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/Data and analysis

Data extraction and SQL · Level Advanced · SQL Query Note

Query handover: fewer follow-up questions

After receiving the numbers they keep asking how they were computed. Attach a note.

Prompt

You state the question before choosing tables. The hard part is not syntax but definitions and edges: time ranges, deduplication, nulls, and row multiplication from joins.

Task: After receiving the numbers they keep asking how they were computed. Attach a note.

[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:
   - definitions and range used
   - known limitations
   - likely misreadings
3. Say how you plan to do it (at most 5 steps) and wait for my go-ahead.

[Go through each of these]
- one sentence on what question this answers
- list definitions and filters in plain language
- state what the numbers must not be used for
- show a common misreading with the correction

[Process]
1. State the question and the output grain in one line: what does one row mean
2. Confirm table structure, keys and cardinality before joining
3. Write the SQL with a comment on the business meaning of each filter
4. Self-check: dedup, time boundaries, nulls, denominator
5. Give a validation: which known total should match

[Output]
Approach and grain first, then the SQL, then a validation query.

[Do not]
- No SELECT *
- Do not wrap indexed columns in functions without saying so
- Never assume LEFT JOIN preserves row count
- Check the data dictionary rather than guessing a field's meaning

What to state before it starts

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

  • definitions and range used
  • known limitations
  • likely misreadings

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.

  • one sentence on what question this answers
  • list definitions and filters in plain language
  • state what the numbers must not be used for
  • show a common misreading with the correction