# What does it take to run a business on systems?

Mostly it takes counting: the hours that go to rebuilding context nobody needed rebuilt, and the workflows that repeat every week and break quietly when nobody is watching. Each post takes one question at a time, with the systems OCTYN builds and runs as the evidence.

17 posts
Page 2 of 2

## Posts

- [How to scope an AI project so it ships: write down what it will never do](https://octyn.co/blog/how-to-scope-an-ai-project-so-it-ships-write-down-what-it-will-never-do) (2026-09-29): To scope an AI project so it ships, tie it to one piece of work your team repeats every week, with your weekly hours on it, and then write down what the first version will never do. Feature lists grow with every meeting. The stated limits keep it small enough to finish and safe enough to leave running.
- [What should a founder automate first? Start with the catching up](https://octyn.co/blog/what-should-a-founder-automate-first) (2026-09-27): The first thing a founder should automate is the step where someone rebuilds context by hand before acting, reading back through WhatsApp and email to see where a client stands. Count it before building anything. Clients times touchpoints times minutes spent catching up gives a weekly figure, and that figure decides what gets built.
- [Build vs buy AI tools for operations: look for the side spreadsheet](https://octyn.co/blog/build-vs-buy-ai-tools-for-operations-look-for-the-side-spreadsheet) (2026-09-26): On build vs buy AI tools for operations, buy wherever your workflow looks like everyone else's and build only the narrow part that is specific to how you work. The deciding cost arrives later, every day, in the workarounds a team invents when a bought product cannot hold one of its steps.
- [Should an AI agent send your emails? Ours did, once](https://octyn.co/blog/should-an-ai-agent-send-your-emails) (2026-09-25): No, an AI agent should not be the part that actually sends your emails. Let the model draft and sort, then pass each message to a small, boring service that sends on a schedule and confirms every delivery. OCTYN learned this after a model driven sender built for a client reported a send that never happened.
- [How to stop rebuilding client context before every call](https://octyn.co/blog/how-to-stop-rebuilding-client-context-before-every-call) (2026-09-25): Stop rebuilding client context by giving each client one record that every channel writes into as things happen. WhatsApp threads, emails, call notes and CRM changes land in the same place, with dates and sources, so the history is already assembled when someone opens it. The coordinator reads one page and starts from the last promise made.

## Topics

- [Build or buy](https://octyn.co/blog/topic/custom-ai-systems): 4
- [Client context](https://octyn.co/blog/topic/client-context): 5
- [Automation that holds up](https://octyn.co/blog/topic/reliable-automation): 2
- [Founder operations](https://octyn.co/blog/topic/founder-operations): 3
- [Growth systems](https://octyn.co/blog/topic/growth-systems): 1
- [Operations systems](https://octyn.co/blog/topic/operations-systems): 1
- [Product systems](https://octyn.co/blog/topic/product-systems): 1

Canonical: https://octyn.co/blog/page/2