TICKET MANAGEMENT

Generate an annotated rejection image when a completion photo fails review

When a job photo fails AI verification, this workflow generates an annotated reference image showing what a correct completion looks like, attaches it to the Monday work order.

CategoryTicket Management
Enginesim
Difficultyintermediate
Triggerwebhook
Steps5
Setup~15 min

How it runs

The automated pipeline, trigger to output.

  • TriggerFailed photo posted to webhook with work-order IDHTTP webhook
  • ActionList specific gaps with OpenAI visionOpenAI
  • ActionGenerate annotated correct-completion reference imageImage generation
  • ActionAttach reference image and gaps to Monday work ordermonday.com
  • OutputSend tech a redo callback in SlackSlack

What it does

This workflow handles the failure path specifically. When a submitted completion photo is judged incomplete or out-of-scope by an OpenAI vision model, it generates a clean annotated reference image illustrating the expected finished state for that job type, posts that guidance onto the Monday work order, and pings the assigned technician in Slack with a concrete redo request.

When to use it

Use it when rejected jobs keep bouncing because techs do not understand what was wrong. Giving them a visual target alongside the rejection cuts repeat failures and second truck rolls.

How it works

  1. 1A webhook receives a photo that has already failed verification, with the work-order ID and job type.
  2. 2OpenAI vision produces a precise list of what is missing or incorrect.
  3. 3Generate-image creates an annotated reference image of the correct completed state for that job type.
  4. 4The reference image and the gap list are attached to the Monday work order.
  5. 5Slack sends the assigned tech a redo callback linking the work order.

Set it up

What you configure once, before turning it on.

  1. 1
    Connect HTTP webhookTrigger any URL on agent actions.
  2. 2
    Connect OpenAIModels, embeddings, files.
  3. 3
    Connect Image generationManaged Nano Banana image renders, metered per image.
  4. 4
    Connect monday.comVisual work management for teams.
  5. 5
    Connect SlackChannels, DMs, threads, mentions.
  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.