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's what I teach.
✦ Claude Code
From zero to professional, one tip a day.
258
tips published.
Tomorrow, 259.
167 days in a row publishing.
Today: #258
By intent
Onboarding, mastery, autonomous...
By topic
Skills, MCP, hooks, models...
Latest
All content by date
My Claude Code workflow.
The skills, agents and instructions I use as a professional Software Engineer. It's called Craft, and it's a plugin you can install.
See the skillsTraining 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 "needs you to sign in again" in Claude Code: reconnect without a new session
An MCP server or claude.ai connector that expires mid-session doesn't mean starting a new one. How to reconnect it in the terminal and in the cloud, tested with tokens that really expired.
Finished Claude Code scheduled task: keep talking to it, even from your phone
A cloud scheduled task run that stopped to ask you something or left work half done isn't fixed by launching another one: open it and reply, even hours after it finished.
Test WebMCP tools from Claude Code: use the Chrome DevTools MCP, not /chrome
WebMCP tools your page registers can be listed and run from Claude Code through the Chrome DevTools MCP, before a real agent touches them. It takes two flags, and without Chrome's the list comes back empty with no error at all.
Claude Code background agents: seeing what they do now costs 99% less
Claude Code background agents rewrite their status every 30 seconds, and on the old path each rewrite re-sends their whole conversation. Anthropic switched it to short notes, but account by account: here is how to check yours.
Dashboard from Claude Code: use a claude.ai connector, not a local MCP
A Claude Code dashboard has no numbers typed into its HTML: each figure points to its source, and a live query runs again when the page opens. The catch: your local MCP server never reaches the published version.
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.
The 51 essentials, as a guide.
One page per tip. Five chapters. What I actually use daily in production. No theory, no fluff.