High quality customer interviews are a superpower for figuring out which features to build and which to kill. I've conducted hundreds over the years, working toward product-market fit.
tl;dr When you ask the right questions, body language tells you what matters most. Transcripts tell you the rest.
Here's a complete LLM prompt framework to get started, created from my real-world usage, including the exact interview script I follow.
The bare-bones MVP is that you clone this repo, point your LLM at a directory of transcripts, and tell it to go.
===
Free idea: build a lightweight version of this, but on freedom tech.
Potential components:
@Soapbox Shakespeare
+ jitsi for video
+ blossom for video storage (encrypted?)
+ @npub130mz...l29s or @Maple AI for post-interview transcription and—most importantly—patterns and insights from a campaign of interviews
I've been thinking a lot about how best to explain the benefits of building on nostr—what's different and why one should care.
Not just what we're running away from…
But what we're moving toward.
I asked @Pip the social graph guy to help, specifically with web of trust, and we recorded it on @Trust Revolution.
Full episode coming Thursday.
