# Practice 3: Feed Real Context & Calibrate the Model

**Essence**

Don’t ask a stranger for bespoke advice. *Show* the model your world: who you are, who it’s for, what’s already on the table.

**What this combines**

* “Feed Real Context” (real constraints, prior work, examples).
* “Calibrate the AI” (role, stakes, bar, style preferences).
* “State the Problem Clearly” (turn mess into a precise ask).
* “Begin with the End in Mind → Frame the Output’s Role”.

**Why it matters**\
Without context, you get generic “internet average” answers. With context, you get tailored scaffolding.

**Common traps**

* Asking “write an email” without saying to whom, from whom, or why.
* Forgetting to share good/bad examples you already have.
* Assuming the model “knows your job”.

**Examples**

* “Here’s the real context in bullets: \[audience, goal, constraints]. Summarize in 3–5 bullets, then ask 3 clarifying questions before drafting anything.”
* “For this chat, act like a \[role] serving \[audience] at \[stakes level]; restate what you think your role is before responding.”
* “Here’s one example I like and one I don’t. Extract what you think I value and use that as a style guide.”

***


---

# 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-3-feed-real-context-and-calibrate-the-model.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.