CONTENT CREATION
Agent-driven art direction with iterative Replicate retries
An agent reads brand guidelines from Figma, generates a hero image per product, critiques its own output against the brand.
How it runs
The automated pipeline, trigger to output.
- TriggerSubmit a batch of products to art-direct
- ActionRead brand reference and tokens from FigmaFigma
- ActionDraft prompt and render candidate with ReplicateReplicate
- LogicCritique vs brand; revise prompt and re-render until pass or retry cap
- OutputSave winning hero image and critique notes to DropboxDropbox
What it does
Replaces a fixed pipeline with an art-director agent that actually iterates. For each product it studies the Figma brand reference, drafts a prompt, renders with Replicate, critiques the result against the guidelines, and revises the prompt and re-renders until the image clears the brand bar or hits a retry cap, then files the winner.
When to use it
Use it when a single-pass generator gives inconsistent results and you would otherwise loop in a human to nudge prompts. Best for higher-stakes hero shots where quality matters more than raw throughput and you want autonomous prompt tuning rather than a hard fail.
How it works
- 1A batch of products to art-direct is submitted to start the run.
- 2The agent reads the brand reference and tokens from Figma.
- 3It drafts a prompt and renders a candidate with Replicate.
- 4It critiques the candidate against the brand; if it falls short it adjusts the prompt and re-renders, up to the retry limit.
- 5Once an image passes, or the cap is reached with the best attempt, the agent records its verdict and reasoning.
- 6The winning hero image and its critique notes are saved to Dropbox.
Set it up
What you configure once, before turning it on.
- 1Connect FigmaFiles, frames, comments, assets.
- 2Connect ReplicateImage, video, and model inference.
- 3Connect DropboxFiles and folders.
- 4Set each agent's modelWe leave models unset so you pick the tier — fast + cheap, or top-quality.
- 5Tune it to your dataEdit the prompts, filters, and field mappings so it matches how your team works.
- 6Test, then turn it onRun once against a sample, confirm the output, then enable the trigger.
More Content Creation workflows
Build a Dropbox B-roll library from exported blog drafts
Triggers when a new blog draft file lands in a Dropbox folder, generates a Replicate B-roll clip for each paragraph.
Generate B-roll clips when a blog post is marked Ready in Notion
Watches a Notion blog database for posts flipped to 'Ready', splits the body into paragraphs, and generates a short B-roll video clip for each paragraph with Replicate.
On-demand: turn a blog URL into narrated B-roll clips
Accepts a blog URL via webhook, scrapes the article, generates a B-roll clip per paragraph with Replicate and a voiceover with ElevenLabs.
On-Demand Screenshot Freshness Report from a Slack Command
A writer requests a freshness check in Slack for a specific docs page; the workflow inspects every screenshot on that page, scores each by age and version gap.
Sync a Figma master frame into localized hero renders
Pulls the current master hero frame and its text layers from Figma, generates a localized image variant for each locale defined in Airtable.
Research-driven localized hero banners tuned per market
An agent researches cultural and seasonal cues for each target market, adapts the master hero concept to fit local context, generates a tailored image per locale.
Run it inside a business
This workflow drops into a full company template. Import the org, and this is one of the playbooks its agents run.
Run this workflow in your colony.
14-day trial. No DevOps. No Sales call. Provisioned in under a minute.