The AI Research Capability Stack
Five Lightning Lessons on the practical stack for AI-assisted research: building an AI research coworker, creating an interview analysis pipeline, getting trustworthy synthetic feedback, orchestrating an agentic research team, and mapping the AI research skills needed for 2027. Designed as an entry path into AI for Customer Research and Agentic AI for Research.
By continuing, you agree to Maven's Terms and Privacy Policy.
Tue Jul 7·4:00 PM UTC
Build Your Claude Research Partner
<p>Most teams now have access to AI, but very few have a reliable AI research workflow. The result is scattered prompts, duplicated effort, and summaries that sound useful before anyone has checked the evidence.</p><p>In this Lightning Lesson, John Whalen shows how to set up an AI research coworker for customer research. You will see how to define the coworker's job, give it the right source material, ask for structured outputs, and add review points so it supports research judgment instead of replacing it.</p><p>This is for researchers, marketers, PMs, designers, and founders who want a practical AI workflow they can reuse across studies.</p>
You'll learn from
John Whalen, PhD
CEO, AI Research Leader, Cognitive Scientist, O'Reilly Author
Wed Jul 8·3:30 PM UTC
Create an AI Interview Analysis Pipeline
Interview analysis is not one task. It is a chain of steps: transcript intake, cleaning, extraction, tagging, theme development, contradiction checks, synthesis, and stakeholder communication.In this Lightning Lesson, John Whalen shows how to create an AI interview analysis pipeline that keeps the work visible. You will see how to decompose the workflow, define handoffs, and make work transparent.
You'll learn from
John Whalen, PhD
CEO, AI Research Leader, Cognitive Scientist, O'Reilly Author
Fri Jul 10·4:00 PM UTC
The AI Research Skills You Need for 2027
AI research is moving from experimentation into professional practice. The skills that matter now are not just prompting or tool awareness. They are knowing when to use AI-moderated interviews, how to judge AI-generated synthesis, when synthetic users are useful, and how to build systems that stay grounded in evidence. In this Lightning Lesson, John Whalen maps the AI capabilities you need today.
You'll learn from
John Whalen, PhD
CEO, AI Research Leader, Cognitive Scientist, O'Reilly Author
Wed Jul 15·4:00 PM UTC
Synthetic Users You Can Trust: Ground, Test, Validate
Synthetic users can sharpen a study before you recruit a single participant. They can also hand you confident answers no real customer would give. The difference isn't the tool — it's whether you have a way to check. In this Lightning Lesson, John shows the validation skill he teaches inside both of his courses: ground synthetic users in real participant data, learn which questions they answer reliably and which they get wrong, and compare synthetic output against real customers so each divergence improves the next round. You'll leave knowing when to trust a synthetic answer, when to override one, and how to make that call visible to your team.
You'll learn from
John Whalen, PhD
CEO, AI Research Leader, Cognitive Scientist, O'Reilly Author
Wed Jul 22·4:00 PM UTC
Orchestrate Your Agentic Research Team
Multi-agent systems are useful when different parts of the research work need different responsibilities. Interview analysis is a good example: one agent can extract evidence, another can find contradictions, another can draft synthesis, and a human can review the final claim. In this Lightning Lesson, John Whalen shows how to orchestrate an agentic research team for interview analysis.
You'll learn from
John Whalen, PhD
CEO, AI Research Leader, Cognitive Scientist, O'Reilly Author