If an agent can rebuild your app in a few weeks, what are your customers actually paying you for? I don't think it's lawyers. A clone gets graded on matching the original, bugs and all, so the best it can do is tie. I wrote up what I'd build instead, and why we made all of Agent-Native free to fork: builder.io/blog/the-best-a-c…

Thanks to GrokBot, I merged more PRs last week than ever before. And also, I'm not gonna keep using it. My 16 bots stayed up all weekend while I slept, burning $100 deciding they had nothing to tell me. On Monday, when I actually needed them, they were out cold. GrokBot is still the closest thing we have to a working always-on staff. It's just not there yet, and the reasons are architectural. Here's what happened, and what I think always-on agents actually need. builder.io/blog/grokbot-revi…

The least productive thing I can imagine doing is watching an agent work. But I still do it, because I'm never really sure if the agent understood what I wanted it to do. So I end up reading the tool calls and watching files change. I want to agree on what it's gonna build, leave it alone, and review what comes back. But an all-text plan that's several pages long just feels like homework, and it's easier to let the agent run, even if it wastes tokens, just so I can see the result. What I need is a better way to verify the plan and review the result, just at a glance. Something where I can see the layout or the API flow and point to the part that's wrong. Here's what I've been doing instead lately. builder.io/blog/stop-watchin…

I keep getting frustrated when I ask an agent to clean up some code and get another wrapper, another helper, and all the original complexity still sitting underneath. Then I have to figure out if anything actually got better. We’re running into this at Builder while developing Agent Native pretty much as fast as we can. People leave feedback in Slack, and an agent factory picks it up and works on it. A lot is changing, all the time. So validation is a big deal for us. In one cleanup experiment, an agent removed a lint warning, passed typechecking, and passed all 23 tests in the focused suite. The code still used unvalidated input. Everything passed, but we still hadn’t checked the behavior we actually needed. I wrote up what we’re learning about asking agents to clean up code, figuring out what needs to change, and checking whether it actually got better. builder.io/blog/de-slop-ai-g…

You never make a slide deck while you still have time to make a slide deck. You make it the night before the QBR. Or the morning of the stakeholder meeting. Usually after the research, analysis, and actual decisions have already eaten up all the time you planned to spend on it. In theory, AI should be great at slide decks. But it needs all the context scattered across your documents, spreadsheets, and meeting notes. It needs to understand (and apply) your brand and design system. And it needs to give you a real, editable presentation, and not just a pretty picture of a deck. So I went through 12 PowerPoint alternatives to see whether any of them could actually take all my context and turn it into a gorgeous, on-brand deck for me. Here’s what I found. builder.io/blog/powerpoint-a…

Nobody really gets what they’re giving you when it comes to AI slop code. You know how it goes. A teammate shows you an internal tool they built with AI. It works. It looks nearly finished. They just need you to “hook up the integrations.” But you see auth, consent, production data, CRM writes, accessibility, analytics, error states, tests, deployment, monitoring, and someone who has to own the thing after launch. The prototype took an afternoon. Making it something the company can depend on could take weeks. So you rebuild it properly. Then another team asks for almost the same tool, with different content and one new integration. That’s how engineering ends up owning six versions of an internal tool nobody meant to build six times. I wrote about why both obvious ways of handling this fail, and how to give teams more agency without turning developers into the permanent cleanup crew. builder.io/blog/stop-rebuild…

If AI makes every marketer, PM, and designer become a developer, then software is failing. AI should make people better at the jobs they chose, not just give everyone a different one. Some more thoughts in the article below on how we can do a better job. builder.io/blog/what-agent-n…

Notion is one of my favorite apps of all time. I've been a user for 10 years, since the beta. I'm one of those obsessive second brain people, and I've tried just about every Notion-like app out there. And especially lately, because Notion is trying to do absolutely everything, it's let competitors pass it by in specific workflows. If you use Notion because you actually need every single feature, great. This post probably isn't for you. But if you use Notion only as an agentic platform, only as a task manager, only as a PKM, only as a data solution, or only as a writing tool? Well, there's almost definitely a better alternative. Here are my top picks and why, from actually using them. builder.io/blog/notion-alter…