# Core Concepts

## **Overview**

Agent Assist Copilot is an AI-powered support tool within the IFS Loops platform that surfaces contextual information and recommended actions to agents while they are working a case. Rather than replacing agent judgment, it reduces the time agents spend searching for information, summarizing history, and locating resolution paths — so they can focus on resolving the customer's issue.

Agent Assist Copilot is designed to work inside the platforms agents already use, consolidating information from multiple enterprise systems into a single view without requiring agents to switch between tabs or tools.

## **How It Works**

Agent Assist Copilot connects to multiple knowledge sources across the enterprise — including historical cases, knowledge articles, documentation, bug escalations, community content, email, and surveys — and feeds them into the Loops Insight Engine. The Insight Engine processes this data through a Customer Engagement Graph and Resolution Engine to surface summaries, suggested resolutions, and case intelligence directly within the agent's workspace. The Copilot surfaces outputs within the platforms agents already work in, including Zendesk, ServiceNow, Salesforce, Intercom, and Jira.

## **Key Features**

**Summarization** 

Agent Assist Copilot generates intent and timeline summaries for active cases, updated with each new interaction. When a case is closed, it also produces resolution notes capturing what was done and how the issue was resolved. This allows agents to get up to speed on ongoing cases quickly and creates a documented record at closure.

**Suggested Resolution** 

The Copilot provides a consolidated resolution view drawn from historical cases, knowledge articles, documentation, bug escalations, and community sources. Agents can review the suggested resolution and respond to the customer or close the case with a single action. Suggestions reflect multiple knowledge sources simultaneously rather than pulling from a single system of record.

**Knowledge Generation** 

Agent Assist Copilot uses the KCS (Knowledge-Centered Service) framework to draft knowledge articles from multiple sources each time a case is closed. This keeps the knowledge base current and reduces knowledge gaps over time by capturing resolution information continuously rather than through manual authoring.

**ASK** 

ASK is a conversational interface that lets agents query knowledge across connected repositories using natural language. Rather than navigating to a separate knowledge base and running structured searches, agents can ask questions in plain language and receive answers drawn from all connected sources.

**Continuously Learn** 

Agents can provide feedback on Copilot outputs by marking suggestions as helpful or unhelpful, and by selecting from categorized feedback options such as inaccurate summary or not helpful. This feedback is used to improve model outputs over time. Agents can also add free-text comments for more specific improvement input.

## **Supported Integrations**

Agent Assist Copilot integrates with Zendesk, ServiceNow, Salesforce, Intercom, Jira, and connects across 65+ enterprise tools including CRM, ticketing, knowledge, collaboration, and community platforms.

## **Agent Assist Copilot in Context**

Auto QA Analyst can be used alongside Agent Assist Copilot to evaluate agent interactions, identify coaching opportunities, and maintain consistent quality standards across the support team.


---

# 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/agent-assist-copilot/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.