In this episode of Hard Software, Upal and Antonio delve into the revolutionary approaches to software creation with Nima Keivan, CEO and co-founder of Durable.

From the limits of traditional code generation to the emergence of neuro-symbolic AI, Nima sheds light on Durable’s mission to elevate software development beyond syntax—into actions, objectives, and real-world results. The conversation explores the challenges of coherence in AI agents, how robotics-inspired planning can reshape software workflows, and the potential of documents as dynamic interfaces for iterative development.

They also tackle the philosophy behind no-code, the future of AI-driven deployment, and the critical importance of trust and hypothesis-driven learning in building robust systems. With a unique perspective informed by a background in robotics and a vision for the future of AI, Nima shares insights into what it truly means to develop software that learns, evolves, and thrives in real-world complexity.

This is a public episode. If you would like to discuss this with other subscribers or get access to bonus episodes, visit blog.bem.ai