
The verifiable civilization runtime for model governance, scheduling, optimization, and authorized compute federation.
Explore Compacitas
MultiplexCompacitas · Prototype
Scheduling many persistent agent identities across bounded model residency and physical compute.
AletheonCompacitas · Protocol in development
A controlled emergence ecology for testing persistent identity, history, diverse substrates, and governance needs.
Verifiable Civilizational LearningCompacitas · Proposed study
Testing whether verified experience can accumulate outside model weights and survive complete agent and model turnover.