Nacho Gutierrez

CTO @Timeline_Tech. I also maintain Sedum (

[Nacho Gutierrez @devnacho]

POV: You work in cybersecurity in October 2026.

[David Marcus @davidmarcus]

The thing I’m most grateful to Elon for is bringing back an age of wonder and excitement to humanity. That was jaw-dropping awesome! Screams and mouths wide open in the audience. Nuts.

[José Valim @josevalim]

I have asked my clanker to send some PRs for the Elixir one. Please ask your clanker to verify them and tell your clanker we are allowed to deviate from the Rails version in the same way Express/Go/Rust/ do (it was objecting to that in other PRs)!

The clanker says there is more work to be done but I don't have infinite tokens, so it would be nice to see those merged first.

[Nacho Gutierrez @devnacho]

@dmokafa Nice! Jev is great for this.

We went the same way with Sedum (open source, on Playwright), and the probability scores made failing tests much easier to trust.

https://t.co/lDplVboogu

[Nacho Gutierrez @devnacho]

@jamesqquick Just added Clef support to my OSS library. Of all the system-one models I’ve tested, Clef is the first one that feels genuinely on par with Jev.

https://t.co/lDplVboogu

[Nacho Gutierrez @devnacho]

@thorstenball if it quacks like not-slop and walks like not-slop, it is probably not slop

[Nacho Gutierrez @devnacho]

@dhh For those adversarial review loops I like Swamp Club and the concept of blackbox UAT tests
https://t.co/EQfXVsF8U1

Could be useful for Omarchy releases :)

[Nacho Gutierrez @devnacho]

@dhh 100% agree. If review is done manual there is a big mismatch in the development pipeline. Is like connecting Starship water deluge system (ie AI code generation) to the pipes of a house. It will not handle the pressure.

[Nacho Gutierrez @devnacho]

@rauchg https://t.co/lDplVboogu

[Nacho Gutierrez @devnacho]

@rauchg Worth adding that a key characteristic for AI end-to-end tests is to bring the cost way down to increase the run frequency.

That's why I've built https://t.co/0VNMqLRkES (Open Source too-slightly different) on top of Jev.

[Tobias Naftali @tobiasnaftali]

made a small thing: s1, a TUI for testing System One (jev-like) models.

fill in a state, pick a type, write an instruction, get a typed answer back: noul, choice, or score; with calibrated confidence. all from the terminal.

https://t.co/msZ4XWAyK3

[Nacho Gutierrez @devnacho]

@typesafeai https://t.co/lDplVboW62

[Nacho Gutierrez @devnacho]

@typesafeai For end-to-end browser tests written in plain english we are talking 50x cheaper (in the worst case) and 5x faster.

Jev 🩷

[Nacho Gutierrez @devnacho]

@eduarD3V_ Lo uso para end-to-end tests escritos en plain english.

Escribí esta librería para reemplazar todos los flaky e2e tests en mi trabajo y correr los tests relacionados al cambio en cada push de una manera económica

https://t.co/lDplVboW62
https://t.co/0VNMqLRSuq

[Nacho Gutierrez @devnacho]

I'm CTO at @Timeline_Tech. We're shipping more than ever, all of it written with agents, and we needed e2e tests that keep up: easy to grow, resilient, and cheap enough to run all the time.

So I built Sedum on top of Jev. Thanks @typesafeai for making the numbers work.

[Nacho Gutierrez @devnacho]

A Sedum test is just sentences:

click the Add to cart button for Monstera
click the Cart link
click the Checkout button
type {{name}} in the Full name field

Here I renamed the Checkout button to "Continue to payment" and didn't touch the test. Still passes.

[Nacho Gutierrez @devnacho]

It's alpha, so the format will change. Works on macOS, Linux and Windows. MIT. Open Source. Bring-your-own key.

npx sedum init
https://t.co/lDplVboogu
https://t.co/0VNMqLRkES