Guardrail Architecture and Security Testing: IChatClient Middleware, Safety Evaluators and Red-Team Regression in CI
Guardrails are middleware placed in the right order in the IChatClient pipeline, with a deliberately chosen fail mode, re-measured with the same harmless red-team set on every model change. We build a kill switch and input and output guards, look at safety evaluators and our own IEvaluator, and show the xUnit set catching our canary-token approach breaking in two different directions when moving to gemma3:12b.
14 Nov 2026
·
26 min
·
4
