Series
How we test and grade Aiko, Gmango's realtime medical voice agent. Phase 1 builds the foundation: synthetic cold-consult cases, an AI patient and an LLM judge. Next come comparisons of several judges, clinician review, and body map integration, plus more along the way. Follow the series to see what works, what breaks and what the numbers get wrong.
Companion to How I Built an LLM-as-a-Judge Eval System for a Medical Voice Agent. In the main post I told the story. This is the reference shelf behind it: every patient we used, every score we got, a
Synthetic cold-consult cases, a patient script, an LLM judge, and where the judge went wrong. TL;DR: Aiko is our realtime medical voice agent, and until now we measured only its speed and cost, never
