Saul Rodríguez

Senior Software Engineer

[Anthony Dupont-Cinko @cinkotweets]

In one day, I went from complete fucking noob to... a Jev power user? (Read this, and you can too!)

I've been playing with Jev, a new AI model from @typesafeai. I'm not a developer, so I wanted to find out what I could actually build with it.

I made four increasingly crafty/interesting demos:

An email sorter
2,000 test emails sorted into buckets in 4.4 seconds, for about 4 cents. It flags uncertain cases for a human to review.

A customer-review playground
Would this person buy again? What should we improve? How did they feel about the product? Ask all three and get answers your app can use.

“Should I send this Message?”
Got anger issues? Give it your draft Slack or email... whether you're about to rage quit, or saying something nice. It picks send now, soften first, sleep on it, or say it in person.

“Am I bombing?”
A pitch-coach experiment. The browser uses Face API to turn camera and voice cues into numbers; Jev uses those to suggest feedback. I simulated nervous and confident pitches to show the feedback changing.

Each one uses the same basic idea: give Jev the situation and the possible answers. It picks an answer, tells the app how sure it is, and the app uses that result.

You can start with one judgment you're tired of making over and over!

Here's my Jev Test™ for new and existing projects:
(1) Do I keep asking the same question?
(2) Can I name the possible answers?
(3) Would deciding faster or more often actually help?
If something in your work passes all three, that's a place to start.

Full 10-minute walkthrough attached, including when I'd still use Claude or ChatGPT.

Watch on YouTube: https://t.co/6keYdAW1vU

What decision at work would you build one of these for?

(Shoutout to @tenex_labs' finest -- @seejayhess and @_raghavdixit_ -- for the knowledge you imparted for this one!!)

[Thariq @trq212]

the right way to use model capabilities is not to ship 10x more features to prod

it's to spend more time understanding your users, trying experiments, building prototypes, learning about things you don't understand so that you can ship things that actually work

[Ion Stoica @istoica05]

https://t.co/XHoYyT3UlG

[dex @dexhorthy]

300k views and counting on “why software factories fail” - don’t be the last one 🙂

Deep dive on coding agents, why we should still read the code, and how to design your software factory

https://t.co/Y2KCg0hzlc

[Adam @adamdotdev]

Me when that one guy still looking at the code asks why we have both a `createdAt` and `created_at` column in the `users_v2` table

[Zach Lloyd @zachlloydtweets]

The software factory approach is getting pretty popular, but it can be daunting to adopt all at once.

Let's go through “crawl, walk, run” steps for making the transition from local, interactive agents to automated cloud development. https://t.co/RugDAn4Vqg

[draw.io @drawio]

https://t.co/ZjrL6HseZq is now in the Claude connector directory 🎉

Ask Claude for a diagram and it renders inline in the chat as an interactive https://t.co/ZjrL6HseZq diagram. One click opens it in the editor for further edits.

No install needed.

https://t.co/C2Sw9S6Kxe

[DevOps ToolBox @devopstoolbox]

Sad but necessary:

https://t.co/BKLkpUqTyx

[Saul Rodríguez @sabo182]

@mattpocockuk Hi there, I took the course and have been coaching engineers into adopting the workflow mostly with Claude Code.

More about my background: https://t.co/NvDn14ApFM

[santi @santtiagom_]

https://t.co/oa3EijQ18u

[Dr Milan Milanović @milan_milanovic]

Here are some Claude skills I found useful

When I started to work with Claude Code, I stored most of my instructions in prompts. Later we moved in to the Claude.md file, and now they live in a folder called 𝘀𝗸𝗶𝗹𝗹𝘀. And what is great about it, that we can share it with others.

Basically this folder has inside one file called 𝗦𝗞𝗜𝗟𝗟.𝗺𝗱. The agent reads only its name and description, and uses it when needed or when we explicitly call it.

Anthropic made it open source in 2025, and now on https://t.co/YDXBhnBK8U you can find 𝟰𝟲 𝘁𝗼𝗼𝗹𝘀 from Claude Code to Codex and Cursor.

Here are some open-source skills I found useful:

1. 𝗦𝘂𝗽𝗲𝗿𝗽𝗼𝘄𝗲𝗿𝘀 (281k) by Jesse Vincent. Probably the most useful one. The agent asks you before doing. It includes different useful skills, from planning, coding, debugging, review and more.

https://t.co/kgFjIZSEIi

2. 𝗦𝗸𝗶𝗹𝗹𝘀 𝗳𝗼𝗿 𝗥𝗲𝗮𝗹 𝗘𝗻𝗴𝗶𝗻𝗲𝗲𝗿𝘀 (253k) by Matt Pocock. A group of small skills which started from his most popular grill-me skill. I liked this one in particular, as you can use it to clear your thoughts before an implementation.

https://t.co/rP7eYKHYl0

3. 𝗞𝗮𝗿𝗽𝗮𝘁𝗵𝘆 𝘀𝗸𝗶𝗹𝗹𝘀 (210k) by multica-ai. It includes a way of working that Andrej Karpathy defined: thinking before coding, keep it simple, change only what you must and finish the goal. Very useful!

