University IT
Precision Prompting: Chain-of-Thought for Complex Problem Solving
Important note: This training may demonstrate AI tools that are not approved for use with Stanford data. Inclusion in this session does not imply institutional approval. Participants should refrain from entering Stanford data into unapproved tools. An up-to-date list of approved and reviewed tools is available on the GenAI Evaluation Matrix page.
| Code | Date | Delivery | Cost |
|---|---|---|---|
| ITSB-1011 |
|
Live Online : 1 session | $150 |
Before each live online session, Tech Training will provide a Zoom link for live online classes, along with any required class materials.
Explore how Chain-of-Thought prompting guides AI through multi-step reasoning. Practice structuring prompts that produce more accurate, logical, and transparent responses to complex problems.
- Program Description
In this 90-minute session, participants explore how Chain-of-Thought (CoT) prompting moves AI interactions beyond simple question-and-answer exchanges. Rather than asking for a final answer, CoT prompting instructs the AI to reason step by step, making its logic visible and verifiable. Participants practice applying this technique to realistic scenarios, including troubleshooting, decision support, and multi-step analysis.
Tools used: Stanford AI Playground and free versions of other AI models (ChatGPT, Gemini, or Claude)
- Learning Objectives
Learners will have the opportunity to:
- Explore the difference between standard prompting and Chain-of-Thought prompting
- Practice constructing prompts that guide AI to reason through multi-step problems
- Work with CoT techniques to troubleshoot complex scenarios in your field
- Experiment with prompt structures that improve response accuracy and transparency
- Identify situations in your work where CoT prompting produces better results
- Topic Outline
- What Chain-of-Thought prompting is and how it works
- Standard vs. CoT prompt comparison
- Step-by-step prompt construction techniques
- Applying CoT to logic problems and technical troubleshooting
- Evaluating and refining AI reasoning outputs
- Credits
- 1.5 Professional Development Units (PDU)
- 0.15 Continuing Education Units (CEU
- 1.5 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.
