University IT
7 Essential AI Prompting Techniques
| Code | Date | Delivery | Cost |
|---|---|---|---|
| ITS-1950 |
|
Live Online : 1 session | $300 |
Before each live online session, Tech Training will provide a Zoom link for live online classes, along with any required class materials.
Explore seven practical AI prompting techniques using different AI models. Practice role prompting, chain-of-thought, few-shot examples, reverse prompt engineering, and more to get more useful, reliable results from any AI assistant.
Don Cameron
Don is the Instructional Design lead in Technology Training and has been at Stanford since 1998. He teaches collaboration and communication classes, as well as courses on Smartsheet, Artificial Intelligence, Google Apps, and survey design. Learn more about Don Cameron
- Program Description
AI tools are only as useful as the prompts behind them. In this hands-on session, explore seven essential techniques that experienced AI users rely on to get clearer, more consistent, and more creative results. Using the Stanford AI Playground alongside the AI model of your choice (free versions of ChatGPT, Claude, Microsoft Copilot, or Gemini), practice each technique directly in the tool of your choice.
One of the most powerful skills covered is reverse prompt engineering, where you start with a high-quality AI output and work backward to understand what kind of prompt likely produced it. This technique builds intuition for prompt construction faster than almost any other approach.
- Learning Objectives
Learners will have the opportunity to:
- Practice zero-shot and few-shot prompting to shape AI responses with and without examples
- Experiment with role and persona prompting to shift tone, expertise level, and perspective
- Work with chain-of-thought prompting to guide AI through multi-step reasoning
- Explore structured output prompting to generate tables, lists, and formatted responses
- Apply constraint-based prompting to narrow and focus AI-generated content
- Use iterative refinement techniques to improve responses through follow-up prompts
- Reverse engineer effective prompts from strong AI outputs to build intuition for what works
- Topic Outline
- What makes a prompt effective: clarity, context, and intent
- The anatomy of a well-constructed prompt
- Zero-shot vs. few-shot prompting: when and why to use examples
- Role and persona prompting: adjusting tone, expertise, and perspective
- Chain-of-thought prompting: guiding AI through multi-step reasoning
- Structured output prompting: generating tables, lists, and formatted content
- Constraint-based prompting: focusing and narrowing AI responses
- Iterative refinement: improving results through strategic follow-up
- Reverse prompt engineering: decoding strong outputs to sharpen your instincts
- Comparing prompt behavior across tools: ChatGPT, Claude, Copilot, and Gemini
- Credits
- 3 Professional Development Units (PDU)
- 0.3 Continuing Education Units (CEU
- 3 Professional Development Hours (PDH)
- Stanford Technology Training Program Certificate of Completion Awarded
Custom training workshops are available for this program
Technology training sessions structured around individual or group learning objectives. Learn more about custom training
Special Group Rates
For groups of 5 or more within the same team or department, special rates are available. Please contact techtraining@stanford.edu for more details.
University IT Technology Training sessions are available to a wide range of participants, including Stanford University staff, faculty, students, and employees of Stanford Hospitals & Clinics, such as Stanford Health Care, Stanford Health Care Tri-Valley, Stanford Medicine Partners, and Stanford Medicine Children's Health.
Additionally, some of these programs are open to interested individuals not affiliated with Stanford, allowing for broader community engagement and learning opportunities.
