A capability of New Relic AI Observability that uses an asynchronous LLM-as-a-judge service to score live telemetry, such as for hallucinations and prompt injections, and attaches those scores to traces beside infrastructure and cost data.
Our description, from the vendor's documentation, as of 2026-11-11; reasoned from those pages, not observed running.
Rendered 2026-11-11
| Fact | Answer |
|---|---|
| Layer | Testing agent output (main layer) |
| Forms | hosted service |
What the maker's own pages said on the dates shown, not a compliance determination.
Our reading of vendors' pages, as of the dates shown. Confirm on the vendor's page before relying on any line that cites it. To report an error write to report@crinaro.ai