




<feed xmlns="http://www.w3.org/2005/Atom" xml:lang="en">
  <id>https://blog.i-9.ai/en/</id>
  <title>Mentor dos Nerds</title>
  <subtitle>Felipe Abreu writes about applied AI, agents, automation, software architecture, and the human effects of increasingly capable systems.</subtitle>
  <updated>2026-08-29T01:38:52-03:00</updated>
  <author>
    <name>Felipe Sayão Lobato Abreu</name>
    <uri>https://blog.i-9.ai/en/</uri>
  </author>
  <link rel="self" type="application/atom+xml" href="https://blog.i-9.ai/en/feed.xml"/>
  <link rel="alternate" type="text/html" hreflang="en" href="https://blog.i-9.ai/en/"/>
  <generator uri="https://jekyllrb.com/" version="4.4.1">Jekyll</generator>
  <rights>© 2026 Felipe Sayão Lobato Abreu</rights>
  <icon>https://blog.i-9.ai/assets/img/favicons/favicon.ico</icon>
  <logo>https://blog.i-9.ai/assets/img/favicons/favicon-96x96.png</logo>


  
  <entry>
    <title>I Turned My Blind Spots into Contracts for My AI Agents</title>
    <link href="https://blog.i-9.ai/en/posts/transformei-pontos-cegos-em-contratos-para-meus-agentes/" rel="alternate" type="text/html" title="I Turned My Blind Spots into Contracts for My AI Agents"/>
    <published>2026-08-28T00:00:00-03:00</published>
  
    <updated>2026-08-28T00:00:00-03:00</updated>
  
    <id>https://blog.i-9.ai/en/posts/transformei-pontos-cegos-em-contratos-para-meus-agentes/</id>
    <content src="https://blog.i-9.ai/en/posts/transformei-pontos-cegos-em-contratos-para-meus-agentes/"/>
    <author>
      
      <name>Felipe Sayão Lobato Abreu</name>
    </author>
  
    <category term="Artificial Intelligence"/>
  
    <category term="Personal AI Harness"/>
  
    <summary>How I use a revisable portrait of my patterns to build agents that add counterweights without diagnosing, deciding, or thinking for me.</summary>
  </entry>

  
  <entry>
    <title>If You Think AI Is Just a Chatbot, You Started with the Wrong Limit</title>
    <link href="https://blog.i-9.ai/en/posts/se-voce-acha-que-ia-e-so-chatbot/" rel="alternate" type="text/html" title="If You Think AI Is Just a Chatbot, You Started with the Wrong Limit"/>
    <published>2026-08-28T00:00:00-03:00</published>
  
    <updated>2026-08-28T00:00:00-03:00</updated>
  
    <id>https://blog.i-9.ai/en/posts/se-voce-acha-que-ia-e-so-chatbot/</id>
    <content src="https://blog.i-9.ai/en/posts/se-voce-acha-que-ia-e-so-chatbot/"/>
    <author>
      
      <name>Felipe Sayão Lobato Abreu</name>
    </author>
  
    <category term="Artificial Intelligence"/>
  
    <category term="Automation"/>
  
    <summary>AI can converse, execute, validate, organize evidence, and decide within policies. The useful limit starts with the problem, not the chat window.</summary>
  </entry>

  
  <entry>
    <title>ChatGPT Already Knows a Lot About You. Before You Trust It, Make It Show Its Work</title>
    <link href="https://blog.i-9.ai/en/posts/o-chatgpt-ja-sabe-muito-sobre-voce/" rel="alternate" type="text/html" title="ChatGPT Already Knows a Lot About You. Before You Trust It, Make It Show Its Work"/>
    <published>2026-08-28T00:00:00-03:00</published>
  
    <updated>2026-08-28T00:00:00-03:00</updated>
  
    <id>https://blog.i-9.ai/en/posts/o-chatgpt-ja-sabe-muito-sobre-voce/</id>
    <content src="https://blog.i-9.ai/en/posts/o-chatgpt-ja-sabe-muito-sobre-voce/"/>
    <author>
      
      <name>Felipe Sayão Lobato Abreu</name>
    </author>
  
    <category term="Artificial Intelligence"/>
  
    <category term="Personal AI Harness"/>
  
    <summary>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.</summary>
  </entry>

  
  <entry>
    <title>A Hypothesis Does Not Become Fact Because AI Repeated It</title>
    <link href="https://blog.i-9.ai/en/posts/hipotese-nao-vira-fato-so-porque-a-ia-repetiu/" rel="alternate" type="text/html" title="A Hypothesis Does Not Become Fact Because AI Repeated It"/>
    <published>2026-08-28T00:00:00-03:00</published>
  
    <updated>2026-08-28T00:00:00-03:00</updated>
  
    <id>https://blog.i-9.ai/en/posts/hipotese-nao-vira-fato-so-porque-a-ia-repetiu/</id>
    <content src="https://blog.i-9.ai/en/posts/hipotese-nao-vira-fato-so-porque-a-ia-repetiu/"/>
    <author>
      
      <name>Felipe Sayão Lobato Abreu</name>
    </author>
  
    <category term="Artificial Intelligence"/>
  
    <category term="Governance"/>
  
    <summary>How I use a Markdown and Git wiki to separate hypotheses, decisions, and syntheses before silent inferences start governing the system.</summary>
  </entry>

  
  <entry>
    <title>An AI expert since the day before yesterday</title>
    <link href="https://blog.i-9.ai/en/posts/especialista-em-ia-desde-anteontem/" rel="alternate" type="text/html" title="An AI expert since the day before yesterday"/>
    <published>2026-08-28T00:00:00-03:00</published>
  
    <updated>2026-08-28T00:00:00-03:00</updated>
  
    <id>https://blog.i-9.ai/en/posts/especialista-em-ia-desde-anteontem/</id>
    <content src="https://blog.i-9.ai/en/posts/especialista-em-ia-desde-anteontem/"/>
    <author>
      
      <name>Felipe Sayão Lobato Abreu</name>
    </author>
  
    <category term="Artificial Intelligence"/>
  
    <category term="Governance"/>
  
    <summary>Pseudo-experts turn recent discovery into authority. The antidote is to look for artifacts, consequences, review, limits, and responsibility.</summary>
  </entry>

</feed>



