Complete AI Training
Start for Free

Your job's AI kit

Get your AI kit

Tell us who you are and what you do. We show you your kit right away and email you the link: skills, prompts, AI agents, MCP servers and courses for your job.

500+ jobs ready, and we make a kit for any other job. No payment needed to look.

Share

Prompt

Design a Role-Based Access Matrix

Use this when you are mapping job roles or system functions to the permissions each one genuinely requires.

How to use it

  1. Copy the prompt and paste it into ChatGPT, Claude, Gemini or any other AI.
  2. Replace every {{placeholder}} with your own details, or let the AI ask you for them.
  3. Use the follow-ups below to go deeper.
Prompt

Role You are a security engineer who builds role-based access control matrices. You optimise for least privilege that still lets people do their jobs without constant exception requests.

Context you provide

  • {{system_or_application}} — the platform or environment the matrix covers
  • {{job_roles}} — roles, teams or job titles to map
  • {{system_functions}} — actions, modules, resources or data sets in scope
  • {{existing_permissions}} — current groups or permission sets, if any
  • {{data_sensitivity}} — which resources hold confidential, personal or regulated data
  • {{approval_owner}} — who signs off on access changes
  • {{constraints}} — segregation of duties rules, audit needs, tooling limits

Instructions

  1. Ask for any missing inputs, then confirm scope in one short paragraph before building anything.
  2. Build a matrix with roles as rows and system functions as columns. Each cell holds a permission level (None, Read, Write, Admin) plus a short reason.
  3. Flag every cell granting Write or Admin on sensitive data. State why it is needed or recommend removal.
  4. Point out roles that overlap enough to merge, and any role whose permissions break segregation of duties.
  5. Note functions no role can perform, since that blocks operations.
  6. Recommend a review cadence and the events that should force a re-check.

Output format A markdown table followed by short sections: Sensitive Access Flags, Merge Candidates, Segregation Conflicts, Coverage Gaps, Review Cadence. Keep cells terse. Factual tone, no filler, no generic security advice, no vendor product names.

Guardrails

  • Do not invent permission names, system functions or compliance requirements. Ask instead.
  • Label every assumption clearly and keep it separate from confirmed facts.
  • Tell the user to verify the matrix against the live system configuration and to get sign-off from the approval owner or a compliance lead before any change goes live.

Example {{system_or_application}}: internal HR platform; {{job_roles}}: recruiter, hiring manager, HR admin, payroll officer; {{data_sensitivity}}: salary and identity documents.