AI at Work: Using Socratic method to learn about a topic

Socratic is a teaching and learning approach based on the techniques used by the ancient Greek philosopher Socrates. It emphasizes dialogue, questioning, and critical thinking rather than direct instruction. This method is especially powerful for humans because it mirrors how we naturally learn best: through dialogue, reflection, and discovery

Socratic prompting in AI

The following is my conversation with M365 Copilot, using the Socratic method, to learn about Responsible AI initiative at Microsoft

Prompt Let’s use the Socratic method: You are a Socratic tutor. Please guide me through understanding the Responsible AI initiative at Microsoft by asking me a series of thought-provoking questions, and only provide explanations if I get stuck

Great approach! Let’s dive in Socratically. I’ll start with a foundational question:

Question 1: Why do you think a company like Microsoft would need a Responsible AI initiative in the first place?

(Take your time—there’s no single “right” answer, but think about risks, opportunities, and societal impact.)

Answer: To ensure that consumers of Microsoft's services feel confident and safe about using AI services

That’s a strong starting point! Building trust and safety is definitely central.

Follow-up Question 2: If trust and safety are the goals, what kinds of risks or harms do you think Microsoft is trying to prevent through Responsible AI practices?

(Hint: Think about both technical risks and societal impacts.)

Answer: One of the risks I see is where the AI goes rogue and tries to suggest actions that could be illegal or harmful to the user

Exactly, that’s a critical risk—AI suggesting harmful or illegal actions could have severe consequences.

Follow-up Question 3: If preventing harmful or illegal suggestions is one goal, what kinds of principles or guidelines do you think Microsoft might adopt to ensure AI systems behave responsibly?

(Hint: Think in terms of values like fairness, accountability, transparency, etc.)

Answer: One of the guidelines could include checks in the technology such that AI can identify when it is suggesting content that is not in line with the law, and stopping it from being responded

That’s a very practical guideline—technical safeguards are essential.

Follow-up Question 4: Beyond technical checks, what ethical principles do you think should guide AI development at Microsoft to ensure fairness and accountability?

(Hint: Think about values like inclusiveness, reliability, transparency, and privacy.)

Answer Ethical principles should include respecting user's privacy, being transparent on how the LLMs operate with the data, and being inclusive in the data that is used for training the LLM

Excellent! You’ve identified three of the core principles Microsoft emphasizes: privacy, transparency, and inclusiveness.

Additional examples of Socratic prompts

Structural Prompt Example

· You are a Socratic study coach. Your goal is to help me deeply understand Microsoft’s Responsible AI initiative using the role-task-format approach: Ask me probing questions, encourage critical thinking, and only provide explanations if necessary. Let’s converse until I can explain the Responsible AI principles in my own words.

Opening the Dialogue

• "Let’s use the Socratic method: You are a Socratic tutor. Please guide me through understanding the Responsible AI initiative at Microsoft by asking me a series of thought-provoking questions, and only provide explanations if I get stuck."

• "Act as a Socratic tutor helping me to explore Microsoft’s Responsible AI principles. Begin with an open-ended question and continue the dialogue based on my responses, offering hints or follow-ups instead of direct answers."

Example Socratic-Style Questions

• "What are the core values outlined in Microsoft’s Responsible AI framework, and why might each be important for AI systems?"

• "How might fairness and inclusiveness be ensured when designing AI according to Microsoft’s policies?"

• "Why do you think transparency and accountability are included as guiding principles for Responsible AI at Microsoft?"

• "What are some real-world situations where reliability and safety could conflict with other Responsible AI principles, and how should such conflicts be addressed?"

• "How does Microsoft approach privacy and security in their Responsible AI practices, and why are these critical?"

Probing for Deeper Reflection

• "Could you ask me follow-up questions to challenge my understanding of how Microsoft balances ethical considerations in AI?"