What Evidence Should Internal Audit Request for a Generative AI Workflow?
Policies and application logs do not necessarily prove what happened in a specific AI-assisted outcome. This fieldwork guide explains the eight records internal audit…
-
Building a Realtime Voice Agent on Top of an MCP Tool Boundary
How a Spanish voice-agent prototype combines WebRTC, server-side tool execution, MCP legal search, and stale-turn handling without exposing retrieval internals.
-
-
You Can’t Whitelist Your Way to an Unattended Agent
Why we built pipe-down, an open-source Claude Code skill that keeps a coding agent inside its own permission allowlist. Start a coding agent on…
-
Most AI Risk in Regulated Companies Isn’t Model Risk
Why we built Audit Grill-Me, an open-source methodology for auditing AI-enabled workflows Ask a team in a regulated company to prove how one of…