Santosh Kumar Radha is Co-Founder and CTO of AgentField, an open-source infrastructure platform for running AI agents at scale. Previously, Santosh led product and engineering at Agnostiq, where he built Covalent, an open-source AI infrastructure platform for workflow orchestration that played a central role in Agnostiq's acquisition by DataRobot. His research focuses on LLM reasoning and agentic AI systems, scalable AI infrastructure, and AI governance and accountability. He holds a PhD in theoretical physics from Case Western Reserve University and a bachelor's degree from the Indian Institute of Technology (IIT).
Beyond the DAG: Building Agentic Workflows That Loop, Branch, and Scale
Friday, July 31, 2026
Online
About this event
Agentic systems don't run as a tidy pipeline - they loop, branch, retry, and call other agents, and that's exactly where most setups fall apart. This talk shows how to build scalable agentic workflows on AgentField, the open-source infrastructure for AI agents. Write each agent as a typed function and AgentField turns it into a production microservice: agents discover and call each other directly, share durable memory, and run long, looping, async workflows with no timeout limits and no orchestration glue to maintain. Santosh Kumar Radha (Co-Founder & CTO, AgentField) builds a multi-agent workflow live - reasoning that loops back and adapts instead of being forced into a fixed DAG. Apache 2.0; SDKs in Python, TypeScript, and Go.
Key Highlights
- Why "one orchestrator with every tool" demos beautifully but fails in production
- Agents as microservices: zero-config discovery, durable memory, async execution with no timeout limits
- Workflows that loop, branch, and retry - reasoning that adapts instead of being forced into a fixed DAG
- Live: from a typed function to a running multi-agent workflow in minutes
Speakers
Launch partner
AgentField is open-source infrastructure for building autonomous software factories and the AI backends that power them. It gives multi-agent systems a single control plane for orchestration, governance, and provenance - so every action your agents take is policy-checked and accountable, with no glue code and no editable logs. Apache 2.0, with SDKs in Python, TypeScript, and Go.
