Home AI Features and Tools

AI Features and Tools

Discover how to customize AI behavior in HostedSuite, including setting up personalized greetings, configuring call transfer rules, and adjusting preferences to enhance customer interactions and streamline workflows.
By Richie
• 14 articles

Customizing AI Behavior: Greetings, Transfers, and Preferences

Customizing AI Features Overview Learn how to configure and maximize the AI functionalities in HostedSuite, including setting custom greetings, transfer preferences, tuning AI responses, and leveraging contact alerts and statuses. Customizing AI Greetings Tailor AI-generated greetings to suit business needs, such as special event announcements or temporary service updates. Default vs. Custom Greetings - Default: Uses the standard greeting found in the General tab if "Override Company Greeting" is left blank. - Override: Enables customized greetings for specific scenarios like holidays or temporary service disruptions. Examples: - Default Greeting: - "Hello, and thank you for calling Evo Tech. Our office hours are Monday through Friday from 9 AM to 5 PM. For inquiries, please stay on the line." - Custom Greeting: - "Thank you for calling Evo Tech. Our office will be closed for Thanksgiving from November 28th to 29th. For urgent matters, email [email protected]. Thank you!" How to Set a Custom Greeting 1. Navigate to the AI tab. 2. Locate the Override Company Greeting field. 3. Enter the desired custom greeting. 4. Click Save. 5. To revert, clear the "Override Company Greeting" field. Configuring AI Transfer Settings Define how the AI handles call transfers, ensuring efficiency and alignment with business needs. Transfer Type Options - None: Calls require manual staff intervention for transfer. - Blind Transfer: Directly connects the caller to the recipient without notice. - Supervised Transfer: AI verifies the recipient’s availability before transferring. - Messages Only: AI takes a message if the recipient is unavailable. - Human Value Transfer: Matches the transfer behavior of human operators. Steps to Set Transfer Preferences 1. Open the AI tab for the selected client. 2. Locate the Transfer Settings section. 3. Select the preferred transfer type. 4. Click Save. Tuning AI for Accuracy or Speed Optimize AI responses for either precision or speed, depending on the use case. Accuracy Mode - Utilizes advanced text-to-speech and speech-to-text capabilities for detailed and precise responses. - Recommended for scenarios requiring accurate information retrieval (e.g., knowledge base queries). Speed Mode - Focuses on faster response times by embedding key details directly into system prompts. - Best for scenarios prioritizing conversational flow and quick replies. How to Toggle Between Modes 1. Go to the Tuning Options section in the AI tab. 2. Select either Accuracy Mode or Speed Mode. 3. Save the changes. Include Contact and Contact Status Enable smarter call management by configuring alerts and statuses for contacts, improving AI's decision-making. Include Contact Alert - Stores short-term notifications (e.g., "Out sick today," "On vacation until [date]"). - Prevents unnecessary transfers by informing the AI of immediate unavailability. Include Contact Status - Sets long-term or recurring preferences (e.g., "Only available after 2 PM," "Send calls to mobile first"). - Guides AI on routing decisions based on defined rules. How to Enable Alerts and Status for AI 1. Navigate to the AI tab. 2. Open the General dropdown settings. 3. Check the boxes for Include Contact Alert and Include Contact Status. 4. Click Save. AI Integration - The AI reviews "Alert" and "Status" fields before making transfer decisions. For example: - "Sorry, I can't transfer your call. [Contact Name] is unavailable due to [reason]." - Fields are adaptable to unique business needs. Benefits - Improved Efficiency: Minimizes unnecessary call handling. - Enhanced Caller Experience: Provides clear and accurate responses. - Customizable: Aligns with specific operational requirements.

