Logless: Privacy-preserving AI product analytics

Product teams need to understand how people use their personal AI assistants (e.g. ChatGPT, Muse, Grok Bot) and where they struggle, without breaching user privacy by opening individual chat transcripts. “Loggy” is a sanboxed AI agent that progressively summarises user data and extracts higher-level insights into a use cases taxonomy. A product manager asks a question in plain English. Loggy (powered by GLM 5.3) plans the analysis and separately writes two programs. Each runs in a fresh gVisor container on a separate Vultr sandbox VM. The containers have no network or model keys and use a read-only root. Before Logless shows an answer, a gate rejects per-person output, checks it against the published map, and requires both programs to agree. A presenter can also pair a phone by QR code and ask Logless questions remotely. NetBird gives each session a PIN-protected URL, routes it to the Vultr app over WireGuard, and deletes the URL when the session ends. The demo uses public WildChat data (~1M agent trajectories).