> For the complete documentation index, see [llms.txt](https://docs.patagon.ai/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.patagon.ai/en/sales-performance/benchmarks.md). # How to read your agent's performance metrics For rating definitions, see the [ILA lead rating system](/en/agent-optimization/ila-rating-system.md). Your agent generates data from every conversation. Knowing how to read that data — and what questions to ask when something looks off — is what separates teams that improve week over week from teams that just watch the numbers. ## The three metrics that matter most **Conversation rate —** The percentage of leads who engaged with your agent after first contact. If this is low, the problem is upstream — your audience targeting or ad creative isn't attracting the right people, or your agent's opening message isn't compelling enough. **MQL rate —** The percentage of conversations that resulted in a 4★ fully qualified lead. If this is low but your conversation rate is healthy, the problem is in your agent's prompt or qualification criteria — not your traffic. **SQL rate —** The percentage of conversations that reached 5★ by becoming fully qualified and confirming a Sales meeting. This is your highest-intent segment — the leads your sales team should prioritize above everything else. ## How to diagnose a performance problem Start by identifying where the drop-off is happening: **Drop in conversation rate —** Is your agent online? Check Agent > General > Settings for AGENT ONLINE status. Is your WhatsApp number healthy? Check the Quality indicator in the status panel. Has your ad targeting changed recently? **Low MQL rate with healthy conversation rate —** Review your agent's prompt — are the qualification questions clear and direct? Check your traffic sources in Leads > Attribution. Review conversations where leads dropped off — what caused them to disengage? **MQL rate is healthy but SQL rate is low —** Your agent is qualifying leads but not confirming enough Sales meetings. Review your agent's conversation flow and contact the Patagon AI team at to review your qualification criteria. ## Week over week tracking The most useful thing you can do with your metrics is track them consistently week over week. A single week's data doesn't tell you much — the trend over 4 to 8 weeks does. Questions to ask every week: * Did my conversation rate go up or down vs. last week? * Did my MQL rate change after my last prompt update? * Which traffic source improved or dropped in High Quality Conv. Rate? * Did I give enough feedback to my agent this week (at least 5 conversations)? ## Using Performance Dashboard alongside this The Performance Dashboard shows your conversion rate overlaid with agent version markers — so you can see directly whether a prompt change improved or hurt performance. Use it in combination with the Leads Dashboard to separate agent problems from traffic problems. See How to read your Performance Dashboard in the Agent Optimization section. --- # Agent Instructions This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com. ## Querying This Documentation If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question. Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter: ``` GET https://docs.patagon.ai/en/sales-performance/benchmarks.md?ask=&goal= ``` `ask` is the immediate question: it should be specific, self-contained, and written in natural language. `goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal. The response will contain a direct answer to the question and relevant excerpts and sources from the documentation. Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.