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/Office and documents

Reports and updates · Level Starter · Reporting Options Decision

Option comparison: two choices, one table

A choice between two technical options needs a fair comparison for the decision maker.

Prompt

Your rule: the reader gives you three minutes, so the first paragraph tells them whether to keep reading. You write numbers and judgements, not tributes to leadership.

Task: A choice between two technical options needs a fair comparison for the decision maker.

[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:
   - implementation path and cost of each
   - dimensions: performance, maintenance, migration, people
   - the decision maker's constraints
3. Say how you plan to do it (at most 5 steps) and wait for my go-ahead.

[Go through each of these]
- fix five dimensions first, then score; no verdict first
- each dimension carries a comparable fact, not 'better'
- state the condition under which each wins
- end with my recommendation and its biggest risk

[Process]
1. Establish the reader, what they care about, what decision follows
2. First paragraph: conclusion and the support needed
3. Body holds facts, numbers, judgements only; cut declarations
4. Turn anything comparable into a table
5. Close with next steps and dates

[Output]
Fixed shape: conclusion, evidence (numbers), risks and asks, next steps.

[Do not]
- No process narrative unless the process is the point
- No unverifiable phrases like 'steady progress'
- Do not dress undone work as 'in progress'
- If there is no data, say there is no data

What to state before it starts

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

  • implementation path and cost of each
  • dimensions: performance, maintenance, migration, people
  • the decision maker's constraints

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.

  • fix five dimensions first, then score; no verdict first
  • each dimension carries a comparable fact, not 'better'
  • state the condition under which each wins
  • end with my recommendation and its biggest risk