Roles | News, how-tos, features, reviews, and videos
Explore related topics
Critics call Garry Tan’s gstack just a bunch of text files. They’re right — and that’s exactly why the future of agentic development looks like Markdown.
AI removes the difficulty of writing code. It does not remove the responsibility of designing systems.
In a policy change, it requires contributors to understand the code they commit. The question, though, is how to determine that.
Something big is happening, all right. But there is reason for optimism in the AI turmoil.
The learning pathway, housed within the Google Developer Program, aims to equip developers with hands-on expertise in building and deploying AI agents using the Agent Development Kit.
Engineers who love building, mentoring, and solving complex problems don’t need to manage people to keep growing. You can lead through influence instead.
While some consider prompting is a manual hack, context Engineering is a scalable discipline. Learn how to build AI systems that manage their own information flow using MCP and context caching.
AI can read and write code, but context and architecture still belong to humans.
Improving developer productivity isn’t about producing more code faster, but producing well-architected, secure, and maintainable code. It’s about platforms, golden paths, and guardrails.
There is probably a more direct route from AI models to the software we want than having agents work with code.
Being a “10x engineer” isn’t about shipping more code — it’s about helping everyone around you ship better, faster and with fewer fires.
To keep AI coding assistants from running amok, developers must learn to write good specs and develop product management skills.
The modern product organization is constantly hitting a critical bottleneck: Platform teams are the engine of leverage, but their capacity is finite.