In fist lecture you defined your agent project. Today you map how it actually runs. Fill in the blanks for your project and post your 5 lines below: PERCEIVE: My agent reads or receives ___ PLAN: The LLM decides ___ ACT: My agent then does ___ OBSERVE: The result my agent reads back is ___ STOP CONDITION: The loop ends when ___ I will comment on every single submission today. No lurking on this one.

I just uploaded a new YouTube video for the community. In this demo, I show how the SaaS Roast Agent reviews a real SaaS codebase using 6 AI agents. One agent scans the project. Five specialist agents review it in parallel: authentication tenant isolation security database performance architecture Then a final synthesis agent combines everything into one Launch Readiness Report. The report gives: → launch score out of 100 → category-level scores → critical issues → security risks → database and architecture problems → practical 7-day fix plan The idea is simple: Founders, indie hackers, and vibe coders are building faster than ever. But fast shipping without review can create dangerous production bugs. This agent helps you move fast without blindly launching risky SaaS code. Built with Python, FastAPI, and the official Claude SDK. Just Claude SDK, structured prompts, tools, and a practical multi-agent workflow. Watch here https://youtu.be/fsE-XLm1yxI After watching, tell me this: Would you use an AI agent like this before launching your own SaaS project?

Nobody talks about this: the 'thinking out loud' style of reasoning models is mostly noise for production. You don't ship a chatbot that goes 'Let me think... I should consider...'. Strip the chain-of-thought from outputs. Reasoning is useful internally, ugly externally.

Day 30 of my email sorter. now also drafts replies for the 'can wait' bucket. team is using the drafts as starter text. saved each person ~20 min/day they say. wild that the simplest agent in my system is the one that's actually useful.

created n8n + dockling + ollama + deepseek + qdrant + obsidian automation to convert all recent US government UFO files into a searchable and interconnected library that can be queried, visually searched and AI prompted.