Small decisions. Interesting possibilities.Submit contentSubmit
JCR preview

JCR

A capability resolver that walks a nested tree of documented operations with Jev choice questions and returns only the instructions an agent needs for the current step.

Added to Jevfast

How it uses Jev

The state is the current request and the step being resolved. Every open candidate in the capability tree becomes one choice question keyed choice_N whose options are that node's direct children plus a none option, and each child's returned probability ranks the walk. When the walk narrows to three finalists, one more choice picks between them, and only the selected operations' documentation is returned.

What Jev decides

Choosing a capability branch (illustrative)Example answers · not a recorded Jev response · Source ↗
Question 1 · choice 0
YOUR APP
INSTRUCTION

At the capability root, which direct child best provides the exact capability needed for this step?

STATE

The state is the agent's request and the current step. Options are the direct children of the node being expanded, each with its name and description, plus a none option; the ids below stand in for one catalog's own paths.

JEV · CHOICE
  1. capabilities/build
  2. capabilities/deploy
  3. __none__

App workflow

  1. Start from the request

    The agent calls the resolver with the task, and the resolver opens the capability tree at its root.

  2. Expand candidates

    For each open candidate it asks one choice question over that node's direct children, sending the request and step as state.

  3. Walk the tree

    Child probabilities extend each candidate's score by the geometric mean of its path, and an unsure branch drops out instead of being followed.

  4. Return documentation

    Up to three finalists get one more choice, and the resolver returns the selected operations' instructions without executing anything.

Why it is interesting

It uses Jev as a search policy over a hierarchy rather than as a text generator, and it scores a whole path by the geometric mean of its question probabilities so a confident early choice cannot hide an unsure one deeper in the tree.