Last updated on Jan 21, 2025

Configuring the Information Feature for AI Responses

Information Feature Overview The "Information" feature allows companies to manage how AI accesses and utilizes company-specific data, ensuring accurate and efficient responses. Below is a breakdown of its functionality and use cases. Purpose The "Information" field stores company-related details separately from system instructions. This allows the AI to dynamically retrieve or embed relevant information when responding to queries, depending on the selected operational mode. Modes of Operation There are two primary modes that define how the AI uses the "Information" feature: Accuracy Mode and Speed Mode. You can find more details about these two modes here. Accuracy Mode In this mode, the AI does not directly embed information. Instead, it retrieves relevant data from the "Information" field when responding to specific queries. - Benefits: - Ensures highly accurate, up-to-date responses. - Ideal for precise transcription and detailed responses. - Trade-offs: - There may be a slight delay in responses due to the need to fetch information dynamically. Speed Mode In this mode, all information from the "Information" field is directly embedded into the system prompt. - Benefits: - Faster response times as no tool call is needed. - Best for scenarios requiring quick replies. - Trade-offs: - Slightly less accurate due to the lack of dynamic information retrieval. How It Works 1. AI Settings: Choose AI Settings from the Source dropdown to enable the use of the "Information" field. When selected, the data from the "Information" and "Keywords" input fields will be used by the AI for relevant queries. Otherwise, use Normal Selection to refer to the information tab. 1. Keywords Field: This field determines when the AI should use the "Information" box. By identifying specific keywords, the AI can retrieve relevant data and provide accurate responses based on the stored information. 1. Response Process: - In Accuracy Mode: The AI identifies the relevant keywords, fetches the data from the "Information" field, and delivers a precise response. - In Speed Mode: The AI uses pre-embedded information for instant replies. Use Cases Accuracy Mode - Best for: Critical responses such as legal, technical, or complex inquiries. - Recommended: When the "Information" field contains detailed or frequently updated content. Speed Mode - Best for: High-volume customer interactions requiring quick replies. - Recommended: When the content in the "Information" field is static or simple. Additional Features - Efficient Processing: Both modes support fast speech-to-text and text-to-speech processing for effective query handling. - Flexibility: Businesses can prioritize between accuracy and speed, depending on their operational needs. By leveraging the "Information" feature effectively, businesses can ensure tailored, responsive, and accurate support, improving user satisfaction and overall productivity.

Last updated on Jan 21, 2025

Configuring Custom Pronunciations for AI Words and Phrases

Custom Words Feature Overview The "Custom Words" feature allows you to define specific pronunciations for words or phrases, ensuring the AI speaks them correctly and consistently. This feature is particularly useful for brand names, technical terms, or uncommon words that may not be pronounced as intended by default. How It Works The Custom Words feature enables you to provide phonetic spellings for words that need specific pronunciation. - When the AI encounters a word that requires a special pronunciation, you can supply a phonetic spelling to guide its speech. - Example: - If the AI incorrectly pronounces "Evo" as "E-vo," you can define the pronunciation as "E E V O" to ensure it says "Evo" correctly. - Similarly, if "Live Answer" is mispronounced as "Live (like live TV) Answer," you can set the phonetic spelling as "L-Y-V-E Answer" to make the AI pronounce it as "Live (rhymes with hive) Answer." Benefits The Custom Words feature offers several key benefits: - Brand Consistency: Ensures correct pronunciation of brand names, fostering a professional image. - Improved Accuracy: Resolves pronunciation issues with industry-specific jargon or unique terms. - Enhanced User Experience: Delivers clearer, more natural-sounding interactions for end-users, improving overall communication. How to Set Up Custom Words 1. Identify Mispronunciations: Recognize the words or phrases the AI is pronouncing incorrectly. 2. Create Phonetic Spellings: Determine the correct pronunciation and write it out phonetically. 3. Add to Configuration: Enter the custom phonetic spellings in the "Custom Words" configuration within your system. By utilizing the Custom Words feature, you can fine-tune the AI’s pronunciation to ensure that it aligns with your communication requirements.

