Pragya Keshap
Pragya Keshap is a Technical Architect with more than 18 years of experience designing enterprise, cloud-native, and AI-enabled systems. She is a Google Developer Expert in Google Cloud and a Docker Captain.
Her work focuses on distributed systems, containers, Kubernetes, cloud security, API platforms, generative AI, and reliable agentic architectures. She has designed and led large-scale technology initiatives in the financial-services industry and regularly writes and speaks about building secure, observable, and production-ready AI and cloud-native systems.
Pragya’s technical articles have appeared in publications including InfoQ, O’Reilly Radar, DZone, Cloud Native Now, and HackerNoon. She has also presented at developer communities and technology conferences on Docker, Google Cloud, AI agents, confidential computing, and cloud-native architecture.
Session
Modern AI agents are becoming increasingly capable, but reliability often gets worse as we give the LLM more tools, more decisions, and more responsibility.
This talk explores a different approach: designing agentic systems by deliberately reducing what the LLM has to decide.
We will look at three practical architecture patterns. First, how tool abstraction can reduce the decision surface by exposing meaningful capabilities instead of dozens of low-level APIs and MCP tools. Second, how to define reasoning boundaries—using deterministic code and rules where results can be computed, and reserving LLM reasoning for places where interpretation is genuinely required. Finally, we will look at how to evaluate these systems layer by layer instead of judging only the final response.
Along the way, we will cover structured evidence, typed contracts, failure boundaries, recommendation versus execution, and when LLM-as-a-judge is—and is not—the right evaluation technique.
Attendees will leave with a practical framework for deciding what the LLM should see, what it should decide, and how each part of an agentic workflow should be tested.