Research

Technical work on policy-gated agent execution, human authorization, provenance, attestation, and reconciliation. We publish working papers, experiments, architecture notes, and implementation reports — including limitations and negative results.

Type

All Architecture note Experiment Implementation report

Topic

All Policy and consequential-action classification Connector and enforcement design Prompt-injection containment Attestation and provenance Human authorization Execution reconciliation Agent assurance and certification

1 publication · Clear filters

Implementation report10 August 2026

Binding human approval to an exact proposed change

An approval link is only meaningful if it authorizes one change, once. We found our single-use enforcement was split across two statements and did not hold under concurrency, and rewrote it as one atomic predicate.

Caretaker ResearchHuman authorization Attestation and provenance