AWS connect documentation change
Summary
Minor editorial updates replacing words like 'leverage' with 'use', 'click' with 'choose', and 'utilize' with 'use' for consistency. No technical content changes.
Security assessment
Changes are purely editorial word substitutions without any security context. No vulnerabilities, security features, or security implications are mentioned or modified.
Diff
diff --git a/connect/latest/adminguide/customer-segments-ai-assistant.md b/connect/latest/adminguide/customer-segments-ai-assistant.md index ca2b50085..64234431e 100644 --- a//connect/latest/adminguide/customer-segments-ai-assistant.md +++ b//connect/latest/adminguide/customer-segments-ai-assistant.md @@ -11 +11 @@ Inspiration Cards for Segment CreationGenerate a segment by promptProvide feedba -Connect Customer Customer Profiles supports generative AI-powered segmentation, enabling non-technical business users to build audiences using natural language queries (segment AI assistant), and to receive recommendations based on trends in the customer data (inspiration cards for segment creation). These capabilities leverage advanced AI algorithms from [Amazon Bedrock](https://aws.amazon.com/bedrock/) that help you improve customer satisfaction and drive revenue through proactive and personalized outreach. For example, you can create a segment of customers who reached out to customer support frequently last week with personalized service offers. You can also identify customers whose total spending increased and offer personalized discounts, fostering loyalty and also driving growth. +Connect Customer Customer Profiles supports generative AI-powered segmentation, enabling non-technical business users to build audiences using natural language queries (segment AI assistant), and to receive recommendations based on trends in the customer data (inspiration cards for segment creation). These capabilities use advanced AI algorithms from [Amazon Bedrock](https://aws.amazon.com/bedrock/) that help you improve customer satisfaction and drive revenue through proactive and personalized outreach. For example, you can create a segment of customers who reached out to customer support frequently last week with personalized service offers. You can also identify customers whose total spending increased and offer personalized discounts, fostering loyalty and also driving growth. @@ -59 +59 @@ The trend data is based on event ingestion dates of default calculated attribute - * **Insight-based recommendations** : Leverage historical trends, data insights and generative AI to create meaningful, actionable insights. + * **Insight-based recommendations** : Use historical trends, data insights and generative AI to create meaningful, actionable insights. @@ -148 +148 @@ The feedback process consists of two stages: - 1. **Initial reaction** : In the bottom right corner of the alert section, you'll find thumbs up and thumbs down icons. Click on either of these to indicate your general satisfaction with the generated segment. + 1. **Initial reaction** : In the bottom right corner of the alert section, you'll find thumbs up and thumbs down icons. Choose on either of these to indicate your general satisfaction with the generated segment. @@ -219 +219 @@ Understanding the data processing lifecycle is crucial for effective use of the -**Data processing and quality impact:** Segment AI assistant evolves through two main phases: initial data ingestion and post-processing. During initial ingestion, the system may not fully utilize actual attribute values, relying more on prompt interpretation. For example, a prompt for _VIP customers_ might suggest a _VIP_ segment instead of using the existing _Gold_ tier from your data. After complete processing, the system leverages actual attribute values, resulting in more accurate segment creation, reduces reliance on prompt interpretation and improves overall segmentation quality. +**Data processing and quality impact:** Segment AI assistant evolves through two main phases: initial data ingestion and post-processing. During initial ingestion, the system may not fully use actual attribute values, relying more on prompt interpretation. For example, a prompt for _VIP customers_ might suggest a _VIP_ segment instead of using the existing _Gold_ tier from your data. After complete processing, the system uses actual attribute values, resulting in more accurate segment creation, reduces reliance on prompt interpretation and improves overall segmentation quality.