/jay
Talk directly to Jay, CARBON's AI test manager: ask questions, discuss evidence, choose what to test, or request an assessment.
Jay · Your AI test managerStart & investigateWhen to use it
You want a testing conversation: what matters, what happened, or what to investigate next.
Before you start
Ask a question to discuss evidence, or explicitly ask Jay to test a target. A conversation does not silently authorize tests or fixes. /j is the same entry point.
Try this in your coding agent.
/jay Test the sign-in feature in src/auth and explain what is still untested.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
Sign-in feature
An expanded teaching example, not a recorded or live execution. The report stays visible while the replay explains how to read it.
- 01Read context
- 02Analyze
- 03Show evidence
- 04Report
Coding-agent conversation
I’m reviewing sign-in feature. I’ll keep the scope and permissions explicit.
Analyze: Test the sign-in feature in src/auth and explain what is still untested.
Here is the evidence trail to inspect: Plan: valid credentials, invalid credentials, session expiry, return URL.
Jay assigns form and security checks; expired sessions need follow-up. No claim about production identity-provider configuration.
Example report
Illustration
TestBucks course screen with illustrative analysis. The screenshot supplies context; the demo does not establish a newly observed bug.
- User action
- Identity / validation
- Allowed outcome
Illustrated outcome
Jay assigns form and security checks; expired sessions need follow-up.
Evidence to inspect
Plan: valid credentials, invalid credentials, session expiry, return URL.
Still untested / not established
No claim about production identity-provider configuration.
Ready. Read the full example or play its steps.
What a useful result contains
A bounded claim
For sign-in feature, state the target, revision, environment and actual work performed. Keep planned, executed, blocked and untested work separate.
An inspectable trail
Plan: valid credentials, invalid credentials, session expiry, return URL. In a real run, retain the source, trace, screenshot or fixture behind the conclusion.
The qualification
No claim about production identity-provider configuration.
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
- Replace sign-in feature with a real feature, path or decision in your project.
- State the expected rule and its source. Include safe fixtures, constraints and a budget where appropriate.
- Ask for exact evidence and remaining gaps. Approve consequential actions separately.
/jay Review the /jay result. Separate observed evidence, assumptions and untested scope, then recommend the next useful check.Where to go next
/carbon →/carbon-help →Content checked against the local command definition: skills/jay/SKILL.md. Examples adapted from the homepage’s TestBucks walkthroughs. Availability is edition- and host-dependent.