Python, Git, agentic systems, evaluation frameworks, human-in-the-loop review workflows, labeling guidelines, taxonomies, error recovery, planning, grounding, synthetic scenario generation, tool-calling behavior, Data Analysis, evaluation rubrics, prompt engineering, quality action sequencing, annotation schemas

Git, Python, Data Analysis, conversational AI, annotation programs, taxonomies, labeling guidelines, evaluation rubrics, prompt engineering, annotation schemas, LLM applications, workflow automation, evaluation frameworks, AI evaluation, synthetic scenario generation