---
schema_version: "1"
id: e16f2d3d9d79af26a69bfbb9e03419b65872e02e2bda7618e51c32c89dfdb620
title: Engagement
collection: admin
version: current
locale: en-us
portal_url: https://docs.salesforce.com/admin/current/en-us/release-notes/260-0-0/rn_engagement.md
canonical_url: https://help.salesforce.com/s/articleView?id=release-notes.rn_engagement.htm&release=260&type=5
source_site: help.salesforce.com
content_type: documentation
content_hash: cf7fceff988e878da0ca8894cc81ec08870694fd9b9f4355c211803baa8093f5
description: Users access AI-driven insights on their home page with the Einstein Quick Insights component. The Salesforce Context Service provides more comprehensive, relevant insights by accessing a broader set of data. Additionally, users improve efficiency with Retained Output, which keeps the last run prompt and its output after a page refresh.
products:
  - Cross Cloud Packages Solutions
release: "260"
---
# Engagement

Users access AI-driven insights on their home page with the Einstein Quick Insights component. The Salesforce Context Service provides more comprehensive, relevant insights by accessing a broader set of data. Additionally, users improve efficiency with Retained Output, which keeps the last run prompt and its output after a page refresh.

- **[Enhance AI Summaries with Multimodal Inputs](https://help.salesforce.com/s/articleView?id=release-notes.rn_engagement_empower_embeded_ai_with_custom_flex_templates.htm&release=260&type=5)**  
    Customize your embedded AI experience by using flex prompt templates that take multiple inputs. Create prompts grounded in multiple objects, text, or files, including PDFs, images, and text documents, directly on the component's UI. Generate more powerful, multimodal insights, eliminating inefficient manual workflows and increasing the accuracy of AI-generated summaries.
- **[Optimize Sorting and Filtering of Prompt Data with Context Service](https://help.salesforce.com/s/articleView?id=release-notes.rn_engagement_integrate_context_service_filters.htm&release=260&type=5)**  
    Improve the reliability of AI-generated summary ranking and prioritization. Use Context Service design time filters to ensure consistent results for your context-driven prompts. Get reliable results by removing the need for the Large Language Model (LLM) to handle sorting and filtering.