Last updated on Jan 21, 2025

How to Enable AI Scheduling

The AI scheduling feature integrates with your calendar system to streamline appointment management. However, enabling this feature depends on your workflow preferences and setup requirements. Below is a step-by-step guide on how to enable and use this functionality. Key Considerations Before Enabling AI Scheduling Before activating AI scheduling, it's important to consider the following options and potential conflicts: - Alternative Options: - If you prefer a simpler scheduling process, the AI can send an SMS message with a link to a calendar for manual scheduling. This avoids potential conflicts with pre-existing scheduling links in other sections of your system. - If this method is sufficient for your needs, enabling full AI scheduling may not be necessary. - Avoiding Conflicts: - Enabling AI scheduling while using SMS-based calendar links may result in conflicts. Review your current workflow to ensure compatibility before enabling this feature. How to Enable AI Scheduling Follow these steps to enable the AI scheduling feature: 1. Navigate to the Organization menu and open the client settings. 2. Click the AI tab and go to the "Scheduling" section. 3. Check the Enabled checkbox. 4. Click Save to apply the changes. How to Use AI Scheduling - Currently, calendars are available only within the Hostess Suite platform and can be used exclusively for booking meeting rooms. - This feature can be enabled on-demand, allowing you to book meeting rooms over the phone. For setup, please contact our tech support team to integrate this feature into your HostedSuite account. Integration with Google Calendar (Beta) - Beta Integration: A beta version of the Google Calendar integration is available for testing. To enable it, follow the steps below (admin privileges are required): 1. Go to the Settings menu and click Integrations. 2. Click the New Integration button. 3. Enter the integration name, select a center, and enter your admin email address. 4. Click Save, which will open the Google authorization page. 5. Authorize the integration by linking your Google account. - Limitations: - Calendar sync is limited to meeting rooms only. - Does not extend to forms or general scheduling tasks. - Additional features may be developed upon request from paying customers. Advantages of AI Scheduling The AI scheduling feature offers several benefits: - Direct Calendar Access: The AI can seamlessly view and book appointments, reducing manual effort. - Streamlined Workflow: Eliminates the need for manual scheduling links, improving efficiency. - Customizable Features: Future updates can be tailored based on user demand, offering more flexibility. By following the steps outlined above, you can enable AI scheduling and optimize appointment management for your business. For further assistance, please contact our support team.

Last updated on Jan 21, 2025

Configuring Customized Prompts for Tailored AI Interactions

How to Use the Customized Prompt Feature The "Customized Prompt" feature allows you to define specific behavioral instructions for the AI, tailoring its responses and interactions to better suit your unique requirements. This feature focuses on adjusting how the AI behaves during interactions and is distinct from custom information features. What Is a Customized Prompt? - Definition: A customized prompt is a set of instructions that guide how the AI should respond or behave in certain situations. - Purpose: Customized prompts help the AI align with your business needs or customer service guidelines by defining its behavior during interactions. - Important Note: - Custom prompts focus solely on behavior. - Custom information (such as facts or data) should be handled separately, in its dedicated section, to ensure proper functionality. Example Use Cases Here are some examples of how you might use customized prompts: - Confirming Customer Names: If you want the AI to confirm customer names during conversations, you could provide this instruction: - Instruction: "Anytime somebody gives you their name, repeat it back to them to make sure that you heard it correctly." - Offering Follow-Up Questions: If you'd like the AI to always offer a follow-up question after providing an answer, you can set this instruction: - Instruction: "After answering a question, ask the user if they need further assistance." How to Set Up a Customized Prompt Follow these steps to configure a customized prompt: 1. Access the Customized Prompt Section Navigate to the "Customized Prompt" dropdown in the AI section of your HostedSuite. 2. Enter Behavioral Instructions Type specific instructions for how the AI should behave. For example: - "Always greet the user with their first name if provided." - "Use a friendly tone and thank the user at the end of every conversation." 3. Avoid Adding Custom Information - Custom prompts should not contain factual or informational data. These belong in the Custom Information section. 4. Save and Test After entering the instructions, save your changes and test the AI's behavior to ensure the customized prompts are functioning as expected. Best Practices To get the most out of your customized prompts: - Be concise and specific: Ensure the prompts are clear and to the point to avoid confusion. - Review and update regularly: As your business needs evolve, review and adjust the prompts to align with any new requirements. - Keep behavior and information separate: Ensure that behavioral instructions (custom prompts) and factual data (custom information) are managed in their respective areas for optimal performance. By effectively using the Customized Prompt feature, you can customize the AI’s behavior to better meet your operational and customer service goals, resulting in more personalized and consistent interactions.

