Command Palette

Search for a command to run...

GitHub

Research

Independent technical reports on AI agent reliability, security and privacy. Each report is archived on Zenodo with a DOI and comes with open code, synthetic data and a single command that reproduces every number in it.

An Exactly Solvable Pilot on Linked, Coarsened and Task-Output Releases, with a Release-Audit Toolkit

Multi-stage AI workflows often pass a few structured findings between stages instead of raw records. This study measures how much several such findings, combined, reveal about an attribute that none of them states, in a synthetic testbed where the best possible attacker is computed exactly. It ships release_audit, a standard-library toolkit that computes the same leakage budget and the best release designs for your own pipeline.

  • Privacy engineering
  • Attribute inference
  • Composition attacks
  • Data minimisation
  • AI workflows

A Hand-Checkable Conformance Suite for Agent Recovery with Provider Contracts and Webhook Evidence

When an AI agent's side-effecting tool call times out, the agent cannot tell whether the action happened. This deterministic, hand-checkable simulator scores retry policies against stale status reads and webhooks that arrive late, twice, out of order or not at all, under providers with and without idempotency-key deduplication. It ships a provider contract checklist, a decision table and commands to test your own scenarios and policies.

  • AI agents
  • Tool use
  • Idempotency
  • Retries
  • Webhooks
  • Distributed systems

A Matched-Pair Pilot on Verifying Consent from Masked and Aliased Logs

AI agent audit logs often have to be redacted before a reviewer sees them, yet the reviewer must still decide whether each recorded action was authorised. This matched-pair pilot measures which evidence a redacted log must keep for that decision. It ships redaction_audit, a standard-library toolkit that tests your own redaction schemes against your own authorisation policy.

  • AI agents
  • Audit logs
  • Redaction
  • Pseudonymisation
  • Privacy engineering