Support Quality Scorecard
Paste any support conversation and get it graded in seconds. See a 0 to 100 quality score and the exact gaps to fix, the same way IrisAgent AutoQA grades both AI and human agents across 100% of real tickets.
Paste the full back-and-forth. Prefix each line with Customer: or Agent: for the most accurate grade.
Your scorecard will appear here. We grade the agent's responses only, the same way IrisAgent AutoQA scores 100% of real tickets.
Grade support quality the way the best QA teams do
Traditional QA reviews a handful of tickets by hand. That means most conversations are never checked, problems surface late, and coaching is based on a tiny, biased sample. This scorecard shows what AI-powered QA looks like: a consistent rubric applied to a full conversation in seconds, with a clear score and specific, fixable gaps.
What the scorecard checks
By default it grades the agent on empathy and acknowledgment, professional tone, accuracy and on-policy answers, escalation of urgent or high-impact issues, completeness on multi-part questions, personalization, and whether the agent closed the loop with a clear next step. You can switch checks on or off, or add your own in plain language.
From one conversation to 100% of tickets
This tool grades a single conversation. IrisAgent AutoQA does it automatically across every ticket, every day, for both AI agents and human agents. It tracks scores over time by agent and team, flags compliance and escalation misses the moment they happen, and turns the gaps into coaching. Nobody else grades both AI and human agents on the same rubric.
Frequently Asked Questions
What is the Support Quality Scorecard?
It's a free AutoQA tool that grades a single customer support conversation against a set of quality checks (empathy, tone, accuracy, escalation, resolution clarity, and more) and returns a 0 to 100 score with the specific gaps to fix. It's the same grading engine IrisAgent AutoQA uses to score 100% of real tickets, both AI and human agent.
How does the grading work?
Paste a support conversation and the tool sends it to the IrisAgent AutoQA evaluator, which reads only the agent's responses and checks each one against the rubric. Customer messages are used for context but are never graded. Each check returns a pass or fail with a short explanation, and the overall score is weighted by severity (high-severity checks count more).
Is my conversation data stored?
The conversation is sent to our grading API to produce the scorecard and is not saved to any customer account or knowledge base. For best practice, remove personal data such as names, emails, and order numbers before pasting, since you only need the message wording to get an accurate grade.
Can I customize the rules it grades against?
Yes. Open the 'Customize grading rubric' section to turn individual checks on or off, or add your own check in plain language (for example, 'Agent verifies the account before sharing details'). The full IrisAgent AutoQA product lets you define unlimited custom criteria and run them automatically across every conversation.
How is this different from the full IrisAgent AutoQA?
This free tool grades one conversation at a time. The full AutoQA product monitors 100% of your tickets in real time across both AI and human agents, tracks scores over time by agent and team, alerts you to compliance and escalation misses, and feeds gaps back into coaching. This tool is a taste of that, run on a single conversation.
Want the full read across 100% of your tickets?
See how IrisAgent AutoQA grades every conversation, AI and human, and turns quality gaps into coaching automatically.
Explore IrisAgent AutoQA