Me and Fleet spent the weekend hacking my own house.
Savant, Lutron, Ketra, Sonos, a camera NVR. Five closed systems from vendors that would rather they never talked to each other.
Now they do, and I run all of it by voice from my iPhone.
Fleet found 12 shades the dealer's own config had never heard of.
https://t.co/daFGSdWmdg
introducing https://t.co/5XovfcaGai 🌱
claude and I built a website that uses rentahuman to spread more good in the world
choose a good deed and AI will hire someone, give them instructions, and validate their work!
Building with AI has quietly turned into reviewing everything a dozen agents write. Nobody signed up for that.
It helps to name where you actually are.
The Levels of AI-Assisted Engineering:
L0: Prompt & paste. Chat on one side, editor on the other. Copy, run, paste the error back.
L1: One agent. It lives in your editor, sees your project, writes real code. You review every line.
L2: The juggle. A dozen terminals of agents, and reviewing them is now your full-time job.
L3: Loops. You engineer the context, the harness, the loops that drive the agents. Running that machine is your new job.
L4: Fleet. You state a goal. The fleet writes the loops, manages the agents, verifies the work, proves it's done. You approve outcomes.
Most serious builders are stuck somewhere between Level 2 and Level 3: juggling more agents than they can review, wiring up loops they never quite finish. Doing neither well. The principal engineers built Level 3 for real, by hand.
I've spent five years on this ladder. This week I'm posting the full map, and what the top rung looks like.
Rentahuman (@RentAHumanX) allows AI agents to communicate with and pay humans to do tasks in the real world. Their mission is to use AI to create new jobs and coordinate workers at global scale.
The future will have more intelligence, more jobs, and more opportunities for people outside of the digital world.
Congrats on the launch, @alexandertw33ts!
https://t.co/3UTfa1SSmU