In today’s fast-moving market, businesses are constantly seeking ways to improve efficiency, reduce costs, and deliver better services. One of the most promising approaches to achieving these goals is through the use of artificial intelligence (AI) in automation.
I keep several claude code windows open, each on its own git-worktree. o3 and sonnet 4 create plans, sonnet 3.7 or sonnet 4 execute the plan, and o3 checks the results against the original ask. Any issues found are fed back into the plan template and the code is regenerated. The factory improves itself.
I’ve been at Lovable for five weeks and yeah… I’m not in Kansas anymore. This company operates on a completely different level – and as someone who’s spent my entire career in traditional tech, I’m seeing a very different pattern here that’s worth sharing.
So a big theme of this conversation is how to identify the right opportunities to design AI into a product that’s already working. Ioana shares a bunch of stories and lessons learned from her time at Miro as well as a refreshing perspective on AI and design as whole that i think will resonate with a lot of you.
With that in mind, we’re focused on increasing the number of designers who receive leads and the number of leads each designer receives, with work underway to improve every facet of the conversion funnel.
In this process we never think to ask if abdicating our creative judgment almost completely to the Large Language Model gods is a good idea. It’s like we’re a tribe of primitive Luddites offering up our drudgery in return for a magical oracle that only rewards the loudest acolytes.
In the spirit of 12 Factor Apps. The source for this project is public at https://github.com/humanlayer/12-factor-agents, and I welcome your feedback and contributions. Let’s figure this out together!
When you hear “whiteboard,” the first thing that probably comes to mind is a classic brainstorming session filled with sticky notes, doodles, and scattered ideas.
After 6 months of hard work, we’re launching Flowbite Design System v3.0! – fully integrated native tokens and variables – refreshed all UI components with modern 2025 design – massively improved performance and memory usage – improved usage documentation and more.
Beyond boosting efficiency, the strongest software developers use AI to explore the problem space and find more creative solutions. Figma’s Vice President of Software Engineering Marcel Weekes and Developer Advocate Jake Albaugh share the crucial skills engineers should learn to meet the moment.
