Most Engineering Teams Are Building the Wrong Thing (or why your 3-month tool build just got replaced by a Markdown file) 🚨
18 years building developer tools taught me this: AI is forcing us to rethink everything about when and what to build. 🛠️
Teams see a workflow problem and immediately think: “Let’s build a tool.” That instinct is costing you months of engineering time. ⚡
The hidden cost of tool-first thinking: Your team just spent 3 months building a custom deployment dashboard. Meanwhile, your competitors wrote deployment context in markdown and let agents handle the analysis.
Guess who ships faster now? 🚀
What winning teams do differently: Instead of log parsers → Rich log schemas that agents query dynamically Instead of API connectors → Documented APIs with failure modes (MCP is becoming the de-facto standard here) Instead of custom dashboards → Structured data that agents visualize on-demand
Building agent infrastructure at enterprise scale has shown me this shift is happening in real-time. Engineers stuck in “tool mode” are getting lapped by engineers in “context mode.”
💡Plot twist: The best “tool” I’ve built this year was a README file. 📄
The uncomfortable truth: Building tools feels productive (and in some cases, still necessary). Writing documentation feels like busywork. But agents don’t need your UI. They need your context.
This shift is happening now. The engineers that figure it out first are already pulling ahead.
Most won’t naturally make this shift because it goes against every developer instinct we’ve built over the past two decades. The teams that do will have a clear advantage.
What’s the last tool you built that could have been a really good markdown file instead? 👇