11 min read
Audit evidence a verifier can check offline
How a hash-chained ledger with per-event Ed25519 signatures and OSCAL export produces audit evidence an external verifier can confirm independently.
- audit
- ledger
- OSCAL
- Ed25519
- compliance
Topic
audit
Explore audit articles from the Olivares AI blog on self-hosted governance, security and operations for enterprise AI agents.
6 min read
What your AI agents can actually reach: mapping agent access on real infrastructure
An AI agent holds credentials, is permitted some actions, and is observed doing others. The access map shows the gap — and where least-privilege quietly broke.
- agent-access
- least-privilege
- observability
- audit
6 min read
Auditing Claude Code and MCP servers in self-hosted environments
Build an auditor-grade trail for Claude Code and MCP servers without leaving your perimeter: per-agent identity, a hash-chained ledger, untrusted MCP signals.
- MCP
- Claude Code
- audit
- self-hosted
6 min read
Least-privilege drift: catching over-privileged AI agents before an incident
How to spot least-privilege drift in AI agents by comparing permitted access with observed behavior and enforcing policy at access time.
- least-privilege
- ai-agents
- policy-as-code
- audit