Customer Support & SuccessPromptPlan
An Automation Misfired and Emailed Customers — Next Steps
Walks you through stopping a misfiring automation, preserving the run log, scoping who was affected, checking for a data exposure, and writing one honest message per affected group.
Opening lines · ~422 words in full
ROLE: You are a calm incident lead for small businesses whose automations went wrong in public: duplicate invoices, a test email to the whole list, the wrong name in a greeting. You stop the damage first, establish exactly who was affected, and then write one honest message. CONTEXT: What happened: [WHAT_HAPPENED]. Tool and workflow: [AUTOMATION_TOOL_AND_WORKFLOW]. When it started and when …
The rest of “An Automation Misfired and Emailed Customers — Next Steps” opens on a plan
You are reading the opening lines. The full prompt (~422 words) — to copy, download as a ready .md file, or finish in the Studio — comes with the Library plan: every prompt and skill, .md downloads, 80 tailoring runs a month.
- Built from
- Role
- Context
- Task
- Constraints
- Output format
- You fill in
- what happened
- automation tool and workflow
- timeline
- affected count
- what they received
- data exposed yes no
- country or state
- goodwill offer
Part of the No-Code Automation Pack — 8 items for no-code automation (zapier / make / n8n).
Written by the PromptCorrectly team© 2026 PromptCorrectly · All rights reserved
How to use it
- Read it, then replace anything in [BRACKETS] with your details — the more concrete the context, the sharper the answer. The Studio lists the blanks for you and can add your project's background.
- Copy it (or download the .md) and paste it into the AI you already use — it knows your work, so that is where the prompt does the most.
- Want it in your brand’s voice? Press “Tailor to my brand” and the Studio rewrites it for your business. To sharpen the answer itself, add self-critique prompting.
Techniques in this prompt
Assigns the model an expert persona so it adopts the right vocabulary, depth, and standards for the task.
Learn this techniqueForces explicit intermediate reasoning instead of jumping to a conclusion, which improves accuracy on hard tasks.
Learn this techniqueSets the rules and boundaries — tone, length, what to avoid — that keep the output on-target.
Learn this techniquePins the response to a defined structure so it drops straight into your workflow.
Learn this techniqueWorks with
Any chat AI — ChatGPT, Claude, Gemini, Copilot, Grok, Mistral or a local model. The structure does the work, so you are not tied to one vendor or one model version.
New to structured prompts? Start with how to prompt AI, the RCTCO prompt framework this prompt is built on, and role prompting examples.