Create intermediate Works with: Any AI

Reply Quality Review and Coaching Feedback

Rubric scoring Has example

Review agent replies and coach improvement.

The Open buttons send the prompt text as currently shown below to that site only when you click. Fill in the placeholders first.

[VERIFY] is an editorial flag, not a blank to fill. Wherever the prompt shows [VERIFY], check that item against a reliable source before you use it.

Review support replies and write coaching feedback. Our quality standards: [QUALITY_STANDARDS]. Reply samples with the customer message above each (anonymized): [PASTE_CONVERSATIONS]. Agent experience level: [EXPERIENCE_LEVEL].

For each conversation, score from 1 to 5 with a quote supporting the score:
1. Understanding: answered the actual question, including unstated needs.
2. Accuracy: correct policy and product information (flag anything you cannot verify as [VERIFY]).
3. Completeness: all parts answered, next steps clear.
4. Tone: warmth, respect, no jargon, no blame.
5. Clarity and structure: easy to read and scan.
6. Ownership: avoids unnecessary handoffs, sets expectations.
7. Efficiency: no needless back and forth.
8. Compliance: privacy and security (no sensitive data in plain text, identity checks).

Then produce coaching notes for each agent: two specific strengths, one priority improvement with a before and after rewrite of a real sentence from their reply, and a practice task. Use a supportive, growth-oriented tone and avoid ranking agents against each other. Summarize team-level patterns in a table and recommend macro or training changes. Do not infer anything about an agent beyond the replies provided.

Go through every fact, figure and claim and verify it against your records or official documentation, then have a qualified professional assess legal, safety or financial points before relying on them.

Fill in before use

Optional: type your details and the prompt above updates. Nothing is saved or sent.

Replace each bracketed placeholder with your own details, then paste into Any AI or another assistant.

Conversation 4 (agent B). Scores: understanding 4, accuracy 3 ([VERIFY] the refund window quoted), completeness 2, tone 4, clarity 3, ownership 2, efficiency 3, compliance 5.
Quote supporting completeness: the customer asked about the refund and the replacement; the reply covered only the refund.
Coaching note: Strengths: warm greeting; stayed calm after the customer's second message. Priority: answer every question in the message. Before: "I've processed your refund." After: "I've processed your refund, and I've reserved a replacement; it ships Thursday." Practice: read the customer's message aloud and list the questions before replying.
Team pattern: 5 of 12 replies missed a second question. Suggest a macro checklist.

• coaching
• qa