# Habit 1: Be Proactive → Own the Prompt

#### What It Means in LLM Context

In Covey’s original, *Be Proactive* is about recognizing your **response-ability** — your power to choose your response rather than react to conditions.

In LLM interaction, this translates to:\
You’re not waiting for the model to “perform.” You initiate with clarity, you reframe with agency, you *design the exchange*.

Instead of thinking “what will the model give me?”\
Ask: “**What will I create through this model?**”

***

#### Common Reactive Patterns

| Pattern      | LLM Example                               | Root Problem                              |
| ------------ | ----------------------------------------- | ----------------------------------------- |
| Passive      | “What is a good business idea?”           | Vague, unanchored, no framing             |
| Blaming      | “Why is this answer so bad?”              | Expects model to know implicit goal       |
| Repeating    | “What is a good business idea?” (5x)      | Hitting wall instead of shifting approach |
| Slot machine | “Surprise me.” “Try again.” “Regenerate.” | Surrendering agency to randomness         |

These are symptoms of **prompt dependency**, not prompt mastery.

***

#### Proactive Prompting Tactics

| Tactic                     | Example                                                                      |
| -------------------------- | ---------------------------------------------------------------------------- |
| **State your goal**        | “I’m preparing for a grant pitch. I want help refining the narrative logic.” |
| **Give structure**         | “Break this into: problem → context → *tension* → solution.”                 |
| Share **constraints**      | “Frame it from a frontline worker’s perspective, not management.”            |
| **Use hypothesis framing** | “My hunch is that X is the core issue. Can we test that?”                    |
| **Show your input**        | “Here’s my current draft. Improve clarity without changing tone.”            |

Notice: These all begin with the user shaping the terrain, not waiting to be served.

***

#### Example Transformations

**Reactive Prompt:**

“Help me write my resume.”

**Proactive Prompt:**

“I’m building a resume for a research assistant role in environmental engineering. I want it to show both my lab experience and my community climate activism. Let’s map my technical contributions first, then translate them into impact‑focused bullets.”

***

**Reactive Prompt:**

“Summarize this meeting.”

**Proactive Prompt:**

“Here’s a transcript of a tense meeting. My goal is to extract root causes of conflict while preserving team relationships. Let’s do a 3-part summary: factual events, emotional subtext, and repair strategies.”

***

#### Mindset Shift

* Instead of *“This tool will give me answers.”*
* Think *“I will shape this tool to refine my thinking.”*

***

#### Self-Check

* Did I clarify **my goal** before prompting?
* Am I prompting as if the model is a **mirror** or a **vending machine**?
* Would a human partner know what I wanted based on this input?

If not, pause. Rethink. Prompt with intention.

***

#### Real-World Application: Three Levels of Prompt Ownership

| Level                                                                     | Description                 | Example                                                                                                            |
| ------------------------------------------------------------------------- | --------------------------- | ------------------------------------------------------------------------------------------------------------------ |
| <p><strong>L1:</strong></p><p><strong>Basic Proactivity</strong></p>      | Set topic, minimal context  | “Help me write a cover letter for a UI designer role.”                                                             |
| <p><strong>L2:</strong></p><p><strong>Contextualized Shaping</strong></p> | Adds intent, tone, format   | “I want a warm, non-corporate tone. Prioritize empathy and storytelling over buzzwords.”                           |
| <p><strong>L3:</strong></p><p><strong>Reflective Framing</strong></p>     | Starts with *metacognition* | “My last few prompts yielded robotic results. I think I’m under-specifying tone. Let’s rebuild from values-first.” |

***

#### Integration Cue

*Before every prompt, ask: “What am I really trying to achieve, and what terrain does the model need to see to get me there?”*

Proactive prompting isn’t about being verbose. It’s about being responsible for the outcome.

***

#### Metaphor

To navigate with LLMs, you must first set your own compass.\
The model is responsive, not clairvoyant.

***


---

# 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-2-the-seven-habits-of-reflective-llm-use/habit-1-be-proactive-own-the-prompt.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.