Overview
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).
Note: the demo URL is substituted with the GitHub repository link.
Tech stack
No comments yet
Be the first to comment on this project.
sentinel
Full-Stack Self-Healing DevOps & Security Copilot The Concept: An AI operations engineer that doesn't just suggest code fixes—it monitors cloud infra, detects uptime/security drops, automatically provisions fixes, and generates audit reports for enterprise compliance.
Agency Compiler
Agentic creative project compiler. Most creatives, agencies and designers dont know how to use ai, none the less agents. We created a platform that allows a creative agency or studio owner to instantly spin up agents based on the project ask, resources and scale.
ProofRun
ProofRun helps developers answer a critical question before shipping: will this update break behavior users rely on? An AI agent inspects two Git revisions, designs targeted experiments, and proposes repairs. An independent Docker-based verifier runs those experiments against both versions, preserves the original tests, and checks whether the repair actually works. Developers receive an update, skip, or postpone recommendation with recorded evidence and a reviewable patch. In a live synthetic…