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

Experiment10 August 2026

Reconciliation at the merge boundary

Approving a change and executing a change are separate events, and nothing structural forces them to match. We recompute the diff from the provider's own API at merge time and block on mismatch — and the first honest run failed.

Caretaker ResearchExecution reconciliation Attestation and provenance