marcelotaparelli

AI & Software Engineering

Brazil Joined on Mar 27, 2024 contato@marcelotaparelli.com.br https://marcelotaparelli.com.br

Education

Systems Analysis and Development — UniBF, 2026

Work

AI Engineer at Agência Catus and EVAG

marcelotaparelli

Oct 10

DefectRisk

#ai #machinelearning #python #programming

4 min read

Want to connect with marcelotaparelli?

Create an account to connect with marcelotaparelli. You can also sign in below to proceed if you already have an account.

Create Account

Already have an account? Sign in

marcelotaparelli

Oct 7

OpsPilot AI: Building RAG and Agents Without Giving the LLM Authority

#ai #python #rag #programming

11 min read

marcelotaparelli

Oct 2

Laya vs Jev in Practice: Zero-Shot, Fine-Tuning, and the Real Cost of an Open-Source Decision Model

#ai #machinelearning #opensource #mlops

12 min read

marcelotaparelli

Sep 23

Jev 1.13 in Practice: I Tested a Decision Model Against Rules and a Local LLM

#ai #llm #machinelearning #programming

4 min read

marcelotaparelli

Sep 19

A Valid JWT Does Not Mean Authorized Access

#security #api #backend #typescript

2 min read

marcelotaparelli

Sep 16

Evals: I Stopped Asking Whether the LLM “Looks Good” and Started Measuring

#ai #llm #machinelearning #programming

4 min read

marcelotaparelli

Sep 15

The LLM Didn't Win Everywhere — and That's What Made the Project Interesting

#showdev #ai #llm #machinelearning

2 min read

marcelotaparelli

Sep 13

Why I Built My Portfolio with Bun + Astro + MDX Instead of a More Complex Stack

#showdev #webdev #astro #bunjs

5 min read

marcelotaparelli

Jul 4 '25

⚡ C# Tip: ToCharArray() vs ToArray() — Why It Matters More Than You Think

#csharp #dotnet #performance #programmingtips

1 min read

DEV Community

marcelotaparelli

Badges

Two Year Club

Writing Debut

One Year Club

Skills/Languages

Currently learning

Currently hacking on

Available for

DefectRisk

Want to connect with marcelotaparelli?

OpsPilot AI: Building RAG and Agents Without Giving the LLM Authority

Laya vs Jev in Practice: Zero-Shot, Fine-Tuning, and the Real Cost of an Open-Source Decision Model

Jev 1.13 in Practice: I Tested a Decision Model Against Rules and a Local LLM

A Valid JWT Does Not Mean Authorized Access

Evals: I Stopped Asking Whether the LLM “Looks Good” and Started Measuring

The LLM Didn't Win Everywhere — and That's What Made the Project Interesting

Why I Built My Portfolio with Bun + Astro + MDX Instead of a More Complex Stack

⚡ C# Tip: ToCharArray() vs ToArray() — Why It Matters More Than You Think