Last updated on Jan 21, 2025

How to Use the Knowledge Base Feature to Enhance AI Responses

Knowledge Base Feature The "Knowledge Base" feature allows the AI to access and retrieve information from various content sources, such as website pages, textual content, or other structured inputs. This enables the AI to deliver accurate and context-aware answers based on the most up-to-date information. Purpose The Knowledge Base feature connects the AI to your organization’s existing help desk resources, ensuring responses are informed by relevant and current information. This connection enhances the AI's ability to provide accurate answers based on your website or other provided sources. Key Features 1. Integration with Website Content The AI can crawl different content types, such as: - Sitemap: Add a sitemap URL for the AI to crawl your entire website, including the knowledge base homepage and all related pages. - Links: Provide specific URLs for the AI to crawl only those pages, with the option to add multiple links. - Text: Paste plain text, useful for information that may not be available on your knowledge base website. 2. Automated Scanning The AI scans the provided sources once a week for updates, ensuring the information remains current. Future updates may include configurable scan intervals. 3. Knowledge Base Status Check Use the "Check Status" feature to view the scanned pages, including all articles added to the AI’s database. This allows you to track what content is accessible. How to Add Your Site to the Knowledge Base 1. Access the Knowledge Base Section: - Open the Client AI tab. - Scroll down to the Knowledge Base section. 2. Choose a Content Type: - From the Type dropdown, select one of the following: - Sitemap URL: Allows full website crawling. - Specific Links: Crawls a single provided page. - Text Blocks: Add critical information manually if it's not available on your website. 3. Enter the Content: - Provide the URL or text in the Content section. 4. Verify Connection (Optional): - Click Check Status to ensure the AI can connect to the provided page. 5. Save Changes: - Click Save to apply your updates. How It Works 1. Provide Content Sources: Share a sitemap URL, specific links, or text blocks for the AI to access relevant information. 2. Automated Scanning: The AI scans these sources weekly to keep its knowledge updated. 3. Query Processing: For each question, the AI searches the knowledge base, retrieves relevant information, and provides an accurate response. Use Case Example - Scenario: A user asks, "How do I add a new number to Evo Voice?" - The AI will: 1. Search the knowledge base for articles about adding new numbers. 2. Retrieve the most relevant article. 3. Generate an accurate, context-aware response based on that article. Benefits - Up-to-Date Information - Ensures the AI always references the latest content available on your website or from other provided sources. - Streamlined Support - Reduces reliance on human intervention by allowing the AI to independently access detailed resources. - Comprehensive Answers - The AI combines information from multiple sources to provide well-rounded, accurate responses. Future Enhancements - Configurable Scan Intervals: Future updates will allow businesses to configure scan intervals, enabling more frequent or less frequent updates based on needs. - Enhanced Analytics: Upcoming features will provide analytics to track which knowledge base articles the AI uses most frequently, offering insights into user queries. By leveraging the Knowledge Base feature, businesses can ensure their AI delivers informed and consistent support, leading to improved user satisfaction and operational efficiency.

Last updated on Jan 22, 2025

Creating AI Insights Fields

Field types can be customized to provide an in-depth analysis of call quality and handling. These fields are crucial components of the analysis dashboard for Call Insights. Managing Fields Adding or Modifying Fields You can add, modify, or edit fields in Phones > Call Insights. For detailed instructions on creating new AI insights, refer to this documentation. Field Types These are the different types of input you can use for Call Insight items: - Number: Outputs a numerical value. - Text: Outputs plain text. - Range: Allows you to define a minimum and maximum value. - Enum: Provides a list of options; the list must be separated by commas. - Boolean: Outputs either true or false. Example Fields for Your Organization Below is a table of example fields that you can use to customize your Call Insights configuration: | Name | Type | Description | | --- | --- | --- | | Accurate Greeting Followed | Boolean | Determines whether the operator's greeting matches the transcript. | | Caller's Name Asked | Boolean | Checks if the operator asked for the caller's name at the start of the call. | | Caller's Name Used | Boolean | Verifies if the operator used the caller's name to address them. | | Professional Tone | Boolean | Assesses whether the operator maintained a friendly, professional tone. | | Rude | Boolean | Indicates if the operator was rude or sarcastic. | | Active Listening | Boolean | Checks if the operator demonstrated active listening skills. | | Paraphrasing | Boolean | Determines if the operator used paraphrasing to confirm the caller's intent. | | Vocalized Pauses | Number | Counts the number of vocalized pauses by the operator. | | Empathy | Boolean | Evaluates if the operator used empathetic language. | | Message Taking | Enum | Ensures the operator repeated back names, numbers, or key information. | | Call Transfer | Enum | Verifies if the operator checked contact availability before transferring. | | Hold Permission | Boolean | Checks if the operator asked for permission to place the caller on hold. | | Information Request | Enum | Ensures responses do not contradict the caller's questions. | | Resolved | Boolean | Confirms whether all caller requests were resolved. | | Profile Instructions Followed | Boolean | Assesses compliance with instructions in the information field. | | Call Ending | Boolean | Checks if the operator thanked the caller and used an appropriate closing. | | Overall Score | Range | Rates the operator's handling of the call on a scale of 0 to 100. | | Improvement | Text | Provides suggestions for improvement based on the call handling. | Use these field types and examples to create tailored insights that align with your organization’s priorities.

