How do you help a developer in 2026?
An IntelliJ plugin for agent efficiency. We put a decision model in the agent's hot path, so the expensive model is only called when it has earned the call.
Jevons paradox, running inside your IDE
The name is not a pun we reverse-engineered. It is the actual problem.
Real problems, not invented ones
Three developers on this team, three answers, all of them the same shape.
Several sessions at once, each producing more than anyone can read. Tracking what each one changed, while still doing your own work, becomes the bottleneck.
The limit hits halfway through and the thread is lost, so you restart rather than resume. Nothing tells you what was finished and what was not.
A throwaway question asked inside a long session, because a new chat would lose the context. The dumbest question in the room costs the most.
Jev · TypeSafe System One
Jev cannot emit a string. That constraint is the whole design, and the shape below is reused by every feature.
What every idea turned out to be
We brought eight ideas and found they were one idea: a go and look, done before the expensive model wakes up.
File finder · the flagship
Grep needs the right word. Embeddings need an index that goes stale. Agents read files one at a time. Jev reads all of them at once.
Bug twins
The same business rule, written three times by three people under three names. No search finds all of them.
How we prove it
Split screen, same task, same LLM, one real repository. Left explores by opening files. Right packs the window in one pass.
What we need from you
We would rather be told now which features to drop than find out on stage.
Jev decides in the hot path, the LLM writes on demand, PSI supplies structure for free. Six features, one shape, which is why they fit in one plugin rather than six.
Kotlin, IntelliJ Platform SDK, Koog, Jev via OpenRouter.