Back to Public SeminarsAI Agent-Driven Research Workflows - A Short Course
A 4-Day Livestream Seminar Taught by Charles Crabtree, Ph.D.
Getting More Done Without Losing Control
Many researchers already use AI in small, informal ways—summarizing papers, cleaning text, drafting code, or checking results. What’s often missing is a clear, practical framework for using AI systematically while keeping accuracy, judgment, and responsibility firmly in human hands.
AI agents can dramatically speed up research processes, but they can also make mistakes harder to detect. This seminar shows you how to move routine work to AI while slowing down at exactly the points where human judgment is essential. The goal is not “automated research,” but more careful research conducted more efficiently.
This 4-day introductory seminar focuses on AI agent-driven research workflows: simple, structured ways to use multiple AI tools together to reduce low-value work while avoiding hidden errors. You’ll learn how to break projects into steps, design multi-stage workflows with built-in checks, and document AI use clearly so that your process remains transparent and reviewable. Examples draw from quantitative, qualitative, and mixed-methods research, with an emphasis on principles that transfer across disciplines. No prior experience with AI agents is assumed.
Starting August 4, this seminar will be presented as a 4-day synchronous, livestream workshop via Zoom. Each day will feature two lecture sessions with hands-on exercises, separated by a 1-hour break. Live attendance is recommended for the best experience. If you can’t join in real time, recordings will be available within 24 hours and accessible for four weeks after the seminar.
Closed captioning is available for all live and recorded sessions. Captions can be translated to a variety of languages including Spanish, Korean, and Italian. For more information, click here.
ECTS Equivalent Points: 1
More Details About the Course Content
By the end of the course, you will have the skills to:
-
- Identify which research tasks are safe to speed up—and which are not.
- Use AI to reduce low-value work without delegating judgment.
- Build simple multi-step workflows that include built-in checks.
- Recognize common AI errors before they affect results.
- Decide where human review is essential and where it is optional.
- Clearly explain and document how AI was used in a project.
Computing
To participate fully, you’ll need to download and set up Warp, a terminal-driven agent interface. No programming setup is required, though you’re welcome to use a laptop and a current project to apply the workflows to your own work.
Who Should Register?
This seminar is designed for:
-
- Faculty and graduate students who want to use AI productively but cautiously.
- Researchers who feel pressure to “use AI” and AI agents in particular but are unsure how to do so responsibly.
- Scholars who care about accuracy, credibility, and reviewability.
- Teams looking to standardize AI use without over-automating research.
This course is not for participants seeking advanced technical training, software engineering, or fully automated research systems.
Outline
Day 1: What AI can help with—and what it should not do
-
- What people mean by “AI agents” and how they differ from chat-based LLM interfaces
- Common ways researchers already use AI
- Breaking a research project into steps
- Identifying routine work versus judgment-heavy work
- Where AI saves time and where it creates risk
Day 2: Simple agent workflows for everyday research
-
- Using different AI tools for different tasks
- Keeping tasks small and clearly defined
- Avoiding black-box AI use
- Designing workflows that are easy to understand and explain
Day 3: Accuracy, checking, and human oversight
-
- Common AI mistakes and how they appear in real projects
- Using comparison and disagreement to spot errors
- When to trust AI output and when to stop and check
- Preventing small mistakes from spreading through a project
Day 4: Transparency, responsibility, and best practices
-
- Keeping track of what AI did and when
- Explaining AI use in papers, grants, and talks
- Who is responsible when AI is involved
- Ethical considerations and institutional expectations
- Developing personal rules of thumb for AI use
Seminar Information
Tuesday, August 4 –
Friday, August 7, 2026
Schedule: All sessions are held live via Zoom. All times are ET (New York time).
10:30am-12:30pm (convert to your local time)
1:30pm-3:00pm
Payment Information
The fee of $995 USD includes all course materials.
PayPal and all major credit cards are accepted.
Our Tax ID number is 26-4576270.