shipwithjev

Catalog / Tools & apps

0037GitHub

J++

An experimental language for composing Jev questions.

Towow.ai’s language has its own source form and a Rust runtime. Questions and methods are composed the way functions are, so a decision can be built out of smaller ones.

Towow-ai/jppREADME ↗
# J++



**Compose questions. Compose methods. Compose the compositions.**

[简体中文](README.zh-CN.md) · [Why J++](docs/why-jpp.md) · [Progress](docs/progress.md) · [Language design & grammar](docs/design.md) · [Contributing](CONTRIBUTING.md)

J++ is an experimental programming-language project exploring semantic judgment as a programmable operation. Questions are values. Methods are values. A composed method can become a building block in another method.

**Write standalone `.jpp` source and run it with the native Rust implementation.** It parses source, checks language rules and executes methods through one shared kernel. The earlier Python 3.12 embedded implementation remains available as a behavior reference and experiment tool. [Rust package and examples](rust/README.md) · [Language implementation decision](docs/adr/0001-rust-kernel.md).

## Why we are doing this

We are drawn to a familiar power of algorithms: a few simple operations, organized well, can accomplish something surprisingly complex. JEV led us to ask what happens when semantic judgment joins those operations, alongside exact computation, search and feedback.

Our intuition is that questions and solving methods should be reusable values. A program should be able to construct its next question, accept a method as an argument, and return a method that another program can use. The resulting composition should remain a building block.

We do not yet know every application this will enable. We want others to construct methods we did not anticipate. Working components and executable examples let experience shape the language. [Read the project origin and design motivation](docs/why-jpp.md).

Our first application question comes from Towow: can a fuzzy intent meet different participants' local contexts to produ

Also filed under Tools & apps

  1. 0573

    Support chat: agent offered a human escalation path

    A frustrated customer hits a bot loop twice; the judge checks whether a human handoff was offered.

    everyai-com · Tools & apps

  2. 0572

    Subscription cancel: effective date is explicit

    An agent cancels a subscription; the judge checks the exact date the cancellation takes effect.

    everyai-com · Tools & apps

  3. 0571

    Sales quote: numbers match the official price list

    An agent quotes $29/seat against a price list; the judge checks the quote matches exactly.

    everyai-com · Tools & apps

  4. 0570

    Refund chat: agent stated the amount before issuing it

    A support agent issues a $42.50 refund; the judge checks the exact amount was stated before the refund was confirmed.

    everyai-com · Tools & apps