> For the complete documentation index, see [llms.txt](https://www.kauneonga.com/docs/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://www.kauneonga.com/docs/ai/quality-assurance-ai/quality-assurance-ai.md). # Quality Assurance AI How Liberty uses AI to support interaction review, coaching, and quality visibility. Quality Assurance AI helps supervisors review more interactions with greater consistency. It supports coaching, quality monitoring, and operational visibility across agents, accounts, and teams. {% hint style="info" %} If Quality Assurance AI is disabled, contact your account manager or email to request access. {% endhint %} ### What Quality Assurance AI supports Quality-focused AI workflows can help teams: * identify coaching opportunities * spot process issues faster * review more interactions with less manual effort * surface patterns across agents and accounts * move from isolated reviews to more consistent oversight ### How teams use QA AI Quality Assurance AI is built for supervisors, managers, and QA leaders who need faster visibility into interaction quality. It is especially useful in high-volume answering service environments where manual review alone does not scale. ### Overview tab The **Overview** view helps supervisors understand quality trends at a higher level. It is useful for spotting patterns across the broader operation before drilling into specific agents or interactions. Common uses include: * reviewing company-wide or team-level trends * comparing performance across agents * identifying outliers that may need follow-up * finding recurring workflow or scripting issues ![QA AI Company Leaderboard and Overview](https://3668331061-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FcvVWNsbzvWkRa4x8QSwZ%2Fuploads%2FKDgO9DpcM8ITGfzfVzUs%2FScreenshot%202026-04-15%20at%2011.09.59%E2%80%AFAM.png?alt=media\&token=1896f27d-1a82-4d9e-b1ab-f17d1852c046) ### What the Overview tab helps answer Supervisors can use the Overview view to answer questions like: * Where is quality improving or slipping? * Which agents or teams need closer review? * Are there common process issues across accounts? * Where should coaching time be focused first? ### Agents tab The **Agents** view shifts from broad trends to individual performance. It helps supervisors review agent-specific results in a more structured way. This is useful when teams need: * a clearer view of individual performance * better coaching follow-up * easier tracking of trends over time * more consistency in review conversations ![QA AI Agent Report Card](https://3668331061-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FcvVWNsbzvWkRa4x8QSwZ%2Fuploads%2FhgBFwl86B8ORaU8ezAoH%2FScreenshot%202026-04-15%20at%2011.10.19%E2%80%AFAM.png?alt=media\&token=378fb209-b080-42f5-976c-b0d4de6a2c1b) ### What the Agents tab helps answer Supervisors can use the Agents view to answer questions like: * Which agents need coaching right now? * Are the same issues repeating for the same agent? * Is performance improving after feedback? * Which agents may be ready for added responsibility? ### Message and call analysis Quality Assurance AI can support summarized review of message and call activity. This helps supervisors triage large interaction volume more efficiently. It is useful when teams need to move quickly from broad QA visibility into specific examples. Common uses include: * reviewing summarized message activity * reviewing summarized call activity * finding interactions that deserve manual follow-up * identifying patterns that may affect service quality or client consistency ![QA AI Message and Call Analysis](https://3668331061-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FcvVWNsbzvWkRa4x8QSwZ%2Fuploads%2FtBqDVMBJchhjTQoQkvgW%2FScreenshot_2026-04-15_at_11_16_18%E2%80%AFAM.png?alt=media\&token=2cba7ae8-808b-408a-87ea-6af50b22f839) ### Why this matters operationally QA AI helps answering services scale supervision without relying only on random spot checks. It gives leaders a faster way to review performance, identify trends, and support more consistent service delivery. Operational benefits include: * faster identification of coaching needs * better visibility across agents and teams * more consistent QA follow-up * improved control across multi-client operations ### A practical QA workflow A common QA workflow looks like this: 1. Start in the **Overview** view to identify patterns. 2. Move to the **Agents** view to review individual performance. 3. Open message and call analysis to inspect specific interactions. 4. Use those findings to guide coaching and operational follow-up. ### Where it fits best Quality Assurance AI works best when teams need: * more consistent QA review * broader visibility into interaction quality * faster identification of coaching themes * scalable review across multi-client operations ### Implementation guidance Strong results usually depend on: * clear QA criteria * defined coaching workflows * regular supervisor follow-up * consistent scripting and operational standards * enough review cadence to turn findings into action --- # 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 by asking a question. Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters: ``` GET https://www.kauneonga.com/docs/ai/quality-assurance-ai/quality-assurance-ai.md?ask=&goal= ``` `ask` is the immediate question: it should be specific, self-contained, and written in natural language. `goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case. 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.