I used to spend an hour every morning checking AI news and figuring out what to post about. Built a model that handles the whole thing automatically. What it does: - Monitors 4 sources daily: Anthropic changelog, Claude GitHub, Gemini release notes, AI influencer posts - An LLM filters the noise — only major updates make the cut - Generates a LinkedIn post, Instagram caption, and branded image for each update - Creates a ClickUp review card — I approve or discard in one click Saves 1 to 2 hours every single morning. Full live demo in the video. Stack: trigger.dev, FAL.ai, ClickUp

Voice agents used to mean clicking through ElevenLabs dashboards and wiring up API endpoints by hand. In this one I built a working voice agent for a website that captures leads and books discovery calls through cal.com, all by describing it in plain English to Claude Code. You'll see the full build, the bugs I hit along the way, and how I debugged them without ever touching the docs.

After 400 hours in Claude Code, I noticed that businesses keep paying for the same six types of skills. In this video, I break down each one, what it does, and why these simple, boring skills are the ones that actually sell. Whether you're brand new to AI automations or already building for clients, these are the skills worth learning first.

This is the full walkthrough of how I build my AI Operating System inside Claude Code, from the frameworks I use to think about it (the Three Ms and the Four Cs) to the actual setup, connections, skills, and routines that run while I sleep. By the end you'll know exactly how to set up your own AIOS, even if you've never opened Claude Code before. The full template, docs, and resources are free in my school community linked below. GITHUB REPO

If you're doing manual lead research on LinkedIn, this might be the most useful build I've shared. I was spending 10-15 minutes per lead, 25 leads a day — that's almost 4 hours of research daily. Built a system that does it automatically the moment someone accepts a connection: - Scrapes their LinkedIn profile and recent posts via Apify - Scores them 1-10: cold, warm, hot, or ideal client - Writes a personalized DM based on their actual profile - Suggests 3 posts to comment on with ready-made comments - Updates Airtable in real time — CRM never falls behind Full enrichment in 40 seconds per lead. Stack: Dripify, Sales Navigator, n8n, trigger.dev, Apify, Claude Sonnet, Airtable