Practice · with Priya Raman
The Demo-to-Production Gap
The demo works. Six months later the project is quietly shelved. Priya Raman has shipped and buried enough AI systems to know exactly where the floor gives way, and she walks us through each drop.
Audio for this episode is not attached yet — add an `audioUrl` to the episode file to enable playback
This week's guest
Priya Raman
Head of Platform Engineering
The demo works. Six months later the project is quietly shelved. Priya Raman has shipped and buried enough AI systems to know exactly where the floor gives way, and she walks us through each drop.
In this episode
Why demos are structurally dishonest
They are built on the happy path, with hand-picked inputs, by the person who knows the system best.
The evaluation gap
Teams that ship have a test set before they have a product. Teams that stall have a vibe and a stakeholder.
Cost curves nobody models
What happens to unit economics when usage triples and prompts grow with every feature request.
The organisational failure mode
The system works and nobody uses it. Adoption is a design problem, not a training problem.
Every AI project I have watched fail, failed at the same place: nobody could say what good looked like.
Mentioned
- The full written companion piece in the articles archive
- Module material on this topic in the AI Fluency programme
Beyond the Prompt publishes a new episode most weeks. Subscribe wherever you listen, or read the written edition first — both cover the same ground, at different speeds.