How I turned old conversations into testable hypotheses about my writing, decisions, and way of working—and then into contracts for a personal AI harness.
01
Artificial Intelligence
Pinned
Technology / career / artificial intelligence
Mentor dos Nerds
Felipe Abreu writes about applied AI, agents, automation, software architecture, and the human effects of increasingly capable systems.
16 published articles
Editorial archive
Recent reads
02
Artificial Intelligence
Pinned
Your Company Doesn't Need to Figure Out Where to Put AI
Where to use AI in the company? A practical guide to finding bottlenecks and choosing between process, automation, AI assistance, agents, and human decision-making.
03
Artificial Intelligence
Pinned
The best answer isn't the one that pleases me most
Why useful agents need to expose uncertainty, point out blind spots, and turn human criteria into a verifiable system.
04
Artificial Intelligence
I Turned My Blind Spots into Contracts for My AI Agents
How I use a revisable portrait of my patterns to build agents that add counterweights without diagnosing, deciding, or thinking for me.
05
Artificial Intelligence
If You Think AI Is Just a Chatbot, You Started with the Wrong Limit
AI can converse, execute, validate, organize evidence, and decide within policies. The useful limit starts with the problem, not the chat window.
06
Artificial Intelligence
A Hypothesis Does Not Become Fact Because AI Repeated It
How I use a Markdown and Git wiki to separate hypotheses, decisions, and syntheses before silent inferences start governing the system.
07
Artificial Intelligence
An AI expert since the day before yesterday
Pseudo-experts turn recent discovery into authority. The antidote is to look for artifacts, consequences, review, limits, and responsibility.
08
Artificial Intelligence
You Wrote It, Didn't Read It—and Then It Bit You: AI Doesn't Sign for You
Real cases show why reviewing AI-generated content isn't polish: it's authorship, accountability, and control before publishing or deciding.
09
Artificial Intelligence
Writing with AI Didn't Make Me Less of an Author. It Made It Possible to Keep Writing
The problem isn't using AI to write, but outsourcing voice, thought, and responsibility. How an authorial system preserves direction and consistency.
10
Artificial Intelligence
Generic Agents Can Be Your Company's Worst First Encounter with AI
A ready-made solution can fail by ignoring process, data, and accountability—and teach your company to reject the AI that could actually help.