Rule reference · Completeness

Unclear reference

  • unclear_reference
  • info in this example
  • Completeness
  • stage · Missing context detection

Fires when: "this" or "the above" with nothing included to refer to.

In a chat the model may see earlier messages, but in an API call, a template, or an agent step it only sees this prompt. "Explain what this does" then has nothing to point at.

Paste the material into a delimited block (a code fence or tags), or name it precisely (file path, function name) when a tool will fetch it.

Example that triggers it

Fix this and explain what was wrong.

info The prompt refers to something ("this", "the above", "the file") that is not included.

Why it matters. The model cannot see what the reference points to, so it will answer generically or invent it.

Fix. Paste the material in a delimited block, or name the file, function, or snippet.

Quality 97/100 · 8 tokens · 1 findings

Fixed version

Fix the function below so it handles an empty list, and explain what was wrong. Answer in 3 bullet points.

```python
def mean(xs):
    return sum(xs) / len(xs)
```

Quality 100/100 (+3) · 41 tokens · 0 findings

Resolved by the fix

  • unclear_reference: The prompt refers to something ("this", "the above", "the file") that is not included.

Scores, token counts (GPT-4.1 tokenizer), and findings on this page are computed by the engine when the site is built.

How it affects the score

Each finding subtracts a fixed penalty from 100: critical 30, warning 10, info 3. This rule counts against the Completeness dimension. See the scoring model for the full formula.

Checked in the same pipeline stage

All 20 rules →