Hands-on backend engineer • multi-time founding engineer • Go, Ruby, and distributed systems. Now harnessing and maximizing AI, and building https://nitter.gq/t.co/rmsjNMTNFV
Spain
Joined February 2013
- Tweets718
- Following171
- Followers135
- Likes599
Pinned Tweet
Last week, I created a TUI for a terminal that helps you navigate through the @EntireHQ committed AI transcriptions (checkpoints).
It basically gives you a "local" way to explore the information, and today I added all the CLI commands that are offered by the entire CLI.
🧵 Let me walk you through each one
1
67
Jose Corral retweeted
Two years ago I created a simple script to detect when the camera is on, and turn on a "LIVE" light signal in my home office to let my wife to know when I was in a meet.
I improved the script which becomes a CLI tool compatible with Linux and macOS
sergiocarracedo.es/on-a-meet…
Jose Corral retweeted
I'm looking for my next professional challenge as an AI Product Engineer or Senior Developer in an inspiring project I can create impact. 🎯
✨ If your company is looking for a profile like mine, I would love to talk!
linkedin.com/posts/sergiocar…
Jose Corral retweeted
Building with AI and SKILLs? 🤖
Humans love nested folders 📂
AI Agents love flat directories 📄
I built skill-organizer to organize skill files in hierarchies, and flatten them automatically for your agent.
skill-organizer.sergiocarrac…
Check the tree structure below 👇
Jose Corral retweeted
harness engineering, coined by @Vtrivedy10 is about the things you build around the model to create a good agent - as @mitchellh puts it
> [it] is the idea that anytime you find an agent makes a mistake, you take the time to engineer a solution such that the agent never makes that mistake again.
First time I've seen an AI feature rejected due to cost.
Anthropic made the announcement of Claude Code AI-powered code reviews.
This team was using the existing GitHub Action, github.com/anthropics/claude… which has some UX issues in code review, so it felt like the perfect feature to upgrade.
But then someone pointed out: "$15 to $25 per PR."
"To expensive."
Result: I think this is probably the first Claude feature I've seen that was ready to use, made sense to use, and wasn't included... just due to cost.
Introducing Code Review, a new feature for Claude Code.
When a PR opens, Claude dispatches a team of agents to hunt for bugs.
1
65
Jose Corral retweeted
Unveiling our new startup Advanced Machine Intelligence (AMI Labs).
We just completed our seed round: $1.03B / 890M€, one the largest seeds ever, probably the largest for a European company.
We're hiring!
[the background image is the Veil Nebula - a picture I took from my backyard, most appropriate for an unveiling]
More details here:
techcrunch.com/2026/03/09/ya…
Advanced Machine Intelligence (AMI) is building a new breed of AI systems that understand the world, have persistent memory, can reason and plan, and are controllable and safe.
We’ve raised a $1.03B (~€890M) round from global investors who believe in our vision of universally intelligent systems centered on world models. This round is co-led by Cathay Innovation, Greycroft, Hiro Capital, HV Capital, and Bezos Expeditions, along with other investors and angels across the world.
We are a growing team of researchers and builders, operating in Paris, New York, Montreal and Singapore from day one.
Read more: amilabs.xyz/
AMI - Real world. Real intelligence.
ALT Photographer: Yann LeCun IC1340 / NGC 6992 / Eastern Veil nebula 20210628-ic1340-rasa-2600mc-lext Scope: Celestron RASA 11" Camera: ZWO ASI2600MC Filter: Radian Triad quad narrow band. Subs: 65 @300 seconds.
Jose Corral retweeted
A very useful tool to get faster and more accurate context for AI agents:
Instead of telling the agent, make the text bigger, with this tool you can just click and select and element and you will get in your clipboard part of the HTML and involved files
react-grab.com/
Jose Corral retweeted
We're hiring for a new role: Agentic AI Developer Advocate
This is a paid contract role ($10k/month) for an agent that will create content, run growth experiments, and provide product feedback
Are you (or did you build) the right agent? jobs.ashbyhq.com/revenuecat/…
The downside of using @EntireHQ is that it requires read access to your repositories.
This is because the CLI stores session metadata on a Git branch, and their servers read that branch to render the web dashboard. Therefore, this means that your repository data will be passing through their infrastructure.
It will be great to have a local first viewer.
1
100
Jose Corral retweeted
When you think you're finished with your development plan for your agent, try this prompt with a few different frontier models. You might be amazed what they come up with:
"What's the single smartest and most radically innovative and accretive and useful and compelling addition you could make to the plan at this point?"
If you've already started development and have a fleshed out project already, replace the word "plan" with "project."
