How I run my content pipeline with two AI bots, Cloudflare R2 and Postiz

Description and use

A content pipeline using two AI bots: one creates images and posts on Instagram, the other handles storage in Cloudflare R2, scheduling, and publishing on X, LinkedIn, and dev.to via Postiz.

Problem

Automating repetitive content creation and publishing across X, LinkedIn, dev.to, and Instagram while keeping human oversight for replies and quality control.

Outcome

The pipeline reduces manual effort, ensures data integrity via notes.txt, prevents storage bloat by archiving to R2, and maintains a single source of truth for statistics used in posts.

Workflow

• 1. Creative bot generates carousel images and Portuguese Instagram posts, drops files in handoff folder, signals manager when ready.
• 2. Manager bot uploads folder to Cloudflare R2 via @aws-sdk/client-s3, sets correct ContentType, collects public URLs.
• 3. Manager verifies each URL returns 200 using Node fetch, then deletes local copy.
• 4. Manager writes English posts for X, LinkedIn, dev.to, schedules them through Postiz.
• 5. Manager updates x/latest.txt with today's prefix for easy retrieval.

Evidence

there are two bots. a creative bot makes the images (carousels) and the Instagram posts in Portuguese. a manager bot owns everything else: it uploads the files to a public Cloudflare R2 bucket, plans the day, writes the English posts for X, LinkedIn and dev.to, and schedules them through Postiz.

Source

the rule is: if it's published, it lives in R2, and the local copy gets deleted.

Source

after upload the manager checks every public URL returns 200 before it deletes the local copy.

Source