Tomas Gonzalez

UTC-3 Product-minded SWE

[Tomas Gonzalez @gztomas]

Atriana is a CAD tool I'm building where the agent does the CAD. I wrote the three things it needs to be useful: a way to draw, a way to see what it drew, and a way to show the result to a human. Here's Claude modeling a wood-burning stove.

[shadcn @shadcn]

Take a break from prompting today and go watch Messi play. Doesn’t matter if you’re a fan or not.

Football like this won’t come around again.

[Tomas Gonzalez @gztomas]

It runs with any MCP client. The app also sends screenshots back to the agent so it can review its own work and iterate.

https://t.co/fuK8KxI2ps

[Tomas Gonzalez @gztomas]

Atriana is a CAD tool I'm building where the agent does the CAD. I wrote the three things it needs to be useful: a way to draw, a way to see what it drew, and a way to show the result to a human. Here's Claude modeling a wood-burning stove.

[Tomas Gonzalez @gztomas]

Same model, 2D drafting mode. Top, front, and right projections come out automatically.

[Tomas Gonzalez @gztomas]

@mattpocockuk Not a secret technique but useful. Letting the agent use your product and give feedback about it, report bugs, etc. https://t.co/rhKuS0q1PE

[Tomas Gonzalez @gztomas]

Don't ever, for any reason, do anything, to anyone, for any reason, ever, no matter what, no matter where, or who, or who you are with, or where you are going, or where you've been, ever, for any reason whatsoever. Never try to start the dev server, it's already running.

[Tomas Gonzalez @gztomas]

@FuHap38899 @astronowi “nomás” 😂

[Tomas Gonzalez @gztomas]

@archie11235813 🤣 tome mi dinero

[Tomas Gonzalez @gztomas]

There's something circular about testing: you can only write tests for bugs you've already imagined. The ones that reach production are always the ones you hadn't considered.

[Tomas Gonzalez @gztomas]

@archie11235813 Exacto! Definitivamente no llega al nivel de un buen QA, pero me sorprendió todo lo que puede encontrar.

[Tomas Gonzalez @gztomas]

@housecor 100%. I write product specs in markdown and have the agent run them against a real browser. It finds bugs I wouldn't have written tests for because I hadn't thought of them yet.

https://t.co/rhKuS0q1PE

[Tomas Gonzalez @gztomas]

It's not a CI replacement. It catches a different category of problems: the bugs that live in the gaps between features you planned. Wrote about the full setup and what it actually finds.

https://t.co/rhKuS0q1PE

[Tomas Gonzalez @gztomas]

I've been trying something different. Instead of test scripts, I write product specs in markdown. Plain descriptions of what each feature does, from each persona's perspective, with invariants the system should hold. Then an AI agent reads the spec and tests the app the way a user would, probing edge cases I never thought to script.

[Tomas Gonzalez @gztomas]

Made a tiny CLI so Claude Code can talk to me using ElevenLabs TTS.
Just tell Claude in your https://t.co/wkiqeMeXQl to use utter me for responses. That's it.
https://t.co/sKgTAPRVrW

[BURKOV @burkov]

The new software development paradigm: the purity of the codebase is no longer the holy cow protected by angry senior devs.

Companies will use agentic code systems like Claude Code Opus 4.5 to fix messy codebases as long as they are fixable.

Once each new fix starts taking too much time or consuming too many tokens, the entire non-fixable piece will be rewritten from scratch based on the spec and the unit tests remaining from the previous non-fixable version.

No human will be involved in the code writing. Only in the spec and test writing.

[Ted Nyman @tnm]

We figured out a new way to work with infra data: not old static dashboards, not “AI on every click” chaos.

But generative UI with structure.

Cased generates a controller, validates it, then runs real data: fast & predictable. AI does the thinking, UX stays fast. Check it out:

[Ted Nyman @tnm]

generative (and extremely fast) infra dashboards for you

[Ted Nyman @tnm]

Read more about why we wrote sandboxes, so you can run AI-generated code safely with any cloud provider:

https://t.co/IIwgTRNYKi

[Ted Nyman @tnm]

Say hello to sandboxes, new open source from @runcased.

A universal interface to AI code execution sandboxes in the cloud.

Write your code once & switch between providers like @modal, @e2b, @daytonaio with one line change.

Run code in any language. Python API + powerful CLI.