Last updated on Jan 27, 2025

Creating a New Call Insights Configuration

Overview Call Insights allows you to customize the data captured during a call, depending on your organization’s priorities for call quality and interaction with the caller. This guide will walk you through creating a new Call Insights configuration step-by-step. Step 1: Access the Call Insights Section 1. Navigate to the Phones section in the application. 2. Click on Call Insights. - This will display a list of all available Call Insights. 3. Click the New Call Insight button to create a new configuration. Step 2: Fill Out the General Information 1. In the General tab: - Enter a name for the new Call Insights configuration in the Name field. - Specify the Center that will utilize this configuration. - This is the name of the center where the insights will be applied. - Enter the Client Name (optional): - Leave this blank to apply the insights to all clients in the specified center. Step 3: Add Custom Fields 1. Navigate to the Fields section. 2. Click Add Field to start defining parameters you’d like to monitor. - Example: - Name: “Caller’s Name Asked” - Type: Boolean (returns a true or false output). - Description: Provide a prompt that describes the parameter. For example: - “The operator asked the caller for their name at the beginning of the call.” Notes: - The AI will use your descriptions and the field type to generate outputs in the reports. - For more details about different field types and example prompts, refer to this documentation. Step 4: Test the Insights 1. Upload a recording to test the new configuration: - Select a Client. - Choose a recording. - Click the Analyze button. By following these steps, you can successfully create and test a custom Call Insights configuration tailored to your organization’s needs..

