Real AI agent use cases, with sources and setup prompts

Classify and dedupe repair requests with an n8n AI workflow

For a Stacked challenge, the author built an n8n flow that classifies repair requests with OpenAI, detects duplicates, groups related reports, raises urgency and flags unclear ones for a human. The intake form was built with Lovable.

Free tier1 dayIntermediateSource linked

Source

@omaya_gg on X · 2026-10-15

Written in our own words. Credit to the original author. Link checked 2026-10-16.

What they did

For a Stacked challenge, the author built an n8n flow that classifies repair requests with OpenAI, detects duplicates, groups related reports, raises urgency and flags unclear ones for a human. The intake form was built with Lovable.

Result (as claimed)

Working workflow demoed.

Tools they used

n8nOpenAIGoogle SheetsLovable

Cost: n8n: free plan, paid from €20/mo; Lovable: free plan, paid from $25/mo. Checked 2026-10-14.

Set it up

  1. Map the task

    Write the trigger, the inputs, the decisions and the output. Note which steps need a human yes.

  2. Connect the tools

    Set up n8n, OpenAI, Google Sheets, Lovable with the narrowest permissions that work. Use a test account or sandbox first.

  3. Build the workflow

    Create the steps in order. Add an approval step before anything sends, pays or deletes.

  4. Run it on real but low-stakes data

    Run a few times, read every output, and fix prompts or rules that misfire.

  5. Schedule and monitor

    Turn on the schedule or trigger, and add a daily summary or alert so you notice failures.

Copy the full setup prompt

Paste into your agent and it will walk you through the setup, asking before anything that sends, posts or spends.

You are helping me set up this AI use case end to end in Claude Code.

Goal: Classify and dedupe repair requests with an n8n AI workflow
What the original author did: For a Stacked challenge, the author built an n8n flow that classifies repair requests with OpenAI, detects duplicates, groups related reports, raises urgency and flags unclear ones for a human. The intake form was built with Lovable.
Reported result (as claimed by the author): Working workflow demoed.
Source: https://x.com/omaya_gg/status/2110722388216160363
Tools they used: n8n, OpenAI, Google Sheets, Lovable
Category: Automation & business

Please:
1. Ask me 3 short questions about my situation (accounts I have, budget, what I want the output to look like).
2. Propose a step-by-step plan using these tools or cheaper alternatives, with the time and cost of each step. Use official pricing pages; say "check pricing" if unsure.
3. Then do the setup with me one step at a time, waiting for my OK before anything that sends messages, posts publicly, spends money or deletes data.
4. Finish with a checklist to run it again next time.

The Daily 5

Get five new use cases tomorrow morning

Free. Real sources. Unsubscribe any time.

Related use cases