The Contradiction of AI Agent Workflows: Why Your Systems Might Be Breaking

The Agent Workflow Paradox

In this episode of Old School New Tech, host Ran Aroussi explores the inherent contradiction in building AI systems with agent workflows. He argues that combining autonomous agents with predetermined workflows creates complexity and brittleness, making these systems difficult to scale. Ran provides examples that highlight the pitfalls of this approach and advocates for a shift toward giving AI agents context and knowledge to enable reasoning and adaptability within defined guardrails, rather than rigid workflows. This episode is sponsored by Automaze, offering CTO-as-a-Service for startups and businesses.

00:00 Introduction to AI Contradictions
01:31 The Oxymoron of Agent Workflows
02:42 Concrete Example: Financial Service Incident
03:54 Guardrails vs. Workflows
05:24 The Alternative: Context and Knowledge
07:19 Evaluating Your AI Systems
09:19 Conclusion and Final Thoughts

-----

🎧 Brought to you by Automaze

This podcast is sponsored by Automaze, the fractional CTO partner for founders and operators. Whether you’re building a high-tech MVP or modernizing internal ops with AI and automation, Automaze can help you scale without the overhead of a full-time team.

Learn more: automaze.io

The Illusion of Progress: Avoiding the Faster Horses Trap in 2025

In this episode of Old School New Tech, host Ran Aroussi delves into the difference between real progress and the illusion of progress, using historical examples like the retail industry's initial forays onto the internet and mobile phone companies' reactions to the iPhone. He discusses how today's 'make me an AI' mentality mirrors past missteps and emphasizes the need for true transformation rather than superficial changes. Aroussi challenges companies to ask the hard, transformative questions necessary for genuine progress. Sponsored by Automaze, this episode urges listeners to reconsider how they integrate new technologies into their business strategies.

00:00 Introduction and Sponsor Message
00:52 A Look Back at 1997: The Illusion of Progress
02:14 Nokia and the iPhone Revolution
03:20 The Real Revolution: Beyond Incremental Improvements
04:36 AI in 2025: The New 'Make Me an Internet'
05:33 Asking the Hard Questions for True Transformation
06:49 Conclusion and Call to Action

-----

🎧 Brought to you by Automaze

This podcast is sponsored by Automaze, the fractional CTO partner for founders and operators. Whether you’re building a high-tech MVP or modernizing internal ops with AI and automation, Automaze can help you scale without the overhead of a full-time team.

Learn more: automaze.io

In this episode of 'Old School New Tech,' I interview Sumit Vekariya, the founder of ZKred, a company specializing in Web3-based, privacy-preserving, verifiable credentials. The episode explores how Sumit's lean team operates remotely, leveraging various AI tools to enhance productivity. We also delve into the challenges and potential improvements in AI technology, highlighting Sumit's vision for the future of decentralized identity management.

You can find Sumit on X/Twitter @Sarkazein7

Chapters

00:00 Welcome to Old School New Tech
00:28 Introducing Automaze: Your Modern Business Partner
01:09 Meet Sumit Vekariya: Innovator in Privacy and Identity
01:37 Exploring ZKREDA: Simplifying Identity Management
03:01 The Future of Verifiable Credentials
05:41 Lean Operations and Smart Tooling
14:02 Balancing Stealth Mode and Growth
14:45 Team Dynamics and Remote Work
16:30 Future Goals and Ambitions
18:35 Final Thoughts and Advice for Founders
20:25 Connect with Sumit Vekariya

-----

🎧 Brought to you by Automaze

This podcast is sponsored by Automaze, the fractional CTO partner for founders and operators. Whether you’re building a high-tech MVP or modernizing internal ops with AI and automation, Automaze can help you scale without the overhead of a full-time team.

Learn more: automaze.io