Wish Course

Wish product architecture

How Hermon Code becomes a product surface for AI software work under Maple authority.

Domain hubEvaluation snapshot

Learning Objectives

What this lesson should make precise

01

Name the core abstraction and its failure modes.

02

Translate the concept into a Maple/Hermon proposal contract.

03

Define at least one evaluation case that can fail the model safely.

Tutorial Flow

How this lesson becomes a demo and training target

Each tutorial is written as a user education path and a model-improvement artifact. The diagram shows how the idea moves into a lab, a typed contract, an eval gate, and then a Hermon/MapleAI demo route.

01

Concept

Product roles

02

Applied Lab

Applied lab: Wish product architecture

03

Output Contract

workflow, services, model_routes, authority_gates

04

Eval Gate

Does the answer separate model proposal from deterministic execution?

05

Demo Route

Wish training and public model checks

01

Product roles

Wish should separate chat UX, repo indexer, patch planner, execution sandbox, CI connector, deployment gate, and receipt store.

  • Planner is not executor.
  • Sandbox is constrained.
  • Receipts are durable.

02

Model lane

Hermon Code can specialize on structured engineering proposals while stronger general models remain available for explanation and synthesis.

  • Use domain adapter.
  • Fallback to general model.
  • Keep same contract.

03

Commercial wedge

The wedge is not another coding chat. It is accountable code operations: patches, tests, CI repair, deployment readiness, and rollback under one authority model.

  • Sell reliability.
  • Sell governance.
  • Sell team memory.

Lab

Applied lab: Wish product architecture

Design the Wish workflow from user request to repo inspection, patch proposal, test execution, review, deployment, and receipt.

Expected result

  • A typed JSON-style proposal rather than free-form advice.
  • Clear authority boundaries and denied operations.
  • A test or rubric that decides whether the proposal is deployable.

Evaluation

How Maple would grade this work

Rubric

  • Does the answer expose assumptions instead of hiding them?
  • Does the answer separate model proposal from deterministic execution?
  • Does the answer produce artifacts that can be tested, reviewed, and rolled back?

Output contract

workflow, services, model_routes, authority_gates, receipts

Use this lesson as training direction

A strong lesson gives users a mental model and gives Hermon a sharper target for examples, probes, and demo prompts.

View evalsDomain hub