Last updated on Jan 27, 2025

Understanding AI Reporting Options + Recommendations

You can export your AI Call Insights dashboard report to explore or use the data externally. The exported report includes aggregate data that is not available directly in the AI Insights dashboard, providing valuable high-level insights and summaries beyond what the dashboard view offers. For large datasets, consider using the spreadsheet (XLSX) or JSON format, especially if you have an API system to process the data. While the PDF format is ideal for summaries and compact reports, it may not be the best choice if your dashboard contains many fields. Spreadsheet and JSON formats offer greater flexibility for data manipulation and integration with other tools. How to Export the AI Insights Report 1. Click the "Reports" menu in your HostedSuite dashboard. 2. Click the "AI Call Insights Report". 3. Select the desired date range for the report. 4. Choose the type of calls to export: - Default: All (includes both incoming and outgoing calls). 5. Select a center and clients. You can choose one or multiple items to combine them in one report. 6. Specify the call retry interval (Round Calls), or leave as "None" (default). 7. Set the call duration if necessary (e.g., to investigate long calls). Otherwise, leave blank for all durations. 8. Set categories, bill time, and group if applicable. 9. Select the Call Insight configuration from the dropdown. 10. Click the "Generate" button to create the report. Mandatory Fields for Export To successfully export a report, the following fields must be selected: - Date Range - Center - Clients - Call Insights Other fields can be customized based on your needs. Export Formats 1. Generate PDF - Produces a PDF report. Note that PDFs may not display multiple fields well due to space limitations. 2. Generate XLSX - Exports the report as a spreadsheet. Ideal for large datasets with multiple fields or metrics. 3. Generate JSON - Exports the report in JSON format, suitable for applications that handle JSON data. Call AI Report Details: Fields and Descriptions | Field Name | Type | Description | Example | |---------------------------------|------------------|---------------------------------------------------------------------------------|--------------------------------------| | Date Range | Date | Specifies the date range for the report. | Jan 01–Jan 31, 2025 | | Only Include Specified Time of Day | Checkbox | Includes or excludes calls within a selected time range. | 9:00 AM–5:00 PM | | Type | Dropdown | Filters calls by direction: All, Incoming, or Outgoing. | Default: All | | Centers | Select | Includes one or more centers in the report. | Example: Main | | Clients | Select | Includes one or more clients in the report. | Example: VitalCare Wellness Clinic | | Round Calls | Dropdown | Controls the call retry interval (how long the system waits before trying the next agent). | Default: None | | Min/Max Call Durations | Number | Filters calls based on their length. | Example: Max 30s (to identify short calls) | | Category | Dropdown | Selects a category for filtering (when available). | Example: Daytime Access | | Billable Time | Dropdown | Specifies the call duration metric for reporting and billing. | Default: Blank | | Call Insight | Dropdown | Specifies which call insight configuration to use. | Example: AI Insight | | Group By | Dropdown | Organizes data by Agent or Center. | Example: Agent | Useful Applications of Reporting Options Only Include Specified Time of Day This option filters the report based on a specific time range, ensuring only calls within the selected period are included or excluded. What This Option Means: - Include specified time of day: Only shows calls within the selected range (e.g., 9:00 AM–5:00 PM). - Exclude specified time of day: Excludes calls within the selected range and shows data outside that window. Use Cases: 1. Business Hours vs. After-Hours Reporting - Track call volume during working hours vs. after-hours for staffing adjustments. 2. Shift-Based Call Analysis - Generate reports for morning vs. evening shift performance. 3. Peak & Off-Peak Call Trends - Identify busy vs. slow periods to optimize resource allocation. 4. Filtering Unnecessary Data - Remove irrelevant time slots like lunch breaks or overnight calls. Type This option filters call data based on the direction of the calls. What Each Option Means: 1. All: Includes both incoming and outgoing calls. 2. Incoming: Includes only calls received by the call center. 3. Outgoing: Includes only calls made by agents or receptionists. Use Cases: - Call Volume Analysis: Compare incoming vs. outgoing call trends. - Agent Performance Tracking: Monitor outbound calls for sales or support. - Customer Interaction Insights: Focus on incoming calls to understand customer demand. - Billing & Call Cost Management: Track outgoing calls for cost analysis. Round Calls This option controls the call retry interval. What These Options Mean: 1. Next Minute: The call waits up to 1 minute before moving to the next agent. 2. Next 30 Seconds: The call waits 30 seconds before transferring to the next agent. Use Cases: - Faster Call Distribution: Use shorter intervals (e.g., 30 seconds) to reduce customer wait times. - Agent Flexibility: Use longer intervals (e.g., 1 minute) to give agents more time to answer. Min/Max Call Duration These fields filter calls based on their length. What These Options Mean: 1. Min Call Duration: Includes calls lasting at least the specified number of seconds. 2. Max Call Duration: Includes calls lasting no longer than the specified number of seconds. Use Cases: - Exclude Short Calls: Filter out calls under 10 seconds (e.g., misdials). - Analyze Meaningful Conversations: Focus on calls over 60 seconds for engagement tracking. - Monitor Long Calls: Identify complex issues or excessive handling times. Bill Time This option selects the call duration metric for reporting and billing. Explanation of Bill Time Options: 1. Ring Time: Time from when the call starts ringing until it is answered or disconnected. 2. Talk Time: Time the agent and caller spend speaking. 3. Transfer Time: Time spent transferring a call to another agent or department. 4. Hold Time: Time the caller spends on hold. 5. Work Time: Time spent on after-call work (e.g., notes, follow-ups). Use Cases: - Customer Experience Monitoring: Use Ring Time and Hold Time to measure wait times. - Agent Performance Tracking: Use Talk Time and Work Time to analyze efficiency. - Call Routing Optimization: Use Transfer Time to reduce unnecessary transfers. Group By This option controls how data is organized in the report. Group By Options: 1. Agent: Groups data by individual agents. 2. Center: Groups data by call center location or department. Use Cases: - Agent Performance: Group by Agent and use Talk Time or Work Time. - Customer Wait Times: Use Ring Time or Hold Time. - Workload Distribution: Group by Center to compare call handling across locations.

