Ceyuan · Content-Ops Console
Getting a business recommended by AI search. Ceyuan pulls the whole content pipeline into one console an operator can run — dossier → generate → QA → publish, every step logged and reconciled.
Why I built it
As more people ask AI to find things, being recommended by AI becomes the new front door for customer acquisition.
Making that work means publishing steadily across many platforms. A handful of clients, you can do by hand. A few dozen, it collapses. A system — automated operations — is the only way that scales.
One console, the whole chain
Ceyuan is an operations console: build a client dossier, generate from it, QA by hand, publish to each platform. One screen shows where every client and every piece of content stands.
The hard part isn’t automation — it’s publishing itself
Publishing to these platforms is adversarial: some return a link instantly, some sit in human review, some block automation outright. The real risk isn’t failing to publish — it’s looking published when you’re not.
Ceyuan tracks each platform’s real state — published (with a real link), in review, needs a human — and re-checks after posting: no real link, not counted as done.
When a human steps in, it’s still on the record
Where automation can’t finish, a person does — and that step is logged too: who, when, which URL, note. No black-box step anywhere in the system.
Only the client’s own facts
Content is generated only from real material in the client’s dossier — real product info and images — with prompts that forbid inventing anything beyond it. Thin material makes hollow copy, and QA catches it. I keep tuning the prompts so the writing genuinely answers what users are searching for.
Where it stands
Live and operating; the first monthly-paying clients are onboarding. An internal system for my own business — no billing, no self-signup. It’s a product I run myself — always glad to walk through the full build and the engineering tradeoffs.