Professional agentic AI, on the Claude platform.
Training for individual contributors and engineering teams.
Most people use AI assistance as a fancier autocomplete. Working with agents in production takes method: context, judgment and verification. That is what I teach.
✦ Claude Code
From zero to professional, one tip a day.
253
tips published.
Tomorrow, 254.
164 days in a row publishing.
Today: #253
By intent
Onboarding, mastery, autonomous...
By topic
Skills, MCP, hooks, models...
Latest
All content by date
Training and consulting on the Claude platform.
AI First on the Claude platform
A working day with your team, online, on the Claude platform. More output without losing quality.
Agentic AI for companies
I assess how your team works and agentify the processes one or several agents can take on.
At FrontendLeap I teach you to build the professional Web with agentic AI and learning science.
FrontendLeapStop Claude Code asking for permission (without losing control)
Permission prompts in Claude Code don't go away with one setting. There are five levers (rules, modes, auto mode, the sandbox and bypass inside a container), and this guide puts them in the order that cuts the most prompts for the least risk.
Claude Code first steps: the fundamentals that don't expire
The Claude Code fundamentals that don't expire: install, sessions, context, quota, models, permissions. What you actually need to grasp on day 1.
AI: the joy of missing out on what doesn't matter
You can't keep up with AI, and you shouldn't try. The answer isn't resistance or passive acceptance: go all in, but deep on one thing instead of scattered.
Claude Code Agent View: managing parallel agents without leaving the terminal
I spent months managing many Claude Code agents by hand. Agent View now does it: my terminal-native workflow with Warp and Neovim, and the gaps I patch.
What is Claude Code: A Practitioner's Overview
What Claude Code actually is, explained by someone who uses it 12+ hours daily in production. No hype, real examples.
MCP server not available in Claude Code scheduled tasks: how to fix it
The MCP server you use in your terminal doesn't exist for a cloud scheduled task, and the run still says Succeeded. The three places it does load servers from, and which one fits yours.
Claude Code 5-hour limit: gone on Ultra, the weekly limit is your only wall
Ultra, formerly Max 20x, no longer has a 5-hour limit on verified accounts: in Claude Code only the weekly limits stop you. What stops happening (the cutoff, the wrap-up) and why your status line may paint a fake 0%.
Claude Code watermark: it's already in what it writes, and costs no tokens
Claude's watermark is already in the text Claude Code writes on current models, with no extra tokens and no price change. Where it lands (little in code, more in commits, PRs and docs) and what doesn't remove it.
Run multiple Claude Code sessions in Desktop: Claude tells you which did what
Multiple Claude Code sessions open and no idea which one is doing what. Desktop puts two side by side with Option+click, pops others into their own window, and lets Claude tell you which one did what.
"Received a CI event" in Claude Code: it's Auto-fix pushing to your PR
"Received a CI event" in Claude Code Desktop comes from your own Auto-fix: the app watches your PR's CI and reviews and wakes the session so Claude fixes and pushes to that branch. What it authorizes, what it doesn't, and how to stop it.
Hi, I'm Juan Andrés Núñez.
Senior Software Engineer specializing in agentic AI, professional educator and speaker. Over fifteen years building for the Web and teaching how to do it. Today I work with the Claude platform every day. Here I publish everything I learn.