Last updated on Feb 03, 2025

Sentinel Setup Guide: Preparing EvoVoice for AI-Powered Insights

This guide provides step-by-step instructions to configure EvoVoice for AI-powered analysis. Before EvoVoice can process calls for AI insights, it requires a recording of each call. The recording is processed by AI, and prompts are applied to generate efficient outputs for the Sentinel process. This document explains how to prepare audio recordings for processing and how to set up the system to provide insights in the dashboard. Step 1: Preparing the HostedSuite Insights Flow The first step is to create a HostedSuite Insights Flow. This will act as a subflow, allowing multiple workflows to share it for AI call analysis. Create a New Flow 1. Open the Flow Designer. 2. Click Create New Flow and enter a name. - Example: "HostedSuite AI Call Insights" Add a Recording File Parameter To ensure each call recording is properly processed, we must define a Recording File parameter. This will receive the audio file before it is analyzed. Steps to Add a Parameter 1. In the Flow Designer, select the HostedSuite Insights flow. 2. Click the Parameters tab. 3. Click Add Parameter, then fill in the details: - **Name**: `RecordingFile` - **Type**: `AudioFile` - **Public**: ✅ *(Check this option)* 4. Click Add Parameter. Once added, the new parameter should appear in your HostedSuite AI Call Insights node. Step 2: Configuring the Node Fields Now that we have the parameter, we need to configure the node settings. Steps to Configure the Node 1. Click Properties in the HostedSuite AI Call Insights node. 2. In the Recording Field, select: - Flow Parameter: RecordingFile (or the name of your parameter) 3. Enter the HostedSuite API Endpoint: - https://v3.hostedsuite.com/api 4. Enter the HostedSuite Customer, Username, and Password. - (This information is provided by EvoVoice. Contact support if needed.) 5. Click Save. Your HostedSuite Insights Flow is now ready to be used in workflows. Step 3: Connecting the Insights Flow to a Parent Flow To integrate this subflow into a larger workflow, we need to create an audio recording parameter in the parent flow. Create an Audio Recording Parameter 1. In the Parent Flow, select the Dial Node. 2. Go to the Parameters tab. 1. Click Add Parameter, then enter: - Name: RecordingAudio (or any temporary name to store the recording) - Type: AudioFile 2. Click Add Parameter. This parameter will temporarily hold the recording before sending it to the HostedSuite AI Call Insights node. Step 4: Configuring the Dial Node for Call Recording Now, we must enable call recording in the Dial Node. Steps to Configure Call Recording 1. Open the Dial Node Properties. 1. Update the following settings to Yes: - Record Call → ✅ Enable recording - Record Transfer Attempts → ✅ Record transfer attempts - End Recording After Hangup → ✅ Automatically stop recording when the call ends 2. Click Save. Step 5: Mapping the Recording to HostedSuite Analytics Now that both the Parent Flow and AI Call Insights Flow are ready, we need to connect them. Steps to Map the Recording 1. In the Parent Flow, locate the Recording Ready event. 2. Connect the Recording Ready event to the HostedSuite AI Call Insights subflow. - This ensures that the recording is only sent for AI processing when it's ready. 3. Add the HostedSuite AI Call Insights Node to the parent flow. 4. Click Properties and set: - Recording File → Flow Parameter: RecordingAudio (the parameter from the Dial Node) 5. Click Save. Final Setup With these steps completed, your EvoVoice setup is ready for AI analysis. The system will now process call recordings, apply AI prompts, and generate insights for the Sentinel process. For further assistance, contact Evo’s support team.

