Experiment
I’ve been exploring a problem space in the automotive industry for a few years now—long before AI entered the spotlight. What started as a client-led Design Thinking project that ultimately stalled became a personal pursuit. After the client engagement ended, I continued the investigation on my own, initially applying classical product design methods to draft a PRD. Recently, I’ve returned to the project, now leveraging AI to push the work further.
Experiment goals
In this experiment, I pick up the original PRD I put together using classical PM approaches and give it to AI. The original material I used to create the PRD draft is a bit dated so I want to refresh the research and clarify the viability of the proposed future-state hypotheses.
- Leverage Claude and Perplexity to conduct deep research on the current state of the vehicle purchase and trade-in industry
- Leverage Claude and Perplexity to identify and validate product market fit, competitor threats and future-state forecasts
- Leverage Claude and Perplexity to assess the viability and feasibility of the proposed solution hypotheses contained in the original PRD draft
- Produce a well-formatted PRD document
- Produce an engaging and powerful pitch deck for VC audiences
Tools and prerequisites
I’ll use just one tool for this experiment. Prior to conducting this experiment, I had collected a variety of primary and secondary research material to help frame the problem space using classical PM approaches. I asked Claude and Perplexity to refresh those reports using current analytics and available research.
- Claude (Free)
- Perplexity (Abacus.ai)