I Built an AI Agent Company (From Scratch)

March 26, 2026

AI Summary

5 min read

Paperclip offers a way to orchestrate AI agents into structured teams that handle business goals, with tracking for tasks, budgets, and progress. In this episode, creator Dota walks through its setup and use, drawing from his experience building it to manage his own projects amid scattered Claude Code windows. He demonstrates on a sample finance app called Moolah, emphasizing high-level oversight while agents execute.

Core Setup and Workflow

To start, install Paperclip locally—ideally with tools like Claude Code or Cursor already set up—and define a company goal, such as "a finance app that builds money habits in three minutes a day." Hire a CEO agent first, using a frontier model like Claude Opus for planning; cheaper or free models via OpenRouter work for routine tasks. The CEO drafts a hiring plan, breaks roadmaps into issues (e.g., user auth, daily loops), and delegates.

Agents operate via a GitHub-style issue system: one agent per task to avoid conflicts, with all activity logged for review. You approve initial hires manually, then monitor via a dashboard showing live tasks, monthly token spend (zero if using subscriptions), and org charts. Dota stresses running multiple companies simultaneously, as he does with Paperclip itself, Forgotten Runes, and others.

Continue reading the full summary in the app — free to try.

Read Full Summary →

Free • No credit card required

Listen to Audio Summary Open in App

What you'll learn

1 (00:00) **Intro to Paperclip** - Host introduces viral open-source project for orchestrating AI agent teams into zero-human companies
2 (01:55) **Creator Background and Episode Goals** - Dota via avatar shares NFT origins and promises setup guide, tips for quality work, future roadmap
3 (02:32) **Paperclip Overview** - Dashboard demo; tool for managing business goals by hiring AI agents with approval workflow
4 (04:21) **Demo: Picking Idea and Setup** - Select "Moolah" finance habit app from idea browser; name company, paste goal, hire CEO agent
5 (07:51) **Hiring First Engineer** - CEO creates hiring plan, roadmap, tasks; dashboard tracks multiple companies, spend, issues
6 (10:40) **Inbox Approval Workflow** - Manual approve CEO's engineer hire; prevents agent conflicts by single-agent-per-task
7 (12:01) **Live Tasks and Concurrency** - Engineer works on scaffolding, auth, daily loop; adjust settings for multi-tasking

+ Full timestamped outline available in the app

Show Notes

I sit down with Dotta, the pseudonymous co-founder of Paperclip, the open-source agent orchestrator that exploded to 30,000 GitHub stars in under three weeks. We walk through a live demo where I pick a startup idea from my idea browser and we spin up a full AI-agent company in real time — hiring a CEO, founding engineer, QA agent, video editor, and content strategist inside Paperclip. Dotta shares practical tips on agent configuration, memory systems, skill installation, and the "Memento Man" mental model for keeping agents on track. The conversation covers everything from token spend management and agentic design patterns to the future of importable, shareable companies and the upcoming Maximizer Mode.

Skills to build your agent team: https://startup-ideas-pod.link/skill-suite

Timestamps:

00:00 Intro

02:32 What is Paperclip

04:21 Choosing a Startup Idea for the Demo

05:48 Setting Up your agents

07:51 Hiring Your First Agent and Creating a Plan

12:39 Agent Configuration and Persona Setup

17:08 Skills: Installing and Managing Agent Capabilities

21:02 How to Get Top-Quality Output from Agents

24:05 Token Spend Tracking and Subscription Usage

25:49 Agentic Design Patterns and QA Loops

29:05 Taste and Values: What AI Still Cannot Do

30:09 How Many Agents Run the Paperclip Project

32:32 Routines: Automating Recurring Agent Tasks

36:36 Who Is Using Paperclip Today

38:57 Shareable and Importable Companies

42:49 The Unproven Frontier: Do Agent Orgs Actually Work?

42:49 Maximizer Mode and What's Next

44:29 Did Dotta Expect It to Go This Viral?

Key Points

Paperclip is a bring-your-own-bot orchestrator: it works with Claude Code, Codex, OpenCode, and any model on OpenRouter, so you are not locked into a single provider.
AI agents are "Memento Man" — they wake up capable but with zero memory, so you need heartbeat checklists, persona prompts, and written context to keep them effective.
The biggest lever for quality output is encoding your own taste and values into agent skills and brand guides, because AI can do everything except know what you actually want.