CONTENT CREATION

Linear cycle completion to Replicate hero art with Slack approval

On Linear cycle completion, this drafts a release-note summary, renders multiple hero-art variants via Replicate.

CategoryContent Creation
Enginesim
Difficultyintermediate
Triggerevent
Steps6
Setup~15 min

How it runs

The automated pipeline, trigger to output.

  • TriggerLinear cycle completed eventLinearLinear
  • ActionCompile completed issues into release summary + art briefOpenAI
  • ActionRender three hero-art variants on ReplicateReplicateReplicate
  • LogicPre-screen variants for palette and aspect-ratio compliance
  • ActionPost variants to Slack for one-click approvalSlack
  • OutputSave approved hero art to R2 storageCloudflareCloudflare R2

What it does

When a Linear cycle closes, it compiles the shipped issues into a release-note draft, generates several hero-art options through a Replicate image model, and sends them to a Slack channel where a reviewer picks the on-brand winner.

When to use it

Use it when art direction needs a human eye but you still want the heavy lifting automated. Good for teams that run on Linear cycles and want changelog art reviewed in Slack before anything ships.

How it works

  1. 1A Linear `Cycle completed` event triggers the run with the cycle's completed issues.
  2. 2An action turns the completed issues into a concise release summary and an art brief.
  3. 3Replicate renders three hero-art variants from the brief.
  4. 4A logic step pre-screens each variant for palette and aspect-ratio compliance, dropping any that fail.
  5. 5The passing variants are posted to a Slack channel as an interactive approval message.
  6. 6The reviewer's chosen image and the release summary are saved to cloud storage and announced back in the thread.

Set it up

What you configure once, before turning it on.

  1. 1
    Connect LinearIssues, projects, cycles, triage.
  2. 2
    Connect ReplicateImage, video, and model inference.
  3. 3
    Connect SlackChannels, DMs, threads, mentions.
  4. 4
    Connect Cloudflare R2Object storage, S3-compatible.
  5. 5
    Connect OpenAIModels, embeddings, files.
  6. 6
    Set each agent's modelWe leave models unset so you pick the tier — fast + cheap, or top-quality.
  7. 7
    Tune it to your dataEdit the prompts, filters, and field mappings so it matches how your team works.
  8. 8
    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.