Agentic engineering for Rails teams | 18 yrs shipping software
Joined June 2014
- Tweets3.2K
- Following370
- Followers2.1K
- Likes2.4K
Cezar Halmagean retweeted
I've been building something for my workshop.
Offcut is a furniture design app. Add it to Claude or ChatGPT as a connector and just describe what you want.
It runs in the browser and it's free.
👉 offcut.diy/
I've been building something for my workshop.
Offcut is a furniture design app. Add it to Claude or ChatGPT as a connector and just describe what you want.
It runs in the browser and it's free.
👉 offcut.diy/
AI agents write good code most of the time. But if you can’t follow a PR in two minutes, you can’t push back on it. You just approve it.
Do that enough and nobody knows the codebase anymore.
What helps me: framework conventions, a plan first, then tests, small changes.
Microsoft says AI agents could become an insider threat. I think they’re right.
So I treat agents like a new hire on day one. Builders get their own branch and dev keys only. A review agent checks every PR. CI has to pass. A human merges.
What’s your setup?
Just throw an em dash into a handwritten email.
Watch people doubt their pattern recognition abilities. :)
How are you testing your MCP tools?
I built an MCP server inside ThinkerNotes and realized Claude was picking the wrong tool.
Which got me thinking about testing these tools since you're basically working with plain text, not code.
This video explains what I came up with. 👇
Enjoy, and let me know if you've got a better way to do it.
youtu.be/VOdTjvTr5sQ
Cezar Halmagean retweeted
Elm 0.19.3 is out today!
✨ elm-lang.org/news/another-st… ✨
Explains the rough roadmap for the next few releases. We are preparing for some exciting improvements and features! 😊
If you love reading/listening to business books or podcasts, but you forget most of it, I've built something for you (and for me as well).
Check out ThinkerNotes, a tool that keeps what you actually took from each book, podcast, and brings it back the moment it's relevant again.
My YouTube channel made over $550k without going viral.
Most of it was contracts from people who watched my videos and decided I knew my stuff.
You don't need big view counts. You need the right few people watching.
Nobody types your product name into Google before they've heard of you.
They type the problem. The error message. The thing they're struggling with.
Blogging, social, YouTube, none of it is there to describe your product. It's there to make people aware it exists.
I keep thinking the AI is stalling just to burn more tokens.
Have you noticed how it dances around the right answer, playing dumb, when the correct one is obviously sitting right there?
If you’re building agents that need web browsing, this video is for you.
youtube.com/watch?v=w5l9EjuF…
