SmartCS AI™
SmartCS AI™ contains 5 features that leverage AI technology to summarize your NPS comments, Pulse, and Engagement notes, in addition to creating personalized emails and analyzing customer segments by ask the data any question you would like.
NPS Analyzer - Summary of all NPS comments, or individual campaigns
Pulse™ Summary - Summary of Pulse notes across your customer base
Engagement Insights - Summarize Engagement notes and post to Pulse™
Email Assist - Create personalized, intelligent 1:Many Emails using AI-driven SmartCS AI™
Customer Segment Analyzer - Analyze segments on the Customer Grid by asking any question
1. NPS Analyzer - The SmartCS AI™ button in the NPS Dashboard will analyze the comments from all or individual NPS Campaign's. The filters can be selected to analyze a more granular dataset to find unique insights across the customer experience survey responses. The NPS Analyzer returns up to the Top 5 things customers like about your company, and the Top 5 areas of recommended improvements based on NPS feedback.
2. Pulse™ Summary - The SmartCS AI™ button in the Current Pulse Health report will perform a summary analysis on your Pulse notes. The filters can be selected to analyze your customer Pulse notes by Customer Type, Assigned To, and Region just to name a few.
When you click on SmartCS AI™, a real-time AI analysis is kicked off to summarize the Pulse notes. Once the analysis is completed, a report will be displayed with the Top 5 things that are going well with your customers, and a recommendation of the Top 5 areas of improvement. At that point you can either download the report or email it to someone on your team.
Note: A weekly Pulse™ Summary can be automatically sent to your Inbox each week by enabling it in My Settings.
Below is an example of the Weekly Pulse Summary email that will be delivered to your Inbox.
3. Engagement Insights - A SmartCS AI™ button will appear in the Engagement App when you create a Call or Meeting Engagement.
After completing your rough notes, select SmartCS AI™ to have your Engagement notes summarized in real-time, and automatically paste them directly into Pulse Notes and Next Steps. From there you can make any changes or simply hit Update Pulse with the previous Pulse, Risk Factors and SuccessFactors are already pre-selected to streamline the workflow.
4. Email Assist - The SmartCS AI™ button in the 1:Many New Email screen will help you create new personalized, intelligent emails using SmartCS AI™.
When creating a new 1:Many Email, click on SmartCS AI™ and you are presented with a modal where you can enter a prompt or question in addition to any email content that you would like to leverage to create the email.
Once the email is generated, the subject and content will be automatically populated into the New Email modal so you can make any small edits or send away.
5. Customer Segment Analyzer - Users now have the ability to create a segmented view on the Customer Grid and then ask the data any question/prompt and receive an AI-generated response.
When you click on SmartCS AI™, a modal will appear where you can select up to 5 columns of data from the grid you want to analyze, and ask the data any question you wish by entering in a prompt/question. SmartCS AI™ will then generate an intelligent analysis of the selected data set and provide an AI-generated response.
Multiple prompts/questions can be submitted simultaneously to provide a comprehensive analysis of the data. Users will also have the ability to save the prompts for future use with other customer segmented data sets from the grid.
Follow-up Question Prompt
A follow-up question prompt has been added to the SmartCS AI™ Prompt screen where users can ask the data a second question to refine the AI analysis response.
Clear The Template and Ask Your Own Question
If you would like to clear the template and ask your own question, click on the X in the "Saved Prompts" drop-down and the template will be cleared and you can start from scratch.
Once you click on the X, the template is cleared for you to use.
Pro Tip
If you run a SmartCS AI™ analysis and get the warning message "The selected data set is too large", remove one of the Selected Data Columns or reduce the customer segment size in the Customer Grid and try it again.
Note: Some very large comprehensive data sets have too large of a payload for the AI engine to handle, so we have limited the number of data columns to be analyzed to 10 until we can remove that limit, which should be in the near future.
Pro Tip #2
If you run a SmartCS AI™ analysis and get the warning message below, remove one or more of the Selected Data Columns or reduce the customer segment size in the Customer Grid and try it again. Usually in this case, we are sending the AI engine large amounts of data and this error may appear based on the size of the data set.
