AI prompt to build a producer scorecard

An agency grows through its people. AI helps owners and managers write job ads, onboarding plans, training quizzes, SOPs and coaching plans faster, so new staff become productive sooner.

Below is a ready-to-copy prompt to build a producer scorecard, a detailed version that asks you clarifying questions first, and 1 specialized AI tool (Gong) with instructions for this task. It also works in ChatGPT, Claude, Gemini or Copilot.

Try it in the search box ›

The prompt

Act as an insurance agency sales manager. Using the de-identified numbers below for two or more team members (use role labels like Producer A / CSR B, no names or client data), build a side-by-side scorecard for the same period: activity (calls, emails, appointments), quotes issued, policies sold, close ratio (sales/quotes), written premium, cross-sell rate, retention, and service metrics for CSRs (tickets handled, response time). Normalize for hours worked and lead volume so the comparison is fair, rank each metric, and note which differences are significant versus noise. Then list each person's top strength, one focus area, and one coaching action, plus how to discuss the results constructively. Do not invent numbers; ask me for anything missing. Data: [paste table]

Detailed version (asks clarifying questions first)

Act as an experienced assistant to a licensed insurance agent. Before answering, ask me up to 3 clarifying questions (the role, the person's experience level and tone). Then complete this task, and finish with a short checklist of statements I should verify with my compliance team.

Task: Act as an insurance agency sales manager. Using the de-identified numbers below for two or more team members (use role labels like Producer A / CSR B, no names or client data), build a side-by-side scorecard for the same period: activity (calls, emails, appointments), quotes issued, policies sold, close ratio (sales/quotes), written premium, cross-sell rate, retention, and service metrics for CSRs (tickets handled, response time). Normalize for hours worked and lead volume so the comparison is fair, rank each metric, and note which differences are significant versus noise. Then list each person's top strength, one focus area, and one coaching action, plus how to discuss the results constructively. Do not invent numbers; ask me for anything missing. Data: [paste table]

What a good result looks like

A good scorecard compares team members fairly: same period, same measures, adjusted for hours and lead volume, with each metric ranked and a note on which differences are meaningful. It ends with a strength, a focus area and a coaching action for each person.

Common mistakes and watch-outs

Small numbers produce noisy rankings, so don't make decisions from one month. Use role labels, not names, in AI tools, and discuss results privately and constructively. Gong data is useful context but not a full picture of performance.

How to adapt the prompt

Add metrics that matter for your agency (reviews, retention by producer) and run it quarterly. Ask for talking points for each one-to-one.

EXAMPLE output (placeholder data, not a real client)

Scorecard - [Quarter] (normalized per 40 hours)

| Metric | Producer A | Producer B |
| Quotes issued | [Number] | [Number] |
| Close ratio | [Percent] | [Percent] |
| Cross-sell rate | [Percent] | [Percent] |
| Retention | [Percent] | [Percent] |

Producer A - Strength: close ratio. Focus: cross-selling. Action: add a life question to every home quote.
Producer B - Strength: retention. Focus: quote volume. Action: block 2 hours a day for follow-ups.

Note: differences under [Threshold] may be noise.

How to use it

Copy the prompt. Copy the short prompt above, or the detailed version if you want the AI to ask clarifying questions first.
Fill in the placeholders. Replace [paste table] with your own details. Use placeholders or de-identified details; never paste client personal information.
Run it in the right tool. Paste it into ChatGPT, Claude, Gemini or Copilot, or use Gong as described below.
Review before you use it. Use aggregated numbers, not individual client records, when you analyze results with AI. Check every fact, name and number yourself.
Take the next step. Next, see: Create a coaching plan for a struggling producer.

Best AI tools for this task

Specialized tools first, ordered by fit for this task (never by payout), then any general AI assistant.

Gong site ↗

Revenue AI platform that records and analyzes sales calls for coaching.

How to use it

In Gong, pull the same period for each team member (use role labels like Producer A / Producer B, not names). Compare side by side the call activity, talk ratio and interactivity, topics and keywords detected, customer sentiment, and deal/pipeline progress from Gong's conversation and deal tracking. Ask Gong's Ask Anything AI: 'Compare Producer A and Producer B over the last 30 days: call volume, talk ratio, how often they ask discovery questions, how they handle price objections, and deals advanced.' Then write a strength, a focus area and one coaching action for each person, and check the numbers against your agency's sales data before discussing them.

Any AI assistant

ChatGPT Claude Google Gemini Microsoft Copilot

Paste the prompt above (short or detailed) into any of these.

Before you use it

Use aggregated numbers, not individual client records, when you analyze results with AI.
Keep employee personal information and performance details out of general AI tools.
Never paste client personal information (names, policy numbers, health or financial details) into AI tools your agency hasn't approved.
Review every AI output for accuracy and compliance before you use it.

Was this page helpful?