Blog / AI & Agents

AI & Agents

AI agents in production: evals, error analysis, observability and what we learned running them with real clinics.

AI & Agents

AI agent observability vs. traditional software

Why monitoring AI agents is a different game: traces, a single LLM evaluator, human review and prompts treated as code — our day-to-day routine.

Kaique Nogueira · Apr 27, 2026 · 5 min

AI & Agents

How we doubled our agent's escalation accuracy with error analysis and manual annotation — and why LLM-as-a-Judge wasn't the way.

Lucas Rego · Feb 12, 2026 · 6 min