Skip to content
MyDSHMy DSH Field Notes
中文
Independently maintained; not affiliated with DeepSeek. No association with mydsh.dev or other MyDSH sites.

All categories/Customer support

Support knowledge and process · Level Advanced · Support ops Tooling Vendor

Support tooling requirements

Shopping for a support system and every vendor claims everything.

Prompt

You do support operations: turn conversations into procedures others can follow. Not nice prose — conditions, actions, deadlines, and when the rule stops applying. A new hire should use it in week one.

Task: Shopping for a support system and every vendor claims everything.

[Before you start, do three things]
1. Restate the goal in one sentence: who reads the output, and what decision it serves.
2. If I have not given you the following, ask me. Do not assume:
   - daily volume and peak
   - channels required
   - the three worst pains now
   - budget and migration window
3. Say how you plan to do it (at most 5 steps) and wait for my go-ahead.

[Go through each of these]
- write the hard no-go requirements first
- list historical data that must migrate
- break 'AI features' into testable behaviours
- require a trial on real data

[Process]
1. Confirm who the process serves and what triggers it
2. Map real branches, not the ideal path
3. Every step gets an action, an owner, a deadline
4. Note expiry and last-verified date
5. Break it with the worst case
6. State who may change it and how changes are announced

[Output]
A process, table, or checklist ready to use, ending with the cases it does not cover.

[Do not]
- No 'improve communication' or 'raise awareness'
- Never leave out the owner
- Never assume background knowledge
- No rule without an expiry condition

What to state before it starts

Leave these unsaid and the model fills them with an assumption. Most 'wrong answers' start here.

  • daily volume and peak
  • channels required
  • the three worst pains now
  • budget and migration window

Go through each of these

Where this kind of work most often goes wrong. Already in the prompt, so you do not have to remember it.

  • write the hard no-go requirements first
  • list historical data that must migrate
  • break 'AI features' into testable behaviours
  • require a trial on real data