The materials for this workshop are located here.
Bruno's version: https://docs.google.com/presentation/d/1GHvBg7aNsoV57uvKs1H09gy8CqnX5-pLK9R1TLOoHLU/edit?usp=sharing
This workshop assumes familiarity with the concepts covered in D-Lab Demystifying AI Workshop. While prior attendance is not strictly required, participants should have a basic understanding of how Large Language Models work and their core limitations.
Check out D-Lab's Workshop Catalog to browse all workshops, see what's running now, and review prerequisites.
In this hands-on workshop for GSPP students, we focus on practical application of AI tools for policy-relevant tasks. You'll learn prompt engineering frameworks to get better results from AI, practice using AI for common policy work products like issue scans, policy memos, and evidence synthesis, and develop strategies for responsible, transparent use in professional settings. Throughout, we emphasize staying "above the AI baseline"—using AI to enhance your work while demonstrating the critical judgment and contextual expertise that only human analysts can provide.
After this workshop, you will be able to:
- Apply prompt engineering frameworks (such as CLEAR) to improve AI outputs for policy tasks.
- Use AI tools effectively for evidence assembly, stakeholder analysis, and memo drafting.
- Critically evaluate AI-generated content for accuracy, bias, and missing context.
- Develop workflows for using AI in internships, capstone projects, and professional policy work.
- Articulate where human judgment remains essential in policy analysis.
This workshop does not cover the following:
- Foundational concepts underlying AI, machine learning, and neural networks. This is covered in Goldman Demystifying AI.
- Applied coding for Machine Learning. This is covered in Python Machine Learning Fundamentals and R Machine Learning with tidymodels.
- Using LLMs for academic research applications. This is covered in LLMs for Exploratory Research.
This 2-hour workshop is highly interactive. You'll need access to at least one AI tool (ChatGPT, Claude, or Gemini) on your laptop. The session includes:
- Prompt Engineering Framework – Learn the CLEAR method for structuring effective prompts
- Issue Scan Exercise – Practice rapid evidence assembly on an assigned policy topic
- Memo Drafting Practice – Use AI to draft policy memo components, then refine
- Human Overlay Exercise – Identify what AI misses and where your expertise adds value
- Professional Workflows – Strategies for transparent AI use in internships and capstones
Check out the following resources to learn more about prompt engineering and AI for professional work:
- Learn Prompting: A comprehensive, free guide to prompt engineering techniques.
- Anthropic's Prompt Engineering Guide: Best practices for prompting Claude and other LLMs.
- DHS Generative AI Public Sector Playbook: Government guidance on AI use in public sector contexts.
- Bardach & Patashnik, A Practical Guide for Policy Analysis: The Eightfold Path framework referenced throughout this workshop.
D-Lab works with Berkeley faculty, research staff, and students to advance data-intensive social science and humanities research. Our goal at D-Lab is to provide practical training, staff support, resources, and space to enable you to use R for your own research applications. Our services cater to all skill levels and no programming, statistical, or computer science backgrounds are necessary. We offer these services in the form of workshops, one-to-one consulting, and working groups that cover a variety of research topics, digital tools, and programming languages.
Visit the D-Lab homepage to learn more about us. You can view our calendar for upcoming events, learn about how to utilize our consulting and data services, and check out upcoming workshops.
Here are other AI workshops offered by the D-Lab: