AI industry’s size obsession is killing ROI, engineer argues - Doing enterprises AI isn’t free in terms of time, money, opportunity cost, and risk. You need target things that have a pay off, an ROI. I hope that this will mean doing more, not cutting costs. That is growth, not firing people.
Why I’m Betting Against AI Agents in 2025 (Despite Building Them) - ‘Meanwhile, the winners will be teams building constrained, domain-specific tools that use AI for the hard parts while maintaining human control or strict boundaries over critical decisions. Think less “autonomous everything” and more “extremely capable assistants with clear boundaries."'
Internal Developer Platform Marketing, part 01
Most platform teams forget they have a product to sell to developers. Part one of my new series over at The New Stacklays out why internal platform marketing is incredibly important. Here’s excerpt on positioning:
Platform Positioning: What Is It Good For?
Positioning defines where your platform fits in your organization’s technical landscape. It answers the crucial question: “When and why should developers choose this platform over other options?”
Oftentimes, platforms are positioned as the everything solution that solves all the problems and, thus, should be used for all applications.
VMware Tanzu enhances support for generative AI and agents with Tanzu AI Solutions - “As customers move from AI experimentation to implementation, they stand to benefit from closer integrations between technology components as they redefine “Ops” frameworks within their businesses. VMware Tanzu AI Solutions are designed to do just that, with specific enhancements like AI middleware that boosts performance, fosters security and reduces time to value when it comes to operationalizing AI models and applications. Tanzu AI Solutions are polyglot for those who are unfamiliar with preferred data science languages or use other languages, and should appeal to Java developers with the launch of Spring AI. Spring AI also includes dedicated feature sets to control, observe, and evaluate models and, ultimately, agents, as organizations' AI capabilities progress. Model context protocol (MCP) is also supported in Tanzu Platform."
Identify, solve, verify - “My job is to identify problems that can be solved with code, then solve them, then verify that the solution works and has actually addressed the problem."
Trump’s pressure on Apple to make All-American phones ignores the last tech giant that tried and failed - If no one wants the product, it doesn’t matter where it’s made. // “In the end, Motorola’s failed U.S. adventure had little to do with where the Moto X was assembled, by all accounts. The phone simply didn’t sell well enough to justify a U.S. assembly line."
Musings on The AI Con - “ask more questions of those pushing AI into everything. What, specifically, is the goal? What is supposed to be automated by the new tool? What are its inputs and outputs supposed to be? What does success look like, exactly? What would count as failure to achieve the goal?"