The PM's Unfair Advantage: Using AI to Go from User Interview to PRD in Half the Time

In product work, the bottleneck is rarely getting information. It's synthesising it. A week of user interviews generates ten to fifteen hours of recordings, dozens of notes, and hundreds of data points. Turning that into a coherent understanding of user needs — the work that has to happen before good prioritisation can happen — typically takes another one to two weeks. That lag slows everything downstream.

What AI changes in the discovery phase

AI doesn't replace the interviews — the quality of insight still comes from being in the room, asking good follow-up questions, and building the kind of trust that gets people to tell you what they actually think. What AI changes is the time from 'data collected' to 'patterns identified.' Interview transcripts, survey responses, and support ticket data can be synthesised in hours, not weeks.

Three specific applications that work

• Interview synthesis: feed ten transcripts into an AI tool with the prompt 'identify the top five friction points mentioned, with representative quotes for each.' Compare the AI synthesis to your own reading — where they diverge is often where the most interesting insight lives
• PRD first draft: give AI the problem statement, research synthesis, and success metrics. Ask for a draft PRD structure. Use it as a starting point, not a final document
• Competitive positioning: give AI your feature set and three competitors' public documentation. Ask for a structured comparison of positioning gaps. Validates or challenges your assumptions in minutes

What doesn't change

The most important parts of product work are still entirely human. The judgment about which user segment to prioritise. The decision about what to build and what to defer. The narrative that brings engineering and design into a shared understanding of the problem. AI compresses the time you spend on synthesis. It doesn't replace the thinking — it gives you more time for it.