AI Agents Are Implemented, Not Adopted

About this episode

Ben Lorica speaks with Hamza Tahir about moving AI agents from demos to production and the necessary components for effective implementation.

Ben Lorica speaks with Hamza Tahir, co-founder of Kitaru, about what it takes to move AI agents from demos to production. They discuss the difference between workflows and agents, why “harness engineering” is becoming a useful frame for application builders, and why long-running agent workloads require orchestration, durable execution, retries, state management, and human-in-the-loop semantics. Subscribe to the Gradient Flow Newsletter 📩 https://gradientflow.substack.com/ Subscribe: App...

People in this episode

Host: Ben Lorica

Guest: Hamza Tahir

Topics covered

• AI agents
• production
• workflows
• harness engineering
• orchestration
• state management

Keywords

• AI agents
• production
• workflows
• harness engineering
• orchestration
• state management
• human-in-the-loop

Mentioned in this episode

Organizations: Kitaru

More episodes of The Data Exchange with Ben Lorica

• Why Your AI Agent Isn't Ready to Ship (And How to Know When It Is) · June 4, 2026 · 43 min
• Why Foundation Models Haven’t Replaced Classical Machine Learning · May 28, 2026 · 52 min
• When "Garbage In, Garbage Out" Gets It Wrong · May 21, 2026 · 43 min
• As Code Generation Speeds Up, Who Tests the Output? · May 14, 2026 · 44 min
• The Gap Between AI Hype and Enterprise Reality · May 7, 2026 · 56 min
• Reading the Tea Leaves: What the World's Top AI Researchers Are Really Working On · April 30, 2026 · 57 min