We're committed to continue to improve our prompt engineering and our SmartCS AI™ engine in Beta to remove these types of limits in a future phase of the product.
Getting Started with the SmartCS AI™ and The Consent Form
We require all customers who wish to use SmartCS AI™ to accept to an in-app user agreement on behalf of the organization they represent. This agreement will acknowledge the risks of using AI in general and Amazon's Bedrock APIs. A ClientSuccess Admin from your company or organization will need to go into the Global Settings>Apps and Integrations Page and toggle the SmartCS AI™ Beta feature on. The Consent Form will then popup and require the acknowledgment to be submitted before any SmartCS AI™ capabilities will be available for use.
After enabling SmartCS AI™, the Admin will need to type in their name and submit the SmartCS AI™ Consent Form to enable the SmartCS AI™ features.
Once SmartCS AI™ is enabled, the features will be visible in the respective ares of the platform with the new SmartCS AI™ button below.
Once SmartCS AI™ is enabled, the features will be visible in the respective ares of the platform.
When you hover over any SmartCS AI™ button, a popup will display with the details of the SmartCS AI™ analysis and potential results based on the data being analyzed.When you hover over any SmartCS AI™ button, a popup will display with the details of the SmartCS AI™ analysis and potential results based on the data being analyzed.
FAQ's/Security Information
Is SmartCS AI™ developed in-house or supplied by a third party?
Answer: SmartCS AI™ leverages the Amazon Bedrock AI engine and Anthropic's Claude models. The SmartCS AI™ features and product experience are built and maintained by ClientSuccess.
What type of AI or LLM models are used?
Answer: SmartCS AI™ uses Anthropic Claude's large language models (LLMs), accessed via Amazon Bedrock, to power its analysis and summarization capabilities.
Is customer data used to train or fine-tune models?
Answer: No. Customer data is never used to train or fine-tune any AI models.
Is the content processed by Amazon Bedrock moved outside the AWS Region where I am using Amazon Bedrock?
Answer: No. Any customer content processed by Amazon Bedrock is encrypted and stored at rest in the AWS Region where you are using Amazon Bedrock.
Are user inputs and model outputs made available to third-party model providers?
Answer: No. User inputs and model outputs are not shared with any model providers.
What security and compliance standards does Amazon Bedrock support?
Answer: Amazon Bedrock offers several capabilities to support security and privacy requirements. Bedrock is in scope for common compliance standards such as Service and Organization Control (SOC), International Organization for Standardization (ISO), Health Insurance Portability and Accountability Act (HIPAA) eligible, and customers can use Bedrock in compliance with the General Data Protection Regulation (GDPR). Amazon Bedrock is included in the scope of the SOC 1, 2, 3 reports, allowing customers to gain insights into our security controls. We demonstrate compliance through extensive third-party audits of our AWS controls. Amazon Bedrock is one of the AWS services under ISO Compliance for the ISO 9001, ISO 27001, ISO 27017, ISO 27018, ISO 27701, ISO 22301, and ISO 20000 standards. Amazon Bedrock is CSA Security Trust Assurance and Risk (STAR) Level 2 certified, which validates the use of best practices and the security posture of AWS cloud offerings. With Amazon Bedrock, your content is not used to improve the base models and is not shared with any model providers. You can use AWS PrivateLink to establish private connectivity from your Amazon Virtual Private Cloud (VPC) to Amazon Bedrock, without having to expose your data to internet traffic.
Will AWS and third-party model providers use customer inputs to or outputs from Amazon Bedrock to train Amazon Titan or any third-party models?
Answer: No. AWS and third-party model providers will not use any inputs to or outputs from Bedrock to train Amazon Titan or any third-party models.
Does the software tag or label its sourced information?
Answer: No.
How do you identify and/or manage security-related incidents impacting your AI systems?
Answer: We use logging to track AI usage and can swap between models and providers if needed (e.g., in the event of a provider or model being flagged for security issues). AWS also provides assurance in their Terms of Service that the Bedrock platform is secure.
How does the team mitigate AI hallucinations?
Answer: Through comprehensive and continuously improved prompt engineering. This is an area we are always actively working to improve.
What type of data is being collected for analysis?
