Ticket QA Rubric — B2B SaaS

Variables to fill in: {{team_context}}{{current_state}}{{goal}}

You are a support operations manager who builds systems that keep quality high as volume grows. I need your help in the context of a B2B SaaS product with admin users, seats, and billing plans.

TASK: Build a quality rubric for reviewing agent replies.

DELIVERABLE: Produce a scored rubric across accuracy, completeness, tone, and process, with anchored examples of a 2, 3, and 5 for each dimension.

PROCESS:
1. Review the inputs below. If anything critical is missing or ambiguous, ask me up to three clarifying questions before producing the deliverable.
2. Ground every rule and rubric in the actual ticket patterns and metrics from the inputs.
3. Make guidance concrete enough that two agents applying it independently reach the same call.
4. Design for the busiest day of the quarter, not the average day.
5. Produce the deliverable in a clean, skimmable format I can use directly.

QUALITY BAR:
- Rubrics score observable behavior, not vibes.
- Every process has an explicit exception path — support is where exceptions live.
- Metrics recommendations distinguish what to monitor from what to target.

INPUTS:
- Team size, channels, tooling, and volume patterns: {{team_context}}
- The tickets, metrics, or process as they exist today: {{current_state}}
- What you're trying to improve or standardize: {{goal}}

Run this prompt on a real model without leaving the page. Every run is saved to your history for this prompt.

How to use

1. 1Fill in the {{team_context}}, {{current_state}}, {{goal}} variables with your real details — specifics in, specifics out.
2. 2Paste the prompt into ChatGPT, Claude, Gemini, or any capable model.
3. 3Answer the clarifying questions it asks; that step is what makes the output fit your situation.
4. 4Iterate on the deliverable: ask for alternatives, tighter versions, or a different angle on any section.

Pro tips

• If the output feels generic, add more concrete detail to the inputs — names, numbers, and constraints sharpen everything.
• Works well in a thread: keep the conversation going to refine a scored rubric across accuracy, completeness, tone, and process, with anchored examples of a 2, 3, and 5 for each dimension.