Selector's NFD40 Pitch: Transparent AI Observability with Full Audit Trails
By
Tony Mattke
2d ago· 12 min readenNews
100/100
Golden Brown
Bagelometer↗
Slow-proofed and worth the wait. Worth its weight in flour.
Score100TypenewsSentimentpositive
Summary
Selector presented at NFD40 with an observability platform that emphasizes transparency and auditability over black-box AI recommendations. Unlike typical AI-powered observability tools that ask users to trust opaque model outputs, Selector's system provides explicit reasoning chains for every recommendation, shows which MCP tools the agent consulted, and allows users to trace conclusions back to raw metrics with one click. The core value proposition is the audit trail rather than the dashboard itself.
Key quotes
· 4 pulledEvery recommendation traces back through an explicit reasoning chain.
Every chat-bot answer shows which MCP tools the agent consulted, in what order, to get there.
Every conclusion is one click from the raw metric that triggered it.
The product isn't the dashboard. The product is the audit trail.
Most “AI-powered observability” pitches you sit through ask you to trust the model. The dashboard says the cloud gateway is the problem, the chat box says open a ticket with your circuit provider, …
