Episode 38: EP 26: The Last Mile of AI-SDLC: When Agents Build What Customers Want
Productmind co-founders Steen Brahe and Alessio Nobile take on the last mile of the AI software development lifecycle: getting from a real customer conversation to shipped code without losing the original intent. They demo how a customer call becomes a feature request, then a living specification, then agent-ready tasks running against an existing codebase, with full lineage preserved from feedback to release. The panel also digs into how AI is redrawing product and engineering roles, what governance of human-agent collaboration looks like in the enterprise, and how the founders cleared 20+ bugs with parallel agents while building Productmind with Productmind.
Special Guests
Steen Brahe
Co-founder of Productmind; software entrepreneur with a PhD in software engineering, previously in the AWS startups organization.
Alessio Nobile
Co-founder of Productmind, based in Amsterdam; AWS-certified solutions architect and startup mentor.
Timestamps
00:00Introduction01:25Episode 26 and the European Takeover02:21Meet the Founders of Productmind06:29Why Steen and Alessio Built Productmind08:58From Customer Feedback to Agentic Product Development13:05How AI Is Changing Product and Engineering Roles19:12Who Is Productmind Built For?24:11Human-Agent Collaboration and Enterprise Governance28:43Productmind Demo Begins31:20Turning a Customer Conversation Into a Feature Request32:57Creating a Living Feature Specification34:54Breaking Features Into Agent-Ready Tasks36:22Starting a Coding Session on an Existing Codebase37:08Complete Lineage From Customer Feedback to Code38:16Previewing an AI-Built Feature39:12Fixing Bugs With Agents40:05Orchestration, Agent Harnesses, and Context Management43:24Why Context Matters for Humans and Agents45:33Productmind's Built-In Product Chat Agent47:14One Workspace for the Product Development Lifecycle47:34Managing 100x More Information With AI50:13The Hardest Technical Problem the Founders Solved51:43Using Productmind to Build Productmind52:26Resolving 20+ Bugs With Parallel Agents54:17Why Clean Orchestration Matters as Teams Scale55:45Tools the Founders Cannot Live Without57:17Closing RemarksRelated Episodes
Episode 33: Open Source Survival in the Age of AI: Joshua Drake on Licensing, Governance & Monetization
Joshua Drake, President and CTO of Command Prompt with nearly 30 years in the PostgreSQL community, lays out the risks AI creates for open source: extraction without attribution, model collapse, AI-generated security holes, and legal exposure from derivative work. He argues that proof of human contribution, signed origins, and governance with humans in the loop matter more than ever, and shows how commercial open source companies can adopt AI without losing community trust.
Episode 32: EP 24: Up a Layer: The Rise of the Agentic Builder and the CAMPstack
The panel unpacks how builders are moving "up a layer", from writing every line of implementation to directing AI agents, composing managed services, and shipping faster on product judgment. They introduce the CAMP stack (Cloud, Agents, Managed services, Platforms) and dig into intent engineering, infrastructure control planes, the token economics of running agents 24/7, and why testing remains the hardest part of AI-generated code.
![Building the Business Behind Open Source AI @ AWS San Francisco [Live]](https://i.ytimg.com/vi/wVRZe8xhymQ/maxresdefault.jpg)
Episode 30: Building the Business Behind Open Source AI @ AWS San Francisco [Live]
A live panel recorded at AWS San Francisco bringing together open-source AI founders and builders from Zep AI, DataRobot, Command Prompt, Scalar Labs, StreamNative, and Omnistrate. The group moves past technical specs to share strategic and personal reflections on how open source AI teams deploy, scale, and monetize.