Beyond the DAG: Building Agentic Workflows That Loop, Branch, and Scale
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
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).
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.
Partners
AI Tabir is an AI adoption platform that helps small businesses run like self-driving companies — AI takes on the operational busywork while owners stay in control of the decisions that matter. It starts with a free assessment that maps how a business actually works and pinpoints where time and money leak out — missed calls, unanswered leads, quotes with no follow-up, overdue invoices — then deploys industry-tuned AI agents, managed end to end, to handle that work. Rather than selling another tool, the platform delivers the work itself and keeps adapting as each business grows, across industries including automotive, HVAC, media, and video production.
KROK
The AI Collective is a global non-profit building the human layer for the AI era. We unite 200,000+ leaders, builders, and stakeholders across 150+ forums worldwide to democratize the frontier, build trust, and coordinate how society navigates the rapid acceleration of technological progress.