I Built a 3-Agent Pipeline That Turns My GitHub Activity Into Weekly Blog Posts

<p>My side project, <a href="https://justinnnnnnn045.github.io/pd-engine/" rel="noopener noreferrer">PD.Radar</a>, ranks resources mentioned in big Ask HN threads by

<p>I publish a blog post. Then I spend the next two hours:</p> <ul> <li>Rewriting it as a Twitter thread (5 tweets, each under 280 chars)</li> <li>Adapting it to LinkedIn tone

<h1> How I Built an AI Agent That Queries GitHub, Calendar, and Sleep Data With One SQL Interface </h1> <p><em>A practical guide to Coral — the local-first SQL runtime that gives

<p><strong>TL;DR:</strong> I built the same browser agent twice — once with 500 lines of Python, once with 7 lines of JSON. The second one took 5 minutes. The agent harness layer

<p><em>This is a submission for the <a href="https://dev.to/challenges/notion-2026-03-04">Notion MCP Challenge</a></em></p> <p>I want to show you something that happened at 3:17

<h1> Building an Automated Engineering Telemetry Pipeline with GitLab CI/CD </h1> <p>When you manage dozens of repositories across multiple projects, microservices, and AI

<ul> <li>GitHub repository: <a href="https://github.com/gezilinll/agent-grove" rel="noopener noreferrer">https://github.com/gezilinll/agent-grove</a> </li> <li>Online

<p>I saw a tweet about Sentry shipping an AI agent that watches your error logs and auto-suggests fixes. I thought: I can build that. So I did — from my phone, on a Friday