Jefferson Lopez

Full-Stack Software Engineer | Building SaaS Products with Next.js, React & TypeScrip

[Jefferson Lopez @jeffersonmendza]

@FaztTech Hoy salió opus 5.5, mañana será el opus 5.6

[Jefferson Lopez @jeffersonmendza]

@0xPrajwal_ It’s missing a few things

- Try/catch error handling
- Data validation
- A better-structured JSON response

[Macfolio @hellomacfolio]

This  Mac App brings App folders to your dock!

[Jefferson Lopez @jeffersonmendza]

@FaztTech Sublime Text para aprender html css y js

[Jefferson Lopez @jeffersonmendza]

@MoureDev Experto en Jev
Curso de 20 horas Jev

[Jefferson Lopez @jeffersonmendza]

Working on themes today 🎨

one visual direction for the whole presentation.

#BuildInPublic

[Jefferson Lopez @jeffersonmendza]

@rpa_dake same haha, i’m trying to make the MCP able to do pretty much everything. basically, if you can do something in the editor, the AI should be able to do it too

[Jefferson Lopez @jeffersonmendza]

time to see how good Jev is at making presentations with MCP

#BuildInPublic

[Jefferson Lopez @jeffersonmendza]

Thanks!! gentle-ai with GPT-5.6 terra on medium helped a lot

But its not just prompting. i still had to figure out the architecture, plan the features, review the code, and keep guiding everything along the way. i also spend a lot of time thinking about the ux and how to make creating a presentation feel as easy as possible

[Shann³ @shannholmberg]

here's how JEV works, simplified

I've been experimenting with it for the last hour, and it's EXTREMELY good at making decisions with the right references and context

you give it the information, your questions, and the type of answer each question needs:

> a choice from options you provide
> a score on a scale you define
> a probability that something is true

the models we're used to often give us long written answers, with explanations and reasoning

jev returns structured answers your app can use directly, instead of generating those explanations

information + your questions + allowed answers → answers your app can use

you define what happens next, based on those answers

that could mean sending information to the right place, checking an AI agent's work, or flagging something for human review

because jev doesn't generate prose, it doesn't invent facts or sources inside a written explanation (hallucinations)

clear questions and useful context matter, including references that explain what it should check

I'm seeing so many cool use cases across X, and I can see people adding this to all kinds of existing apps

if you haven't started building with it yet, try it on one decision your app already makes

[Jefferson Lopez @jeffersonmendza]

@j3rah_ thanks! really appreciate that 🙌

[Jefferson Lopez @jeffersonmendza]

Making text editing a little better

Type something...

#BuildInPublic

[Patrick @glorpiak]

@codewith55 You are writing a post on X.

What are you using?

A) ChatGPT
B) Gemini
C) Claude
D) Grok

[Jefferson Lopez @jeffersonmendza]

@elijs_dev Y no son lo mismo🤔

[Jefferson Lopez @jeffersonmendza]

@DmitryBBLV Thanks!! 🙌 trying to get the little details right

[Jefferson Lopez @jeffersonmendza]

Transitions are in.

Slowly making presentations feel a little less static. #buildInPublic

[Jack Cheng @jackcheng]

Jev is the future

[Jefferson Lopez @jeffersonmendza]

@BendikMatej index.html
styles.css
app.js

[Fazt @FaztTech]

Mis herramientas de IA favoritas a día de hoy

Orquestación → Herdr
Coding Harness → Claude Code / Codex / OpenCode
Asistente → Hermes CLI / Hermes Desktop
Research → Perplexity
Testing → Playwright CLI
Tareas → Notion MCP / Linear MCP / CLI propio
Imagen + Video → Higgsfield CLI
Diagramas → Excalidraw MCP
Git → gh CLI
Deploy → AWS CLI / Railway CLI / Azure CLI
Editor → VS Code (solo exploración de archivos)
Terminal → WezTerm