gast@schmalzl.tirol — One person, many agents
Style
Look
Random
Style
Background
Font
Text
Language
Emojis
Reading
Display
Show
Mouse trail
Quick
Help on all settings →only stored in this browser
Games in the terminal
Arrow keys, space, P to pause, Esc quits. High scores stay in this browser only.
?
How to use
Style
Looks like the macOS terminal, a Linux shell or PowerShell, each light, dark or blue. Remembered in the browser.
gast@schmalzl ~
The prompt line is the navigation. It shows the path, for example ~/software/macos: every part is clickable, ~ leads to the home page, /software one level up.
Pages with a lock are only visible after signing in. login at the top right.
Tables
The search box searches all columns, clicking a column heading sorts, the drop-downs filter.
One click copies the install command for Chocolatey, winget or Homebrew to the clipboard.
– ☐ ✕
The window buttons, on macOS the traffic-light dots, minimise, maximise and “close” the page. Everything comes back by itself.
The status line at the very bottom counts just for fun: time on the page, left and right clicks, mouse distance in metres, scroll distance, keystrokes, pages. Only in this tab, nothing is sent.
14 small games in terminal style, from Serpent and Blocks to Ski Jumping and Mines. Arrow keys, space, P to pause, Esc quits.
Pride
The fourth style: rainbows everywhere, with little hearts when you move the mouse. “↺ reset everything” in the same menu puts all settings back to the start.
Aa
The style menu can also change the font (Terminal, Arial, Times, Comic, Wild or any Google Fonts font by name), translate the whole page (1337, Pirate, ASCII, upside down, CAPS) and switch on an emoji mode that adds matching emojis to words. Applies to every page, including new posts.
Keyboard
? opens this help, Esc closes menus.
Read the help → · everything in detail →
PS gast@schmalzl ~C:\Users\gast/en/blog/2026-10-15-ein-mensch-viele-agenten
DE login

One person, many agents

By

#KI #Agenten #Claude #Werkstatt

15 October 2026

"I built an office for my AI agents." That is how an Instagram post begins that I made a note of this week. It shows an office with 8 teams and 31 AI agents that share a common memory. One team searches GitHub for new things every morning. One writes texts. One edits videos, with sub-agents working in parallel. One plans the posts for social networks.

One sentence in it stuck with me: nothing bigger goes out without a human OK.

From assistant to team

An agent is an AI that does not just answer, but carries out steps itself: reading files, searching the web, writing code, checking results. For a long time, that meant one agent for one task. Now they are becoming teams.

There are ready-made tools for this by now. oh-my-claudecode lets several agents in Claude Code work together as a team. Multica wants to turn people and agents into one shared team, self-hosted. And in a video, the AI expert Allie K. Miller explains how a single person runs 34 agents.

The work shifts

If you have many agents, you write less yourself. Instead, you have to define more:

The crucial question is: who decides the next step? If the goal is missing, the AI has to guess. With 31 agents, it guesses 31 times.

My small example

I work like this myself, just on a small scale. For this blog there is an editorial office with an AI editor. I send links to a collection inbox. Claude reads them, checks the sources and writes drafts. I see every draft exactly as it would appear in the blog, and I decide: approve, revise or discard.

This text was created the same way. It will only be published when I click "Approve".

My conclusion

Agent teams take a lot of legwork off your hands. But they do not replace judgement. The more agents work on something, the more important the point becomes where a human says: this is right, this goes out.

Sources: Instagram @bexruz.khamidullaev · oh-my-claudecode on GitHub · Multica on GitHub