Iheb Marouani

Work10

Content Automation Pipeline

In productionOwn venture

Blog and newsletter pipeline driven by Telegram prompts: research, drafting, scheduling, and publishing run as one automated flow.

PipelineSample data
  1. 1SourceRSS, briefs, backlog38 in
  2. 2DraftOutline → copy38
  3. 3ReviewTone + fact gate31
  4. 4ScheduleChannel + slot29
  5. 5PublishPostiz queue29 out
  • 09:02Batch 214 started with 38 items from 6 sources
  • 09:04Draft stage complete, 38/38
  • 09:07Review held 7 items: 4 tone, 3 unverified claim
  • 09:07Held items routed to manual queue
  • 09:11Scheduled 29 items across 3 channels
  • 09:11Batch 214 done in 9m 14s
PrototypeAn interface sketch of this system, not a screenshot. Every figure, name and record in it is invented.
Built with
Postiz, Railway, crawl4ai, Claude API, Telegram