# Practice 1: Start with Intent & Own the Question

**Essence**

Know why you’re here before you type. Decide the job, the audience, the stakes, and what “good enough” looks like.

**What this combines**

* “Be Proactive → Own the Prompt”
* “Own the Question” (define outcome, audience, constraints, why it matters).
* “Slow the Ask” (pause before firing a reflex prompt).
* “Start with Intent” (one-sentence purpose + quality bar).

**Why it matters**\
If you’re fuzzy, the model fills in the blanks with generic internet defaults. That’s how you get “fine but useless” answers.

**Common traps**

* Vague asks: “Help with this” / “Write a report about X”.
* Dumping material without a clear job: “Here’s 5 pages of notes, summarize?”.

**Examples**

* *One-sentence intent*:
* “I’m trying to \[achieve X] for \[audience Y], it needs to be \[quality bar].”
* *Clarify before answer*:
* “Restate my goal in one sentence and propose what a ‘good enough’ outcome for this session is.”
* *Ask for sharpening*:
* “Ask me 3 questions to sharpen what I actually need before answering.”

***


---

# Agent Instructions: Querying This Documentation

If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://praxistutor.gitbook.io/llm/reframing-the-7-habits-for-reflective-llm-use/section-3-operators-toolkit-practical-examples/7-practices-in-the-operators-toolkit/practice-1-start-with-intent-and-own-the-question.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.