Getting started
Create your product, connect your website and repo, and let the onboarding loop orient itself.
1. Create a product
Everything in 1mn is scoped to a product — one SaaS you’re running. From the top bar choose + New product, give it a name and your website URL.
When you add a website, an onboarding run kicks off automatically: it reads your site and drafts a business profile, a brand voice guide, and a first pass at your competitors — so the agent starts with context instead of a blank page.
2. Talk to the dispatcher
The left sidebar is your conversation with the primary agent. It doesn’t do the heavy lifting itself — it routes. Ask in plain language (“audit my SEO”, “draft a launch ad”, “why are users hitting this error”) and it spawns the right background task.
3. Connect your tools
Most loops get better with a connection or two. From Integrations:
- GitHub — required for any loop that writes code or docs (coding tasks, content, the docs loop).
- Analytics (PostHog) and Revenue (Polar) — power the business digest and demand-generation.
- Search Console — powers SEO ranking and audits.
- Telegram — get pinged and reply to the agent from your phone.
See Integrations for the full list and setup steps.
4. Review and approve
Loops surface their work as tickets and drafts. Low-risk, reversible work applies on its own; anything irreversible — a production deploy, money out, a live ad — pauses for your approval. You review on the Tasks board, or right in chat.
5. Let it run
Turn on the loops you want from Cadence. From then on they wake on their own schedule, decide whether there’s anything worth doing, and hand back to you only when they need a decision.
Point Cast at staging
Cast personas drive a real browser through your app. Aim them at a staging URL with a throwaway account, not production.
What is 1mn?
1mn runs a solo founder’s SaaS as autonomous AI loops — growth, product, and support that act, verify their own work, and hand back only at the edges.
How loops work
The shape every 1mn feature fits — trigger, discover, decide, act, verify, gate, persist, hand off — and the three properties that decide how autonomous it can be.