Chain of Thought | AI Agents, Infrastructure & Engineering

Agentic AI exploded in 2025, but how do businesses move beyond prototypes to deploy reliable, valuable agents at scale?Join host Conor Bronsdon and Lyzr AI CEO Siva Surendira as they discuss the complexities of building and managing AI agents for enterprises. Siva shares his journey creating Lyzr, focusing on making powerful agent frameworks accessible and trustworthy for enterprise developers. They discuss the critical hurdles businesses face, including productionization challenges, ensuring responsible AI, and bridging the gap between rapid innovation and the stringent requirements of regulated industries.Listen as Siva explains Lyzr's approach to embedding safety guardrails natively and learn about the nuances of multi-agent orchestration, including managerial, DAG, and hybrid flows. Siva also offers insights into the limitations of "vibe coding" for enterprise use cases and stresses the crucial role of robust evaluation (evals) and choosing the right models—from local open-source options to frontier LLMs. Explore the bottlenecks hindering adoption, like custom application integration and data readiness, and learn why Siva believes the biggest opportunity for agent companies may not lie in replacing SaaS platforms but rather in automating the mundane work currently performed by humans.Chapters00:22 Introduction and Guest Welcome00:52 Enterprise Agent Framework02:48 Building Enterprise-Friendly AI Frameworks04:56 Enterprise Concerns with Vibe Coding09:23 Safe and Responsible AI Implementation11:05 Multi-Agent Orchestration14:13 Challenges in Multi-Agent Systems14:22 Enterprise Integration Bottlenecks17:37 The Role of Low-Code and No-Code Solutions19:55 Inter-Agent Communication Standards21:49 Future of AI Agents in Enterprises29:37 Evaluating AI Agents36:34 Conclusion and Final ThoughtsFollow the hostsFollow⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠ Atin⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠Follow⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠ Conor⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠Follow⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠ Vikram⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠Follow⁠⁠⁠⁠⁠⁠⁠⁠⁠ ⁠⁠⁠⁠Yash⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠Follow Today's Guest(s)Website: lyzr.aiLinkedIn: Siva SurendiraCheck out Galileo⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠Try Galileo⁠⁠Agent Leaderboard

Show Notes

Agentic AI exploded in 2025, but how do businesses move beyond prototypes to deploy reliable, valuable agents at scale?

Join host Conor Bronsdon and Lyzr AI CEO Siva Surendira as they discuss the complexities of building and managing AI agents for enterprises. Siva shares his journey creating Lyzr, focusing on making powerful agent frameworks accessible and trustworthy for enterprise developers. They discuss the critical hurdles businesses face, including productionization challenges, ensuring responsible AI, and bridging the gap between rapid innovation and the stringent requirements of regulated industries.

Listen as Siva explains Lyzr's approach to embedding safety guardrails natively and learn about the nuances of multi-agent orchestration, including managerial, DAG, and hybrid flows. Siva also offers insights into the limitations of "vibe coding" for enterprise use cases and stresses the crucial role of robust evaluation (evals) and choosing the right models—from local open-source options to frontier LLMs. Explore the bottlenecks hindering adoption, like custom application integration and data readiness, and learn why Siva believes the biggest opportunity for agent companies may not lie in replacing SaaS platforms but rather in automating the mundane work currently performed by humans.


Chapters

00:22 Introduction and Guest Welcome

00:52 Enterprise Agent Framework

02:48 Building Enterprise-Friendly AI Frameworks

04:56 Enterprise Concerns with Vibe Coding

09:23 Safe and Responsible AI Implementation

11:05 Multi-Agent Orchestration

14:13 Challenges in Multi-Agent Systems

14:22 Enterprise Integration Bottlenecks

17:37 The Role of Low-Code and No-Code Solutions

19:55 Inter-Agent Communication Standards

21:49 Future of AI Agents in Enterprises

29:37 Evaluating AI Agents

36:34 Conclusion and Final Thoughts


Follow the hosts

Follow⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠ Atin⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠

Follow⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠ Conor⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠

Follow⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠ Vikram⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠

Follow⁠⁠⁠⁠⁠⁠⁠⁠⁠ ⁠⁠⁠⁠Yash⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠


Follow Today's Guest(s)

Website: lyzr.ai

LinkedIn: Siva Surendira


Check out Galileo

⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠Try Galileo⁠⁠

Agent Leaderboard

What is Chain of Thought | AI Agents, Infrastructure & Engineering?

AI is reshaping infrastructure, strategy, and entire industries. Host Conor Bronsdon talks to the engineers, founders, and researchers building breakthrough AI systems about what it actually takes to ship AI in production, where the opportunities lie, and how leaders should think about the strategic bets ahead.

Chain of Thought translates technical depth into actionable insights for builders and decision-makers. New episodes bi-weekly.

Conor Bronsdon is an angel investor in AI and dev tools, Head of Technical Ecosystem at Modular, and previously led growth at AI startups Galileo and LinearB.