CONTENT CREATION

Auto-annotate raw screenshots with Figma callout overlays

Watches a Drive folder for raw product screenshots, generates numbered callout arrows and labels on a Figma template, and exports finished annotated images to R2 for the docs team.

CategoryContent Creation
Enginesim
Difficultyintermediate
Triggerevent
Steps5
Setup~15 min

How it runs

The automated pipeline, trigger to output.

  • TriggerNew raw screenshot in watched Drive folderGoogle DriveGoogle Drive
  • ActionRead sidecar annotations JSONGoogle DriveGoogle Drive
  • ActionPlace image and instantiate callout markers in Figma frameFigmaFigma
  • ActionExport composed frame as PNGFigmaFigma
  • OutputUpload annotated PNG to R2 and comment the URL on DriveCloudflareCloudflare R2

What it does

Turns bare product screenshots into polished, annotated tutorial images. When a designer or PM drops a raw capture into a watched Google Drive folder, this workflow places it onto a Figma annotation template, draws numbered callout markers and label text at coordinates you specify in the filename or a sidecar JSON, then exports a flattened PNG to R2 with a stable public URL.

When to use it

Use it when your help center or onboarding flow needs consistent, branded screenshot annotations and you don't want every contributor hand-placing arrows in Figma. It enforces one callout style across every image.

How it works

  1. 1A new file in the watched Drive folder fires the trigger.
  2. 2The flow reads an accompanying `.annotations.json` describing callout positions and label text.
  3. 3It uploads the raw image into a Figma annotation frame and instantiates numbered marker components at each coordinate.
  4. 4Figma exports the composed frame as a PNG.
  5. 5The finished image is written to R2 under a predictable docs path and the URL is posted back as a Drive comment.

Set it up

What you configure once, before turning it on.

  1. 1
    Connect Google DriveDocs, sheets, slides, files.
  2. 2
    Connect FigmaFiles, frames, comments, assets.
  3. 3
    Connect Cloudflare R2Object storage, S3-compatible.
  4. 4
    Set each agent's modelWe leave models unset so you pick the tier — fast + cheap, or top-quality.
  5. 5
    Tune it to your dataEdit the prompts, filters, and field mappings so it matches how your team works.
  6. 6
    Test, then turn it onRun once against a sample, confirm the output, then enable the trigger.

Run this workflow in your colony.

14-day trial. No DevOps. No Sales call. Provisioned in under a minute.