Works · Framework Demo
Treats trustworthiness as a system-level property that emerges from the interaction between security filtering, confidence handling, and downstream response control — not just a better model. A lightweight k3s-based pipeline layers prompt-injection defenses with calibrated confidence scores so resource-constrained SMEs can deploy customer-support RAG safely.
How it works
Routed through a lightweight k3s edge cluster into the pipeline.
Structured prompt filtering plus a pre-trained GenTel-Shield detector screen the query.
Relevant business documents are retrieved for grounded generation.
The LLM answers with a structured JSON output carrying a calibrated confidence score.
Low-confidence or blocked queries are escalated or rejected instead of answered.
Worked example
Illustrative example using representative data from the paper — not a live model call. Pick a scenario to see how the pipeline responds at each stage.
—
—
—