How to run a Jev decision workflow offline with mock responses with Awesome Jev

Who it is forA developer who wants to see how a state-and-questions workflow behaves before paying for or configuring live access.

The problemSetting up an API key and account before seeing a working Jev workflow slows down evaluation.

The outcomeA local run of a complete workflow that shows how questions, answers, and fallback handling fit together.

What you need first

Node.js 22 or later, for installing the Awesome Jev Guide skill
A coding agent such as Claude Code or Codex
Python, if you want to use the TypeSafe Python SDK
A TypeSafe API key, only for live calls; the offline examples need no account or key

Steps

Clone the AppitStudio/awesome-jev repository to your machine.
Open docs/getting-started.md and follow its local run steps.
Run the example with its synthetic mock responses.
Read docs/decision-patterns.md to see how Choice, Score, and Noul differ in the example.
Change one question in the example and confirm the output changes as expected.

Prompt for your agent

In the AppitStudio/awesome-jev repo, follow docs/getting-started.md to run the local example with mock responses. Report the output of the <example name> run and confirm that no network call or API key was needed.

Caveat. The mock responses are synthetic, so the run shows the workflow shape, not how Jev performs on real data.