The online narrative is just throw everything at agents and figure it out. I use them all day, I barely write code myself at this point. But the people who seem to get the best results are strong engineers. I think foundational knowledge still matters a lot, maybe even more now.

Agree, you do lose some depth on how things work

So much to build!

It seems not to matter how strong these models get, you eventually start to get a grasp of their limits. Just sort of an interesting thing you notice as you use them.

It has become increasingly clear to me that one of the most interesting areas to keep an eye on right now is how you maintain a solid understanding of a codebase as more work gets delegated to coding agents. You can only make good trade-offs if you have such understanding. Even

Curious how parity evolves as time passes

The Buffer Public API and MCP server are now in public beta. 🎉 We built an MCP server that lets AI assistants manage your Buffer content. Schedule posts, browse your queue, check channels, and capture ideas. It works with Claude Desktop, N8N, Zapier, Claude Code, Raycast, and

You asked for TanStack skills, we built the whole pipeline. Introducing TANSTACK Intent (alpha) 📦 Ship agent-readable "skills" inside npm packages 🔍 Auto-discovered from node_modules 🔄 Knowledge sync with npm update 📂 Distributed - skills live in library repo 🧩

It's easy to jump straight into implementing something without really understanding your options. Worse, you might not even be working on the right thing in the first place. As execution gets faster and cheaper, deeply thinking through what to do, how to do it, and most

so refreshing to read this take on this timeline

Software has been composable for decades. You don't build everything from scratch. You plug into what's already there. Libraries, APIs, contracts. Products weren't like that. You logged into an app, used what they gave you, and that was it. Some offered a public API but most

what's happening is the complete opposite of this

There's a version of shipping fast that comes from understanding the problem and a version that's just because it's easy now.

Cost of code dropped but the bar for products is higher than ever.

Tools got smarter, and the expectations for what to build with them got higher.

Chat in products is great but it doesn't make good UIs less important. You want both.

More people are being upfront about steering AI agents, rejecting suggestions, and carefully reviewing changes. It's quite refreshing after so many vanity metrics for a while now. The hype cycle is tiring. Once you've used these tools enough, you realize they are obviously

your MCP server should include skills in the resources part of it, and for clients that don't support resources ship a 'load_resources' tool as a fallback

Liam Murray slow down. make work small. review every line. rinse and repeat.

Coding with AI is wildly inconsistent. Some sessions feel like magic, others the model confidently invents APIs for hours.