Sai Rakshit Yerram
Staff Software Engineer
Atlanta, Georgia, United States
Actions
Engineering Leader with over a decade of experience building scalable enterprise platforms, specializing in the architecture, security, and deployment of cloud-native, AI-driven engineering systems. Proven track record delivering secure, production-grade AI platforms, with deep expertise in RAG pipelines, LLM orchestration, multi-model routing, and agentic workflows. A hands-on visionary adept at pioneering AI applications across MLOps, LLMOps, advanced automated testing, and zero-trust security infrastructure to ensure robust, compliant, and highly available enterprise solutions.
Area of Expertise
Topics
Closing the Loop: How to Engineer Agents That Learn, Act, and Stay Accountable
Everyone is building AI agents. Far fewer are engineering the loop that makes an agent more than a clever one-shot prompt. The real power—and the real difficulty—of agentic systems lives in the feedback loop: perceive, reason, act, observe, learn, repeat. Get the loop right and you get systems that adapt, self-correct, and compound in capability over time. Get it wrong and you get runaway costs, infinite retries, silent drift, and confident-but-wrong actions at scale.
This session treats the agentic loop as a first-class engineering discipline. We'll break down the anatomy of a well-engineered loop—grounding agents in real signals, designing termination and escalation conditions, managing context and memory across iterations, controlling cost and latency per cycle, and building in human checkpoints for high-impact decisions. I'll use autonomous quality engineering as a concrete, battle-tested case study: agents that generate, execute, and self-heal work while reasoning over production telemetry, delivering measurable gains alongside real governance challenges. You'll leave understanding why the loop—not the model—is the unit of design, with practical patterns for building agentic systems that are reliable, observable, and accountable rather than impressive demos that fall apart in production.
Agentic Payments: When AI Agents Start Spending
AI agents are evolving from passive assistants into autonomous actors that can search, decide, negotiate, and execute commerce workflows. This shift introduces a new challenge: how can agents safely initiate, authorize, and manage financial transactions on behalf of users, businesses, and machines?
This session introduces Agentic Payments, an emerging infrastructure model for AI-driven commerce. We will explore the payment rails, protocols, identity systems, authorization models, risk controls, stablecoins, wallets, and compliance patterns needed to support agent-led transactions. The talk will cover how agents can request payment permissions, operate within spending limits, verify merchants, use programmable money, trigger approvals, and maintain audit trails.
Attendees will learn practical design patterns for agentic commerce, including delegated authorization, policy-based spending, transaction risk scoring, human-in-the-loop approval, fraud detection, and stablecoin settlement. The session provides a roadmap for building secure, compliant, and scalable payment workflows for the next generation of autonomous digital agents.
Agentic Quality Engineering
AI adoption is outpacing the maturity of the practices used to test and secure it. Engineering and security leaders need concrete, platform-grounded patternsnot just principles — for assuring AI systems in production. This session delivers a vendor-aware but architecture-first framework grounded in peer-reviewed research and real enterprise adoption.
Agentic Quality Engineering
Agentic Quality Engineering: how autonomous AI agents generate, execute, self-heal, and prioritize software tests while reasoning over production telemetry. Drawing on my published research, I'll share a reference architecture, measurable benefits, a practical maturity model, and the governance guardrails nonprofit tech teams need to adopt AI-driven testing responsibly.
Please note that Sessionize is not responsible for the accuracy or validity of the data provided by speakers. If you suspect this profile to be fake or spam, please let us know.
Jump to top