Social Pipeline Schema
The end-to-end social pipeline: ideas come in, posts are drafted and reviewed, imagery is generated, and finished posts move through to publishing — across the three channels — with the animal-persona cast on hand.
What it stores
The end-to-end social pipeline: ideas come in, posts are drafted and reviewed, imagery is generated, and finished posts move through to publishing — across the three channels — with the animal-persona cast on hand.
Owned by the Social agent. Lives in the Internal Tools database · public schema.
The tables
Friendly names first, with the real table name underneath. Key fields only.
Social Postssocial_posts
Every post the pipeline produces — copy, format, scheduling, imagery, and publishing state.
| Column | Type |
|---|---|
channelthe three channels | Choice |
post_formattext, image, carousel, poll… | Choice |
post_body | Text |
statusdrafted → designed → audited → approved → scheduled → published | Choice |
scheduled_at | Date & time |
mediaImage config and output | Structured |
Relationships
- one-to-many
social_post_images. Has one or more images
Content Ideassocial_content_ideas
Where other agents drop ideas; the social agent picks them up and drafts from them.
| Column | Type |
|---|---|
submitted_byWhich agent suggested it | Text |
topic | Text |
key_pointThe single takeaway | Text |
gz_quoteVerbatim, if it came from GZ | Text |
statusnew, in progress, drafted, dismissed, merged | Choice |
Relationships
- one-to-one
social_posts. Becomes a post once drafted
Animal Personassocial_animal_personas
The cast of animal characters used across social and animation imagery.
| Column | Type |
|---|---|
name | Text |
archetype | Text |
pain_points | List |
visual_description | Text |
Post Imagessocial_post_images
Links a post to its generated images and tracks each image's generation.
| Column | Type |
|---|---|
sort_orderOrder within a carousel | Number |
prompt | Text |
generation_statuspending, dispatched, completed… | Choice |
Relationships
- one-to-one
social_posts. Belongs to one post
Mission Briefsocial_briefs
The weekly GZ-voice LinkedIn newsletter store, kept separate from the main post pipeline.
| Column | Type |
|---|---|
title | Text |
body_mdThe article | Text |
pillarContent pillar 1–5 | Number |
statusdrafted, finalized, published, rejected | Choice |
You don't need all of this to start
Most of what these agents rely on has a simpler equivalent. Anywhere we use a database, you can usually start with a spreadsheet or a document — whatever you're comfortable with. Anywhere we built a custom MCP server, you can reach for a prebuilt AI connector instead of building your own.
We go further because it's where our experience pays off. Years of hands-on database work make a custom data layer feasible for us, and purpose-built MCP servers let us hand each agent a short, sharp instruction file and exactly the tools it needs — custom descriptions, only the endpoints we want, and the occasional extra gate — instead of a long manifesto or playbook. Nothing more, nothing less.
Ready to build technology that works for your mission?
Tell us where your organisation is and what's slowing your team down. We respond personally.