# Core Concepts {% embed url="" %} ## **Overview** Auto QA Analyst is a quality assurance product within the IFS Loops platform that evaluates support interactions — both agent-handled and bot-handled — against configurable quality standards. It automates the scoring and review process across all resolved tickets, and includes a built-in manual QA path for cases that require human evaluation. The result is complete QA coverage without requiring a proportional increase in QA staffing. ## **How It Works** Auto QA Analyst evaluates resolved tickets using customizable Rubrics — sets of quality indicators that assess dimensions such as service quality, accuracy, and procedure adherence. The system scores each ticket automatically and generates insights that surface patterns across interactions. Manual QA workflows are also available for QA administrators who need to review specific cases, run calibration sessions, or audit reviewer consistency. Role-based access controls govern what each user can see and do within the platform, ensuring appropriate separation between agents, reviewers, managers, and QA specialists. ## **Key Features** **Auto QA** The automated QA engine scores resolved tickets against configurable Rubrics without requiring manual intervention for each case. Scores and insights are generated in real time, enabling immediate feedback delivery and pattern detection across large interaction volumes. Rubrics can be customized to reflect the specific quality standards of the support organization. **Manual QA** Auto QA Analyst includes a full manual QA path for cases that require human review. QA administrators can select cases for manual review either randomly through automated sampling or by direct selection. Manual reviews feed back into the automated system, improving scoring accuracy over time. Key manual QA capabilities include random case selection based on configurable criteria, calibration sessions where reviewers assess the same cases to align on standards, and reviewer auditing through secondary reviews that check evaluation consistency. **Dispute Management** Agents can formally challenge QA scores through a structured dispute process. Disputes follow a documented path that includes initiation, collaborative resolution between the agent and reviewer, and an escalation path to higher management for cases that cannot be resolved between the two parties. All steps are tracked and documented within the platform. **Agent Coaching** Auto QA Analyst includes a coaching module that allows supervisors and QA managers to translate quality scores into targeted development plans. The module supports performance tracking, customized training plans, session scheduling, and progress monitoring over time. Coaching sessions are grounded in rubric-based performance data rather than subjective observation. **Role-Based Dashboards and Reporting** Each user role has access to a dashboard configured for their responsibilities. Dashboards surface relevant quality metrics, performance data, and reporting tools based on the user's role — so agents see their own performance data, managers see team-level trends, and QA specialists see evaluation queues and calibration tools. **Roles-Based Access Controls** Administrators control access to QA data and platform features at the user level. The permissions system enforces appropriate separation of duties across reviewers, managers, agents, and QA specialists, ensuring users can only access the data and tools relevant to their role. ## **Supported Integrations** Auto QA Analyst connects with CRM, ticketing, knowledge, collaboration, and 65+ enterprise tools, including Zendesk, ServiceNow, Salesforce, Slack, Microsoft Teams, HubSpot, Datadog, Notion, Google Drive, and others. ## **Auto QA Analyst in Context** Auto QA Analyst is designed to work alongside both AI Autopilot and Agent Assist Copilot. When used with AI Autopilot, it monitors self-service response quality and flags drift or inaccuracies in automated interactions. When used with Agent Assist Copilot, it evaluates agent interactions and supports coaching workflows. --- # Agent Instructions: 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: ``` GET https://kb.theloops.io/cxplatform/ifs-loops-cx-platform/auto-qa-analyst/core-concepts.md?ask= ``` The question should be specific, self-contained, and written in natural language. 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.