Answer: The data analyzed by SmartCS AI™ is the data you and your team have entered into ClientSuccess - such as customer grid data, Pulse notes, NPS responses, and Engagement notes. Nothing beyond what exists in your ClientSuccess environment is collected or used.
What input or output data around SmartCS AI™ is stored?
Answer: For standard SmartCS AI™ features (NPS Analyzer, Pulse Summary, Engagement Insights, Email Assist, Customer Segment Analyzer), there is no permanent storage of AI inputs or outputs. Some information is held in-memory by the LLM for context during a session, but nothing is persisted beyond that. Note: Meeting Intelligence works differently - see the Meeting Intelligence section below for details on what data is stored in that context.
Where is input or output data around SmartCS AI™ stored?
Answer: For standard SmartCS AI™ features, data is not stored. See the note above and the Meeting Intelligence section below for the exception that applies to meeting transcripts and summaries.
Meeting Intelligence and Recall.ai
What is Meeting Intelligence?
Answer: Meeting Intelligence is a sub-feature of SmartCS AI™ that enables an AI-powered bot to join, record, and transcribe customer meetings, then automatically generate a meeting summary, action items, and follow-up tasks directly within ClientSuccess. It is available as a separate, additional opt-in on top of SmartCS AI™.
What is Recall.ai and how is it used?
Answer:
Recall.aiis a third-party product that powers the meeting recording and transcription component of Meeting Intelligence. When a meeting bot is deployed,Recall.aijoins the meeting and captures the audio and video, then produces a transcript. That transcript is then passed to SmartCS AI™ (Amazon Bedrock) for summarization and action item generation.Recall.aitemporarily retains meeting data for 14 days, after which it is automatically and permanently deleted from their systems. ClientSuccess stores only the transcript and AI-generated meeting content (summary, action items) - no audio or video is stored in ClientSuccess.
Does Meeting Intelligence use SmartCS AI™ / Amazon Bedrock?
Answer: Yes. Once
Recall.aiproduces the transcript, Meeting Intelligence uses the SmartCS AI™ engine (Amazon Bedrock) to generate the meeting summary, action items, and follow-up content. The same data handling standards apply: no data is used for model training, and no AI queries or responses are stored.
Is Meeting Intelligence opt-in?
Answer: Yes. Meeting Intelligence requires multiple explicit opt-ins before any recording will occur. At the tenant level, SmartCS AI™ must be enabled and the consent form completed, and Meeting Intelligence must then be separately enabled by an Admin in Global Settings. At the individual level, each employee must enable meeting bots in their personal settings, connect their calendar, and have a supported meeting platform enabled. The bot will only join a calendar event that contains a meeting link and includes at least one external client contact email. It will never join internal-only meetings. If any of these conditions are not met, no recording will occur and no data will be sent to
Recall.ai.
What data does Recall.ai have access to?
Answer: When a meeting is recorded via Meeting Intelligence,
Recall.aiprocesses and temporarily retains the following data for up to 14 days: the meeting URL, recorded audio, recorded video, participant display names, and chat messages.Recall.aidoes not have access to participant email addresses or any other data from the ClientSuccess platform. Participant emails are sourced by ClientSuccess separately through your connected calendar integration.
What data does ClientSuccess store from Meeting Intelligence?
Answer: ClientSuccess stores the meeting transcript and the AI-generated meeting summary and action items. No audio or video files are stored in ClientSuccess. This data is retained in ClientSuccess in accordance with ClientSuccess's standard data retention policies (e.g., upon account or tenant offboarding).
Does Recall.ai train AI models on customer meeting data?
Answer: No.
Recall.aidoes not use customer data to train AI models, and does not sell customer data to any third parties.
What compliance certifications does Recall.ai hold?
Answer:
Recall.aiis SOC 2 Type 2 certified, ISO 27001 certified, HIPAA compliant, and GDPR compliant. ClientSuccess maintains a Data Processing Agreement (DPA) withRecall.ai.
For more information on Amazon Bedrock AI, please refer to the Amazon Bedrock FAQ.
For more information about Recall.ai 's data retention policies, refer to: Storage and Data Retention
Please reach out to your CSM or our Support Team with any additional questions.