AI Explained Lessons Learned from Building Agentic Systems With Jayeeta Putatunda
21 snips
Aug 16, 2025 Jayeeta Putatunda, Director of AI Center of Excellence at Fitch Group, shares her expertise on building AI agent systems. She dives into the hurdles of moving from concept to production, discussing critical evaluation metrics and the significance of observability in reliable AI. The conversation highlights the hybrid approach necessary for finance applications and the crucial developer-business partnership for customized metrics. Additionally, she examines the evolution from MLOps to AgentOps, unpacking new challenges in AI operational frameworks.
AI Snips
Chapters
Transcript
Episode notes
Prioritize High-Impact Use Cases
- Focus 80% on high-impact, low-effort use cases instead of chasing every new model or framework.
- Align efforts to business ROI to avoid building obsolete prototypes that waste time and money.
Generative AI Needs New Evaluation Metrics
- Generative systems produce rich, varied outputs that defy simple ML metrics like accuracy or recall.
- You must define specific, business-aligned evaluation criteria tied to measurable productivity or cost savings.
Two Agent Patterns And Finance Constraints
- Jayita described two agentic patterns: deterministic workflow-augmented systems and more autonomous reflection-based agents.
- She emphasized finance use cases often require constrained autonomy due to governance and accountability.