Mmarcuscheninvoicelatency.hashnode.dev·Aug 19 · 7 min readThree weeks before the enterprise contract, the voice agent wasn't operator-readyLook. We had 99.2% uptime in staging. We had eval coverage on 1,400 test turns. We had latency under 280ms first-token. We were not operator-ready. I know this because the enterprise pilot started on 00
Mmarcuscheninvoicelatency.hashnode.dev·Aug 18 · 3 min readYour ASR confidence score is a number you can act on. We were throwing it away.Voice agents treat the transcript as ground truth. The speech recognizer often tells you it is not sure, and we were ignoring it. TL;DR: When I went back through a month of "the agent did the wrong th00
Mmarcuscheninvoicelatency.hashnode.dev·Aug 13 · 13 min readThe call failed on turn nine. My eval gave me one number for the whole call.The transcript was fourteen turns long and the score was 0.62. That is the entire output. One float, one call, and a rubric that said something like "did the agent resolve the customer's issue." It di00
Mmayaanderssoninllmasajudge.hashnode.dev·Jul 1 · 7 min readI reviewed six "operator-ready" checklists for AI agents. None of them define the problem correctly.The industry has converged on a definition of "operator-ready" that is measurable, deployable, and wrong. The most cited frameworks, Anthropic's "Building Effective Agents" (December 2024), Hamel Husa00
OOmnithiuminomnithium.hashnode.dev·Jun 1 · 14 min readAI Agent Drift Detection: Monitoring Model Decay in ProductionIntroduction AI agents are no longer experimental curiosities, they’re core components of production systems, orchestrating workflows, making autonomous decisions, and interacting with users in real t00
OOmnithiuminomnithium.hashnode.dev·Jun 1 · 13 min readAgent Hallucination Detection and Mitigation in ProductionThe hallucination problem moves from chat to agents When a customer support chatbot invents a refund policy, the damage is usually contained: a confused user, an escalation, a corrected response. But 00