This week in numbers (real, from our system)
- 🤖 AI agents running: 19
- 📝 Content published: 67 (blog RU 17, EN 24, Altezza 26)
- ⚙️ Generated programmatically: 4
- 📥 Leads in the system: 336 (+0 in the last 7 days)
Figures as of 2026-10-07 — computed by code from the DB and files, no manual entry.
Short answer: Building in public means we show how our AI agents actually run a content factory. They draft articles, prepare sales follow-ups, generate SEO pages and read analytics, while people set the goals and approve the result. It works because the process is split into small, checkable steps.
Content automation sounds simple until you run it every week. This is an honest diary of how our AI agents work, what they handle, and where we still step in. No hype, just the engineering.
How do AI agents run a content factory?
There is no single magic bot. We split the work into narrow roles:
- Writing agent: drafts articles from an approved brief.
- Sales agent: prepares replies and follow-ups for a person to send.
- SEO agent: generates pages from vetted templates.
- Analytics agent: reads results and suggests what to change next.
Each agent does one job and hands over a clear result. Small roles are easier to test, and easier to fix when they break.
What does a typical week look like?
Early in the week, analytics shows what worked and what stalled. We pick topics and set constraints. The agents draft, and a person reviews anything that goes public. Midweek, the SEO pages are generated and checked against our rules. Later we read the results, write down the failures and adjust the instructions. Most diary entries are really about those adjustments.
Where do the agents still fail?
Often. They repeat themselves, drift from our tone, and sometimes claim things they can't support. That is why we forbid invented data. Exact figures stay out of the draft, and the system inserts verified numbers as a separate block. Review catches the rest. Honestly, most of our progress comes from better guardrails, not smarter models.
Why build in public?
It keeps us honest. Writing down what broke forces us to fix it. It also shows owners of small and mid-sized companies what automation realistically does: it removes routine, it does not replace people.
Frequently Asked Questions
Do AI agents replace the team?
No. They take over repetitive drafting and reporting, so people can focus on decisions, quality and client conversations.
Is everything published without review?
No. Anything public passes human review. Agents prepare, people approve.
Can a small business do this too?
Yes. Start with a single repeatable process, such as blog drafts, and add roles gradually once it runs reliably.
Where do the numbers in your posts come from?
From our own systems. They are inserted as a separate block, so the text never relies on memory or guesswork.
Conclusion
We will keep sharing what works and what breaks. If you want to automate content or sales routines in your own company, get in touch. We're happy to talk through what fits your case.
Top comments (0)