Why Vibe Coding Isn't Enough
"Vibe coding" — describing what you want and letting a model write the code — is genuinely remarkable. For a prototype, a script, a weekend project, it collapses hours into minutes.
But enterprise software has rarely failed because a developer couldn't write a function. It fails somewhere upstream and downstream of the code: in the gap between what the business meant, what got built, and what actually shipped.
The task is not the mission
Writing code is a task. Delivery is the mission. The mission includes:
- Understanding the real problem behind the stated request
- Coordinating a dozen people who each hold one piece of the truth
- Preserving decisions so they don't have to be re-litigated every sprint
- Getting the thing into production without breaking the last thing
A model that writes flawless code still leaves most of that untouched.
Where the failures actually live
After twenty years of enterprise Salesforce delivery, the pattern is consistent. Projects stall on:
- Lost context — the "why" behind a requirement evaporates between refinement and build.
- Coordination overhead — more time is spent syncing than building.
- Knowledge that never compounds — every project starts from scratch.
None of these are coding problems. They're delivery problems.
Toward vibe delivery
The interesting question isn't "can AI write the code?" It's:
Can AI hold the context, coordinate the work, and carry the knowledge forward — so that delivery itself becomes fluent?
That's the shift I'm researching: from vibe coding to vibe delivery. The next essays work through what that actually requires.