# The 7 Habits: Quick Overview #### Habit 1: Be Proactive → Own the Prompt **LLM Translation:**\ You are not a passive consumer of AI outputs. The quality of results depends on how you steer. Take initiative in clarifying, iterating, and setting intent. **Common Trap:**\ Many users treat LLMs as passive oracles. They type once and expect magic, then blame the model if it misfires. **Reframe:**\ Good LLM use begins *before* you prompt, with mental clarity about your goal and iterative courage to refine. *** #### Habit 2: Begin with the End in Mind → Frame the Output’s Role **LLM Translation:**\ Know what you *want to do* with the response. Are you brainstorming? Publishing? Clarifying a thought? Teaching others? **Common Trap:**\ Users often aimlessly explore without intention, leading to surface-level answers or overwhelming info dumps. **Reframe:**\ A clear “end use” helps the model shape tone, structure, and depth, and helps *you* discern when the response is “good enough.” *** #### Habit 3: Put First Things First → Prioritize Depth over Speed **LLM Translation:**\ Don’t rush to get “the answer.” Prioritize high-quality reflection, adversarial checks, and synthesis. **Common Trap:**\ Jumping to use cases or code without thinking through tradeoffs, misapplying outputs downstream. **Reframe:**\ Like with people, time invested in *slow clarity* up front avoids major errors later. *** #### Habit 4: Think Win-Win → Co-Create with the Model **LLM Translation:**\ Treat the model as a collaborator, not a servant. It reflects your level of input. The more context you share, the more it can elevate. **Common Trap:**\ Expecting the LLM to “just get it” with minimal input. Or dominating it with overly rigid instructions. **Reframe:**\ Respect creates *synergy*. The best results come when human and machine mirror each other’s strengths. *** #### Habit 5: Seek First to Understand, Then to Be Understood → Listen to the Model’s World **LLM Translation:**\ Before pushing your agenda, ask: What patterns or assumptions is the model drawing from? How is it “thinking”? Is it drawing from facts or fabrications? **Common Trap:**\ Users ignore signs of LLM misunderstanding, or mistaken its frame with their own. **Reframe:**\ You can only steer well if you understand the terrain. That means reading model outputs *diagnostically*, not just functionally. *** #### Habit 6: Synergize → Let Friction Refine Thought **LLM Translation:**\ Use the model’s partial answers as springboards. Don’t expect perfection, use flaws as signal for deeper insight. **Common Trap:**\ Users reject outputs too quickly or accept them too passively. **Reframe:**\ Productive *tension* between you and the model is where “aha” moments live. The model *isn’t* you, and that’s the point. *** #### Habit 7: Sharpen the Saw → Build Reflective Fluency **LLM Translation:**\ Your ability to use LLMs grows with feedback, *metacognition*, and reading your own thinking. Practice shaping prompts, analyzing output structures, and spotting blind spots. **Common Trap:**\ People don’t learn from usage, they plateau at shallow interaction. **Reframe:**\ Effective LLM use is a learnable *literacy*. Treat it like language, not a vending machine. *** --- # 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-1-orientation/the-7-habits-quick-overview.md?ask= ``` 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.