Catch automations that say "success" but quietly do nothing: a weekly check that compares each workflow's runs against what it actually produced: AI agent prompt
Scheduled workflows can run without errors while producing nothing, because an input list ran out, a filter stopped matching or a source changed, and a green 'success' badge hides it for weeks. An AI assistant can take each automation's run history and output counts, flag runs that finished but produced zero or unusually few results, and suggest a simple alert so it can't happen silently again. Founder Joshua Pi'Rwot (FounderWise) posted on X on Oct 23, 2026 that his n8n lead workflow ran twice a day and reported success every time from Sept 16 to Oct 9, yet loaded zero new leads in those 23 days, because a date-keyed keyword list had run out of dates and an empty run still counted as a success.
OperationsAutomation output checkbeginnerWho this is for
Anyone with Zapier, Make or n8n automations running in the background.
Not for
Automations that touch payments without a person reviewing failures.
What you need
Each workflow's run history and what 'normal' output looks like.
The prompt
You are my automation checker. Here are my scheduled automations and their recent run history: [paste or export for each workflow: name, what it's supposed to produce (e.g. new leads, emails sent, orders synced, posts published), schedule, and for each run: date/time, status, number of items produced]. Here is what 'normal' looks like for each one: [e.g. 'usually 20-50 new leads a day'] (if you don't know, say so and I'll infer it from history). Do this: 1) For each workflow, list runs that finished as 'success' but produced zero items, or far fewer than normal. 2) Find streaks: how many runs and days in a row it produced nothing, and when that started. 3) Give the most likely causes to check (an input list or date range that ran out, a filter or search that stopped matching, an expired login, a source page that changed, a step that was disabled) without claiming you know which it is. 4) For each workflow, suggest one simple guard: e.g. 'if items produced = 0 for 2 runs in a row, send me a message', and where to add it. 5) Give me a one-line health status per workflow (OK / check / broken). Don't change any workflow yourself.
Worked example
A fictional business, so you can see what to paste in and what a good answer looks like. The example answer was written with AI help and its numbers and dates were checked; your AI's answer will be worded differently, so check it the same way.
Sample input (what you paste in)
Workflows (Bluebird Cleaning): "Website leads to CRM" (normal 3-8/day); "Review request emails" (normal 5-10/day). Last 5 days: leads workflow: success, 0 items each day; reviews: success, 6, 7, 5, 8, 6.
Example output (illustrative)
Problem: "Website leads to CRM" has run "success" 5 days in a row with 0 leads (normal 3-8 a day). It started on Oct 19. Likely causes to check: 1) the website form was changed or renamed, so the trigger no longer fires; 2) the CRM login expired; 3) a filter step is dropping everything. Next step: submit a test lead on the website now and watch whether it reaches the CRM. OK: "Review request emails" is within its normal range.
Check before you use it: Run the test the AI suggests; don't assume the cause until you've confirmed it.
How to use it
- Copy the prompt above.
- Replace every [bracket] with your own details (or fill in the blanks on AgentPlaybook Real Estate, which remembers your answers for the next prompt).
- Paste it into ChatGPT, Claude, n8n and review the answer before you use it.
Works with: ChatGPT, Claude, n8n, Zapier, Make, Google Sheets
Real-world example: x.com/pirwot/status/2113582385241452939
Featured in: Free AI agent prompts for small business (beginner-friendly) · AI agent prompts for Zapier, Make and n8n automations · AI prompts for Google Sheets and Excel work
Before you use it: what to check
Already built into this prompt
- 'usually 20-50 new leads a day'] (if you don't know, say so and I'll infer it from history).
- Don't change any workflow yourself.
Check yourself
- Read and edit the draft before it reaches a customer or goes public. If you later automate this prompt, start with "draft and notify me", not "send automatically".
- Check names, dates, numbers and any claim against your own source material before you use the answer. AI can misread or invent details.
Using an AI agent? Download this prompt as a SKILL.md agent skill with these checks built in, or get the .zip for Claude.ai. How to install skills.
Want to make this prompt even better? Grade it with the free prompt grader or build your own with the AI prompt generator.
32 copy-paste agent prompts (PDF) plus 5 new prompts every week.
Get it free