From Prompt Engineering to Harness Engineering: Building Observable and Governed GenAI Systems

with Lakshmi Devi Prakash

About This Session

As Generative AI moves from prototypes to production, prompt engineering alone is no longer enough. Developers now need a broader engineering layer around prompts, models, retrieval, tools, agents, evaluation, logging, safety checks, and observability. This session introduces Harness Engineering as a practical approach for building reliable and governed GenAI applications. Through enterprise-style architecture patterns, the talk explains how teams can add traceability, prompt/version control, metadata logging, policy checks, evaluation loops, and monitoring to GenAI systems. Attendees will leave with a practical blueprint for moving GenAI applications from experiments to production-ready systems.

Topics

Generative AI (GenAI)
Governance
LLMOps
Observability
Prompt Engineering
Retrieval-Augmented Generation (RAG)

← Back to Sessions

Speaker

Lakshmi Devi Prakash

VP, Applied AI/ML Lead · JPMorgan Chase

Vice President, Applied AI/ML Lead | GenAI Governance, Risk & Enterprise AI Security

Read bio Hide bio

Lakshmi Devi Prakash is a Vice President and Applied AI/ML Lead with over a decade of experience across Generative AI, NLP, machine learning, model observability, and enterprise AI adoption. Her work focuses on building production-ready AI systems for regulated environments, with emphasis on GenAI governance, risk intelligence, workflow automation, auditability, and responsible AI implementation. She has led and contributed to enterprise-scale AI/ML initiatives involving Generative AI solutioning, operational workflow automation, anomaly detection, sentiment analysis, and predictive modeling. Her current interests include secure GenAI observability, AI provenance, model risk, agentic AI governance, and practical frameworks for trustworthy AI adoption. Lakshmi is also a PhD scholar in Generative AI, specializing in multimodal distillation and advanced AI systems. She has authored two technical books, published seven international research papers, holds a patent in AI-driven software automation, and has earned 140+ global certifications across AI, cloud, and machine learning. She serves as an academic contributor and speaker, regularly delivering sessions on Generative AI, Agentic AI, vector search, and enterprise AI architecture.ng to curriculum design and mentoring in AI/ML and Generative AI. As a thought leader and community contributor, she writes Medium blogs on Generative AI, Agentic AI, and applied ML, and frequently delivers expert talks and workshops, empowering thousands of learners.