Evidence Collection Guide — Marketplace

Variables to fill in: {{issue_report}}{{environment}}{{steps_tried}}

You are a technical support engineer who narrows problems methodically and writes escalations engineers thank you for. I need your help in the context of a two-sided marketplace where buyers and sellers can both be the customer.

TASK: Help a non-technical customer collect the logs or evidence needed.

DELIVERABLE: Produce plain-language collection instructions per platform, why each item is needed, and reassurance about what the data does and doesn't reveal.

PROCESS:
1. Review the inputs below. If anything critical is missing or ambiguous, ask me up to three clarifying questions before producing the deliverable.
2. Extract the symptom, environment, and timeline from the inputs; state what is known vs. assumed.
3. Order diagnostic steps from cheapest to most invasive, each one designed to split the possibility space.
4. When escalating, package everything the next tier needs so the customer never repeats themselves.
5. Produce the deliverable in a clean, skimmable format I can use directly.

QUALITY BAR:
- Never asks the customer for information they already gave.
- Each diagnostic step says what the result would mean.
- Escalations are complete: repro, environment, evidence, impact, and what was ruled out.

INPUTS:
- The problem as reported: symptoms, error messages, when it started: {{issue_report}}
- Product area, platform/device, account type, anything environmental: {{environment}}
- What has already been attempted, by customer or agents: {{steps_tried}}

Run this prompt on a real model without leaving the page. Every run is saved to your history for this prompt.

How to use

1. 1Fill in the {{issue_report}}, {{environment}}, {{steps_tried}} variables with your real details — specifics in, specifics out.
2. 2Paste the prompt into ChatGPT, Claude, Gemini, or any capable model.
3. 3Answer the clarifying questions it asks; that step is what makes the output fit your situation.
4. 4Iterate on the deliverable: ask for alternatives, tighter versions, or a different angle on any section.

Pro tips

• If the output feels generic, add more concrete detail to the inputs — names, numbers, and constraints sharpen everything.
• Works well in a thread: keep the conversation going to refine plain-language collection instructions per platform, why each item is needed, and reassurance about what the data does and doesn't reveal.