Sharath Thirunagaru
Founder - Qyoob AI - AI for Enterprise that's Private, MultiModal, Agentic
Franklin, Tennessee, United States
Actions
With over 15 years of experience, I have led teams in creating advanced AI systems across various sectors. In the P&C industry, I developed vision-based systems and NLP models to automate property reviews and predict home outcomes. My work in the Automotive, Payroll & HR, Financial, Telecom, Music, and Retail industries includes building predictive models using machine learning, implementing advanced vision modeling, and developing automation solutions to enhance efficiency and accuracy.
Links
Area of Expertise
Topics
From Static LLMs to Adaptive Agentic AI: Building with Tools, Memory & Experience
In this hands-on full-day workshop at the DataTuneConf, you’ll move beyond static LLM assistants and create intelligent multi-agent systems that evolve over time. We’ll start with building tool-enabled agents with memory, then deploy a production-ready agent with multi-turn capability, caching, and tracing. We’ll introduce the concepts of MCP and A2A protocols, and build agents that talk to each other with MCP servers like Knowledge-bases, Databases, ServiceNow, GitHub, Jira and more.
You’ll learn when it makes sense to fine-tune LLMs versus adopting memory-based continual learning so that your agents don’t stay static but improve after every interaction—without updating the LLM weights. We’ll also cover instruction-tuning and GRPO training for domains that demand tight control.
By day’s end you’ll walk away with the foundations, code examples, and best practices needed to build adaptive, tool-enabled, memory based multi-agent AI systems ready for real-world production scenarios.
From Static LLMs to Adaptive Agentic AI: Building with Tools, Memory & Experience
Most AI assistants today are static—they reset every time you talk to them. In this session, you’ll learn how to transform LLMs into adaptive, agentic systems that learn from context, memory, and experience.
We’ll walk through how to build a tool-enabled agent with memory, demonstrate how MCP (Model Context Protocol) and A2A (Agent-to-Agent) communication enable agents to collaborate, and show how they can integrate with real-world services like GitHub, Jira, or ServiceNow through MCP servers.
You’ll also see when it makes sense to fine-tune an LLM versus using memory-based continual learning so your agents can improve without retraining the model.
By the end of this session, you’ll understand the core patterns and trade-offs behind building adaptive, multi-agent AI systems that evolve over time—ready to scale from simple prototypes to production-grade architectures
Sharath Thirunagaru
Founder - Qyoob AI - AI for Enterprise that's Private, MultiModal, Agentic
Franklin, Tennessee, United States
Links
Actions
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