CARBON — Engineering ConfidenceUser Guide
CHAPTER 59 / 60 Pro

/carbon-human

Ask, retain, and record the smallest set of project-specific human decisions that materially change CARBON confidence, readiness, risk, test selection, or release interpretation.

Jay · Your AI test managerTesting operations

When to use it

Business intent or risk tolerance cannot be inferred from code.

Before you start

Answer only consequential questions and retain unknowns explicitly. Human context informs the judgment; silence is not approval, and this command is not a mandatory gate for every test.

Try this in your coding agent.

/carbon-human Ask me what matters most before testing the new checkout experience.

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

Human testing priorities

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

  1. 01Read context
  2. 02Analyze
  3. 03Show evidence
  4. 04Report

Coding-agent conversation

Read context

I’m reviewing human testing priorities. I’ll keep the scope and permissions explicit.

Analyze

Analyze: Ask me what matters most before testing the new checkout experience.

Show evidence

Here is the evidence trail to inspect: Question: wrong charge, blocked purchase or delayed receipt? Record the answer as context.

Report

Jay asks about the costliest failure before committing to a plan. The demo does not submit or store a real answer.

CARBON

Example report

Illustration
Project → decisions → retained evidence
Project → decisions → retained evidence — TestBucks teaching screen

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

  1. TestBucks project
  2. Command action
  3. Reviewable output

Illustrated outcome

Jay asks about the costliest failure before committing to a plan.

Evidence to inspect

Question: wrong charge, blocked purchase or delayed receipt? Record the answer as context.

Still untested / not established

The demo does not submit or store a real answer.

Ready. Read the full example or play its steps.

What a useful result contains

A bounded claim

For human testing priorities, state the target, revision, environment and actual work performed. Keep planned, executed, blocked and untested work separate.

An inspectable trail

Question: wrong charge, blocked purchase or delayed receipt? Record the answer as context. In a real run, retain the source, trace, screenshot or fixture behind the conclusion.

The qualification

The demo does not submit or store a real answer.

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 human testing priorities 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-human result. Separate observed evidence, assumptions and untested scope, then recommend the next useful check.

Where to go next

/carbon-confidence →/carbon-confidence-plan →

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