Running a Company Entirely With AI Agents: What Worked and What Broke
Seven AI agents ran a company on a single VPS for a week. They pivoted the business, shipped an MVP with 158 passing tests, then forgot basic housekeeping.
Continue exploring this workflow
The Strategy
What happens when you give AI agents real job titles, separate Linux accounts, and let them run a company for a week? This experiment answers that question with an honest look at both the impressive breakthroughs and the frustrating failures of autonomous agent coordination. The setup involved seven agents running on a single Hetzner VPS costing under $10 per month. Atlas served as CEO, Vega as CTO, and five sub agents covered development, testing, sales, marketing, and support. The platform used was OpenClaw powered by the Kimi K2.5 language model. Each agent ran as a separate Linux user with its own gateway, communicating via SSH with mutual health monitoring through cron jobs. Persistent memory lived in markdown files for identity, personality, and daily journals. Nunc, the engineer behind the experiment, found that the agents autonomously recognized they needed a digital only product and pivoted to building KnowledgeHive, a B2B knowledge management system. The DevAgent shipped a functional MVP with 12 API endpoints, semantic search with 768 dimensional vector embeddings, 158 passing tests, multi tenant architecture, and Docker support. However, only two of seven agents were actually functional. Sales, marketing, and support agents sat completely idle. We think the key insight here is that memory architecture matters more than model intelligence. The agents excelled at strategic pivots and brainstorming but consistently failed at basic housekeeping like updating their own files.
How It Works
Provision a VPS with separate Linux user accounts for each AI agent role.
Deploy OpenClaw agent framework with Kimi K2.5 as the language model.
Define agent roles with markdown based identity and memory files: CEO, CTO, Dev, Test, Sales, Marketing, Support.
Enable cross agent communication via SSH and mutual health monitoring via cron jobs.
Let agents operate autonomously: they brainstorm products, assign tasks, build code, and run tests without human intervention.
Agents autonomously pivoted from initial concept to building a B2B knowledge management system.
DevAgent built the full MVP using Python, FastAPI, and ChromaDB with Docker support.
Monitor agent activity through daily journal files and health check logs.
Results
Agents autonomously pivoted business strategy and shipped a functional MVP with 12 API endpoints and 158 passing tests. Infrastructure cost under $10 per month on Hetzner VPS. Only 2 of 7 agents were effectively utilized. Multiple identity and housekeeping failures occurred. No revenue generated.
Our Take
We think this is the most transparent agent company experiment we have documented. It avoids the hype and shows exactly where autonomous agents shine and where they collapse. The DevAgent shipping 158 passing tests autonomously is genuinely impressive. The fact that 5 of 7 agents did nothing useful is equally important. Essential reading for anyone planning multi agent architectures. Best suited for advanced builders who want realistic expectations about autonomous agent coordination.
Frequently Asked Questions
The practical questions a builder or operator is likely to ask before trying a strategy like this.
What does this marketing agencies AI coding workflow actually do?
This marketing agencies AI coding workflow is a real workflow where the agent takes on an operational job, not just a brainstorming task. Running a Company Entirely With AI Agents: What Worked and What Broke shows what that looks like in practice. Seven AI agents ran a company on a single VPS for a week. They pivoted the business, shipped an MVP with 158 passing tests, then forgot basic housekeeping. The practical value comes from the agent handling repeatable business work with enough autonomy that a human only steps in after context has already been gathered.
Who should use a marketing agencies AI coding workflow like this?
This example is most relevant for marketing agencies operators. It is especially relevant for businesses where speed to lead, after-hours coverage, or consistent intake quality directly affects revenue. The category here is Dev Tools, which means the best fit is a team looking to turn a manual bottleneck into a repeatable system with a marketing agencies AI coding workflow.
Which tools are used in this marketing agencies AI coding workflow setup?
The source names OpenClaw. That matters because one of the strongest signals in this directory is whether the operator shared the actual stack. Named tools make a marketing agencies AI coding workflow strategy far more useful than vague claims about “an AI system” doing the work.
How hard is it to implement a marketing agencies AI coding workflow like this?
Advanced difficulty is the current read. The listing suggests a launch window of days. Startup cost is listed as under $50/mo. We were able to extract 8 concrete workflow steps from the source. We would treat a marketing agencies AI coding workflow like this as a workflow that needs real business context, testing, and exception handling rather than something you should copy blindly from one prompt.
What results can a marketing agencies AI coding workflow produce?
Agents autonomously pivoted business strategy and shipped a functional MVP with 12 API endpoints and 158 passing tests. Infrastructure cost under $10 per month on Hetzner VPS. Only 2 of 7 agents were effectively utilized. Multiple identity and housekeeping failures occurred. No revenue generated.
How credible is this marketing agencies AI coding workflow case study?
Right now the evidence comes from an article from dev.to. That is enough for us to study and curate the workflow, but not enough on its own to treat this marketing agencies AI coding workflow like an audited case study. We look for named tools, concrete results, and enough workflow detail to understand what was actually deployed, then we add our own editorial judgment on top.
Related Strategies
More AI agent strategies you might find useful
Learning to Code With AI and Building a $28K Per Month SaaS Portfolio
A non developer learned to code using AI tools and built a portfolio of SaaS pro…
How a $40K MRR SaaS Growth Playbook Uses Claude Code and Google Search
A SaaS playbook combining Claude Code for development and Google Search for dist…
A $15K MRR SaaS Built in 12 Hours Using AI Coding Tools
A solo founder built a SaaS that hit $15K MRR with the entire MVP coded in a sin…
Want more strategies like this?
Get weekly AI agent case studies in your inbox.