CARBON — Engineering ConfidenceUser Guide
CHAPTER 08 / 60 Core + Pro

/carbon-demo

Create a fresh, disposable CARBON demo project when the user has no code to test yet, choose a bundled website, SPA, API, eval harness, or large codebase, optionally include a representative existing suite, then run CARBON First Look against the copy.

Jay · Your AI test managerStart & investigate

When to use it

You have no project handy, or want to learn the evidence loop safely.

Before you start

Choose a disposable website, SPA, API, eval harness or larger fixture. Keep seeded demo defects separate from claims about a real product. Inspect the generated project before adapting its tests.

Try this in your coding agent.

/carbon-demo Create a disposable coffee-shop demo and test its checkout flow.

Replace sample paths with your project. Slash names are shorthand; your host may use a plugin prefix or a skill picker. Invocation help →

ILLUSTRATIVE WALKTHROUGH

Disposable coffee-shop app

An expanded teaching example, not a recorded or live execution. The report stays visible while the replay explains how to read it.

  1. 01Create fixture
  2. 02Choose flow
  3. 03Test
  4. 04Report

Coding-agent conversation

Create fixture

I’m reviewing disposable coffee-shop app. I’ll keep the scope and permissions explicit.

Choose flow

Choose flow: Create a disposable coffee-shop demo and test its checkout flow.

Test

Here is the evidence trail to inspect: Create fixture → remove discounted item → inspect stale total.

Report

A seeded cart defect makes the evidence-to-regression loop tangible. The project is disposable and uses synthetic data.

CARBON

Example report

Illustration
Follow the cart state
Follow the cart state — TestBucks teaching screen

TestBucks course screen with illustrative analysis. The screenshot supplies context; the demo does not establish a newly observed bug.

  1. Cart input
  2. Totals & state
  3. Checkout evidence

Illustrated outcome

A seeded cart defect makes the evidence-to-regression loop tangible.

Evidence to inspect

Create fixture → remove discounted item → inspect stale total.

Still untested / not established

The project is disposable and uses synthetic data.

Ready. Read the full example or play its steps.

What a useful result contains

A bounded claim

For disposable coffee-shop app, state the target, revision, environment and actual work performed. Keep planned, executed, blocked and untested work separate.

An inspectable trail

Create fixture → remove discounted item → inspect stale total. In a real run, retain the source, trace, screenshot or fixture behind the conclusion.

The qualification

The project is disposable and uses synthetic data.

The next decision

Decide whether the evidence calls for a focused check, a reviewed fix or more context. Do not convert a plausible example into a verified finding.

Adapt the example to your project

  1. Replace disposable coffee-shop app with a real feature, path or decision in your project.
  2. State the expected rule and its source. Include safe fixtures, constraints and a budget where appropriate.
  3. Ask for exact evidence and remaining gaps. Approve consequential actions separately.
/jay Review the /carbon-demo result. Separate observed evidence, assumptions and untested scope, then recommend the next useful check.

Where to go next

/carbon →/carbon-map →

Content checked against the local command definition: skills/carbon-demo/SKILL.md. Examples adapted from the homepage’s TestBucks walkthroughs. Availability is edition- and host-dependent.