34 agents in this category
Analyses interview recordings for authenticity (reading/recited vs spontaneous). Advisory delivery signal — not a hiring verdict or proof of misconduct.
One-shot probe for sqlite-vec behaviour inside a cubby. Delete after use.
Per-model health probes for the NLP pipeline (ASR / LLM / embedder / diarization / SER). One event → one model call → one cubby row. Backs the Kuma "NLP Pipeline" dashboard rows.
Turns a recorded sales call into an advisory coaching read — talk-ratio, discovery, objection handling, and whether a next step was secured, each traceable to a quoted moment. Advisory coaching signal only — never a performance rating or proof of anything.
Interview-recording authenticity + delivery analysis, shared with the SolveIT team for QA/dev collaboration. Same engine as the Hiring Coach lab, republished under SolveIT's Agent Service.
No description provided.