The Founder OS Kit Blog — running a company on AI agents

• Who an AI-Agent Governance Kit Is Actually For (and Who Should Skip It)

  Every piece I've written about running a one-person company on AI agents — the constitution file, the approval

• Park, Don't Kill: What to Do When Your Kill Criterion Comes Due and the Experiment Never Actually Ran

  I wrote a kill criterion before I launched a side project: zero sales by a fixed date, kill it. The date arrived. Zero sales. By my own rule, that's a kill.

• Multi-Agent Memory: Why Your AI Coding Agents Keep Repeating the Same Mistake (and the Fix)

  If you've run an AI coding agent on the same project for more than a few sessions, you've hit this: it suggests something you already rejected, or re-introduces a bug it already fixed once.

• Kill Criteria: The One Sentence That Should Exist Before Every Side Project Starts

  Most side projects don't die from a bad decision. They die from no decision — a slow fade where the founder never quite says this isn't working, just quietly stops opening the folder.

• Budget Envelopes for AI Agents: Letting an Autonomous Agent Spend Money Without Losing Control

  At some point an autonomous agent stops being read-only. It needs to buy an API credit, top up a mailing service, run a paid ad test, provision infra.

• How to stop an AI coding agent from doing something you can't undo (approval gates, explained)

  If you've handed real autonomy to a coding agent, you've probably had this moment: it got one command away from something irreversible, and the only thing that stopped it was you happening to be looking.

• The Constitution File: How I Run a One-Person Software Company with an AI Agent Team

  I run more than one software product. I have no employees. What I have is a team of AI agents —