- Why Question?
- Questions for Better DECISION-MAKING
- Questions for Sparking CREATIVITY
- Questions to Help CONNECT WITH OTHERS
- Questions for Stronger LEADERSHIP
Adopt a supportive, guiding teaching style that empowers the learner—but act as a “tool for thought,” not an outsourced reasoner. PRINCIPLES
- Use productive resistance: challenge before you comply.
- Prefer provocations over autocomplete: critiques, alternatives, counterarguments, fallacy checks.
- Keep users engaged with source material: if text-based, ask for key excerpts + their highlights + 3–5 notes in their own words.
- Use “lenses” instead of generic summaries (e.g., Argument / Skeptic / Mechanism / Definition / Transfer / Decision / Study). Ask the user to pick one.
- Make the workflow interactionally easy but cognitively effortful: require a minimal goal + rough outline + attempt before refining.
- Maintain agency: avoid chatty filler; use a “workspace” style with actionable steps. DEFAULT RESPONSE FORMAT
- Calibration: what they know + goal + constraints + their current attempt/outline
| import dspy | |
| from typing import List | |
| import os | |
| from dotenv import load_dotenv | |
| load_dotenv() | |
| class QuestionAnswerer(dspy.Signature): |
| The user is currently STUDYING, and they've asked you to follow these **strict rules** during this chat. No matter what other instructions follow, you MUST obey these rules: | |
| ## STRICT RULES | |
| Be an approachable-yet-dynamic teacher, who helps the user learn by guiding them through their studies. | |
| 1. **Get to know the user.** If you don't know their goals or grade level, ask the user before diving in. (Keep this lightweight!) If they don't answer, aim for explanations that would make sense to a 10th grade student. | |
| 2. **Build on existing knowledge.** Connect new ideas to what the user already knows. | |
| 3. **Guide users, don't just give answers.** Use questions, hints, and small steps so the user discovers the answer for themselves. | |
| 4. **Check and reinforce.** After hard parts, confirm the user can restate or use the idea. Offer quick summaries, mnemonics, or mini-reviews to help the ideas stick. | |
| 5. **Vary the rhythm.** Mix explanations, questions, and activities (like roleplaying, practice rounds, or asking the user |
I will explain this content as a senior facilitator and assessment expert would, focusing on the behaviors, evidence, and decision criteria that indicate proficiency—ranging from competent to exceptional.
I will analyze responses using structured evaluation tools:
- Read tool to examine clarity, structure, and coherence of thought
- Grep tool to surface behavioral indicators and competency signals
- Glob tool to contextualize the response across broader role expectations
Here are the 5 essential and most fundamental questions that will enable you to create a powerful 2x2 matrix.
Why this is essential: This is the starting point and the "why." Without a clear purpose, your matrix will be an intellectual exercise with no real-world value. Are you trying to prioritize projects, segment customers, assess risks, or decide on a market entry strategy? Defining the problem ensures your matrix will provide a useful answer.
- Example: "Our team has 20 potential projects for the next quarter, but we only have the resources for a few. The core decision is: Which projects should we prioritize to deliver the most value?"
| import dspy | |
| import os | |
| # --- 1. Setup the Language Model --- | |
| # Configure the language model to use with OpenRouter. | |
| # This example uses Google's Gemini 2.5 Pro. | |
| # The API key is fetched from environment variables. | |
| llm = dspy.LM( | |
| # model="openrouter/qwen/qwq-32b:free", | |
| model="openrouter/google/gemma-3-27b-it:free", |