Run your solo business from a text-based agent system
A solo founder used one generalist agent to handle sales, content, outreach, and ops from a git-based workspace with human approval on risky actions.
- What they did
- They organized the company as plain-text folders and playbooks inside a single git repo, then let one broad agent assign work across sales, CRM, content, outreach, and operations. Browser and CLI tools connected the agent to LinkedIn, Instagram, Google Workspace, and internal software. The agent drafted everything into an approval queue, while the person checked edits and took over any step that could not be undone.
- How it went
- Over six months, they landed a first paying client, closed two cold leads, cut about ten subscriptions by switching to tools they owned, and brought in five-figure revenue. It also caused problems: social automation led to an account suspension, some drafts and queues sat unnoticed, and AI-made engagement on reused content came off as slop copy.
- Tips
- Use subagents only for tasks that truly need parallel work, since the poster said they burn about 15x the tokens. Keep a strict review step before anything is sent, posted, paid for, or deleted.
Try it yourself with Claude Cowork
I run [type of business] and want to manage it with an AI agent. Use this content source: [paste post or notes]. Break it into [number] useful assets, such as [email draft, social post, reply draft, checklist], and keep the wording close to my style using these examples: [paste 2-3 samples]. Put every item into a review queue, flag anything that needs my approval, and stop for confirmation before you send, publish, delete, pay, or submit anything. Also tell me what you would do first, what you can automate safely, and where human review is required.
Fill in the [brackets]. Agents can make mistakes, so review anything before it is sent, paid or deleted.
Get 3 agent uses like this every morning
With the day's top AI news. Free, and one click to unsubscribe.
Related agent uses
Review contracts and consumer rules with legal agents
An in-house lawyer used cloud legal AI tools to review agreements and check consumer-protection compliance.
Move supplier email details into an inventory sheet
An automated email workflow turned supplier messages into spreadsheet updates for a small e-commerce store.
Use a voice agent for oral exams
A professor used a voice agent to run oral finals, then had an LLM panel grade the transcripts and flag shared weak spots.
Use AI to speed up multifamily deal research
A multifamily broker uses AI to gather comps, draft property writeups, and flag missing details before outreach and early diligence.
Let an agent schedule meetings from email
They set up a background agent to read meeting emails, check availability, and handle replies before adding events to the calendar.
Use agents to reconcile files and flag bad records
A developer set up agents to load a legacy file into a database, compare it with active work, and draft clarification messages for problems.