# Core concepts

## **Overview**

AI Autopilot is a self-service product within the IFS Loops platform designed for high-volume support environments. It handles customer-initiated support interactions by detecting intent, attempting resolution, and escalating to a human agent when needed. The goal is consistent resolution quality across every interaction — not just volume deflection.

## **How it works**

When a customer initiates a support interaction, AI Autopilot analyzes their message to identify intent. It then draws on historical resolution data and connected knowledge sources to generate a situation-aware response. If the issue cannot be resolved automatically, AI Autopilot creates a structured support ticket — populated with a summary, labels, chat history, and full interaction context — and hands it off to a human agent. The customer does not need to repeat themselves, and the agent does not start from scratch.

AI Autopilot learns continuously. Each resolved interaction contributes to its knowledge base, improving response accuracy and reducing gaps over time.

## **Key features**

**Smart Resolution Suggestions** 

AI Autopilot generates responses using historical resolution data and contextual knowledge rather than scripted decision trees. This allows it to handle real-world complexity and variation in how customers describe their issues.

**Customer Ticket History Awareness** 

The product retains awareness of a customer's prior interactions. When a returning customer contacts support, AI Autopilot factors in that history, so customers do not need to re-explain context and agents receive a complete picture if the issue escalates.

**Seamless Ticket Creation and Handoff** 

When a conversation requires human intervention, AI Autopilot automatically generates a support ticket containing a case summary, relevant labels, the full chat history, and interaction context. This ensures agents can engage immediately without requiring the customer to restate their issue.

**Dynamic Status Updates** 

Customers can request status updates or request case closure directly through the self-service interface. These updates are handled automatically, without requiring a human follow-up.

**Knowledge Generation** 

AI Autopilot identifies gaps in existing knowledge based on unresolved or recurring cases. It uses these signals to surface opportunities for knowledge base improvement, keeping self-service content current and relevant.

**CX Signals** 

AI Autopilot includes quality and experience safeguards that monitor response accuracy and flag issues without overstating the system's autonomy.

## **Supported integrations**

AI Autopilot connects with CRM, ticketing, knowledge, and collaboration tools across 65+ enterprise platforms, including Zendesk, ServiceNow, Salesforce, Intercom, Jira, Slack, Microsoft Teams, HubSpot, Datadog, Notion, Google Drive, and others.

## **Auto QA Analyst in context**

Auto QA Analyst can be used alongside AI Autopilot to monitor self-service response quality, detect drift or hallucinations, and enforce quality standards across automated interactions.


---

# 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/ai-autopilot/core-concepts.md?ask=<question>
```

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.