https://t.co/wOjOJlGV68

4. 𝗔𝗻𝘁𝗵𝗿𝗼𝗽𝗶𝗰 𝘀𝗸𝗶𝗹𝗹𝘀 (169k). This is Anthropic's official skill set. You can use it to produce Word, PowerPoint, Excel and PDF files.

https://t.co/eq6b3RjUG5

5. 𝗣𝗼𝗻𝘆𝘁𝗮𝗶𝗹 (127k) by Dietrich Gebert. This one start from the premise I like the most "The best code is the code you never wrote." Before writing any code, the agent asks you questions like: does this need to exist, is it a native platform feature, an installed dependency and more. Then do the minimum that works.

https://t.co/kx2SltPoGZ

6. 𝗨𝗜/𝗨𝗫 𝗣𝗿𝗼 𝗠𝗮𝘅 (125k). This one is useful if you do any kind of UI creation. You probably saw that every agent-based UI look the same. So, here you have 79 UI styles and 192 color palettes to choose from.

https://t.co/4f69Toc5x0

7. 𝗔𝗴𝗲𝗻𝘁 𝗦𝗸𝗶𝗹𝗹𝘀 (92k) by Addy Osmani. It includes 25 skills that follow your full development process, from specs through testing, security review and deployment. This one you will use every day.

https://t.co/KGY7CuKQXy

8. 𝗚𝗿𝗮𝗽𝗵𝗶𝗳𝘆 (75k). If you need to understand your legacy codebase, this one is the right one. With one command, /graphify, it creates a map of your whole project, including code, SQL and docs. Then you can query it.

https://t.co/WMHQO7rK6g

These repos have about 1.3M stars, and they are mostly text files.

Back to you, which one do you find useful?

[Zach Lloyd @zachlloydtweets]

Software factories should be built on an infrastructure stack that is open, composable, and defined-in-code.

This article lays out the principles that apply to anyone who is looking to move to a factory model. https://t.co/cRq5sBVsB4

[Visual Studio Code @code]

Stunning Icons in Seconds 😺

🔗 https://t.co/bO9B2QZduj

[Kenny Damian @Kenny_GTM]

https://t.co/RDtJxIV3Ug

[Matt Pocock @mattpocockuk]

Tactical vs Strategic Programming, and why I'm nervous for juniors:

Good programming involves a mix of tactical and strategic decision-making:

- Tactical: on the ground, short-term. The soldier doing the fighting.
- Strategic: high-view, long-term. The general planning the war.

You need to be a tactician to write good code. To choose the right syntax. To figure out the file structure. To figure out how best to test your changes.

But you need to be a strategist to build code that lasts. To design the architecture. To automate away problems. To think beyond today.

Agents have eaten the tactical part of programming. When you can pay below minimum wage for code, there's no point going into the trenches yourself.

But AI cannot code strategically. Agents need someone at the top of the pyramid to tell them what to do. They need oversight.

So, a developer's day-to-day job has become 100% strategy. Long-term thinking, all the time. (maybe this is why I'm so tired all the time now)

If you identify as a tactical programmer - a code monkey - then you are out of luck. The job has changed.

Personally, I like it. I always preferred thinking strategically about code. If you asked me what my job was about, I'd say 'building apps', not 'writing code'.

But what makes me nervous is that we've pulled down the only bridge that brought juniors into the industry.

We used to train juniors like this:

1. Give them only tactical tasks
2. Let them build up their strategic experience slowly

Eventually, they are a good enough strategist that they are no longer a junior.

But what happens when all tactical code is written by AI? What is the point of a junior?

We obviously need juniors. We need new lifeblood coming into the industry. We need to leave paths open for extraordinary hires to enrich our companies.

But how do we train them? How do you train strategic thinking?

These are the questions I'm thinking about. I'd love to know your thoughts.

[danialhasan @danialhasan]

https://t.co/wOFoVYiFV8

[David Ondrej @DavidOndrej1]

if you feel confused by AI progress

read this: https://t.co/aAkQhgsnec

[Josh Rosen @JoshARosen]

https://t.co/Ji42qhyxNj

[Uber Engineering @UberEng]

https://t.co/4E91KTbzDU

[Uncle Bob Martin @unclebobmartin]

Rights. What are they? If something is a right, then it MUST be provided. If we assert that healthcare is a right, then we MUST provide it -- by force if necessary.

What force would be necessary? Taxation would, of course, be the first force to be applied. But taxation is not sufficient. We'd also have to force providers. We could not allow providers to set their fees, schedules, or even their careers. We would HAVE to guarantee that there would be enough providers, of the right kinds, and in the right places, at all times. So we'd have to force the people with aptitude to become providers, and deprive them of any options. We'd have to make it illegal for those who are able to provide, to refuse to provide.

Some governments claim that they offer healthcare as a right. But they don't. What they offer instead is a queue to access a scarce resource. Worse, that queue is not served by the best -- because the best go where they can be paid what they are worth.