Juanchi.dev
Digital Native · real systems
·
HomeCasesCVBlogLabContact
Juanchi.dev
Digital Native · real systems
·
HomeCasesCVBlogLabContact

Agents and LLMs with judgment

39 posts on LLMs and 30 on agents: sandboxes, guardrails, cost per task, and running your own benchmarks instead of trusting screenshots.

  • Agents that execute

    Sandboxes, permissions, and what happens when an agent actually runs commands.

  • Measuring models

    Comparisons on your own cases, with cost and latency, not generic leaderboards.

  • The real cost of AI

    Tokens per task, caching, and where the monthly bill comes from.

Recommended reads

View more
Sep 09 2026

Claude API Key Security: Why .env Is Not Optional

Pasting a Claude or DeepSeek API key straight into your code "just to test it quick" leaves a trail in your git history and your logs. A no-nonsense guide to environment variables, rotation, and what to check before sharing a repo.

Sep 09 2026 · 7′ · Tutorials · nextjs · anthropic

7′
Sep 07 2026

Sniffnet: How Much Traffic Are My AI Agents Generating Behind My Back

I installed Sniffnet to check what network traffic Cline and background LLM API calls actually generate. Here's what the tool shows you, and what you can't conclude from a single observation session.

Sep 07 2026 · 8′ · Tutorials · agentes-ia · networking

8′
Sep 03 2026

DeepSeek Reasonix: A Technical Read on a Native Coding Agent with Aggressive Caching

DeepSeek Reasonix shows up as a native coding agent with aggressive caching and low cost. Before you adopt it or dismiss it, there's a more useful question: what specific problem does it actually solve in a real stack, and what reproducible experiment confirms that?

Sep 03 2026 · 9′ · Opinion · LLM · ia

9′
Aug 17 2026

Noroboto: Lying Fonts and Rust Mitigation — A Technical Read Without the Hype

Fonts lie. Noroboto documents how the text subsystem can return incorrect metrics and proposes mitigations in Rust. Before you copy it into production, you need to understand what problem it actually solves, where the common recipe breaks down, and what reproducible experiment is actually worth runn

Aug 17 2026 · 8′ · Opinion · linux · sistemas

8′
Aug 17 2026

Cline in production: the autonomous code agent for VS Code I use with deliberate constraints

Cline can create files, run commands, and open the browser autonomously from inside VS Code. That sounds like productivity. It also smells like risk if you haven't thought through the permissions before you start. My thesis: the mental model matters more than the tool.

Aug 17 2026 · 9′ · Tutorials · TypeScript · LLM

9′
Aug 02 2026

Qwen3 locally with Ollama: what changed in the architecture and whether it's worth switching

Qwen3 landed with thinking mode and real improvements in code generation. But before you replace the model already running in your Ollama setup, there are technical questions you need to answer first. I answer them here without selling hype.

Aug 02 2026 · 9′ · Tutorials · TypeScript · Inferencia Local

9′

Juanchi.dev is Juan Torchia’s public notebook — architecture, real systems and product decisions. Written and reviewed by hand in Buenos Aires. Built with Next.js, Prisma and PostgreSQL; deployed on Railway. No third-party trackers beyond aggregate analytics.

BlogUsesNowGitHubRSS© 2026 Juan Torchia · All rights reserved.