Last updated on Feb 04, 2025

Creating a HostedSuite Call AI Insights Flow

This guide provides step-by-step instructions for creating a HostedSuite Insights Flow that can be used as a sub-flow in multiple workflows. This sub-flow ensures that call recordings are properly processed and ready for AI-powered analysis. Step 1: Creating a HostedSuite CaIl Insights Flow The HostedSuite Insights Flow will act as a sub-flow, making it reusable across different workflows. Create a New Flow 1. Open the Flow Designer. 2. Click Create New Flow. 3. Enter a name for the flow. - Example: "HostedSuite AI Call Insights". 4. Click Save. Step 2: Adding a Recording File Parameter To process call recordings efficiently, we must define a Recording File parameter. This parameter ensures that recordings exist before being processed. Steps to Add a Parameter 1. In the Flow Designer, select the HostedSuite Insights flow. 2. Click the Parameters tab. 3. Click Add Parameter. 4. Enter the following details: - Name: RecordingFile - Type: AudioFile - Public: ✅ (Check this option to make the parameter accessible to other flows). 5. Click Add Parameter. Once added, the new parameter will appear in your HostedSuite AI Call Insights node. Step 3: Configuring the Node Fields Now that the parameter is set up, we need to configure the node settings. Steps to Configure the Node 1. Click Properties in the HostedSuite AI Call Insights node. 2. In the Recording Field, select: - Flow Parameter: RecordingFile (or the name of your parameter). 3. Enter the HostedSuite API Endpoint: - https://v3.hostedsuite.com/api 4. Enter the HostedSuite Customer, Username, and Password. - (This information is provided by EvoVoice. Contact support if needed.) 5. Click Save. Your HostedSuite Insights Flow is now set up and ready to be used in any workflow requiring AI-powered call analysis.ll

Last updated on Feb 06, 2025

Configuring EvoVoice for AI-Powered Sentinel Insights

This guide provides step-by-step instructions for configuring EvoVoice to process and analyze calls within a single flow, combining both the Dial Node and AI Call Insights for a streamlined Sentinel setup. Step 1: Creating the Main Flow with the Dial Node The first step is to create a main flow that includes both the Dial Node for call handling and the AI Call Insights for processing the recorded calls as part of the Sentinel analysis. Create a New Flow 1. Open the Flow Designer. 2. Click Create New Flow. 3. Enter a name for the flow. - Example: "EvoVoice AI Sentinel Call Flow". 4. Click Save. Step 2: Create an Audio Recording Parameter This parameter will temporarily hold the recording before sending it to the HostedSuite AI Call Insights sub-node for Sentinel analysis. 1. In the Flow Designer, select the Dial Node. 2. Go to the Parameters tab. 3. Click Add Parameter, then enter: - Name: RecordingAudio (or any temporary name to store the recording) - Type: AudioFile - Set to Public by enabling this option. 4. Click Add Parameter. It should look like this once added: Step 3: Enable the Call Recording Properties Now we have to enable the call recording capabilities of our Dial Node to ensure that calls are recorded and passed on for AI analysis. 1. With the Dial Node selected, click the Properties section/tab to configure the call recording. Follow the settings below to ensure Sentinel analysis can process the calls. - Record Call → Yes ✅ Enable recording - Record Transfer Attempts → Yes ✅ Record transfer attempts - End Recording After Hangup → Yes ✅ Automatically stop recording when the call ends - Output → Select the flow parameter we’ve previously created Flow Parameter: RecordingAudio 1. Click Save. Step 4: Adding AI Call Insights to the Same Flow Since we are integrating AI-powered Sentinel analysis within the same flow, we need to configure the AI Call Insights node directly after the Dial Node. 1. Add the HostedSuite AI Call Insights Node to the flow. 2. Click Properties and set the recording file to the flow parameter we’ve created for the Dial Node: - Recording File → Flow Parameter: RecordingAudio (parameter from the Dial Node). 3. Now you can connect the Recording Ready property from the Dial Node to the HostedSuite AI Call Insights Node for Sentinel processing. 4. Click Save. Please note that the HostedSuite AI Call Insights Node is created separately. You can follow this GUIDE if you haven’t done so. Final Setup With these steps completed, your EvoVoice setup is now fully integrated with Sentinel Call AI Insights. Calls will be recorded and processed seamlessly, applying AI insights and providing detailed Sentinel analysis within the HostedSuite dashboard. For further assistance, contact EvoVoice support.

Last updated on Feb 06, 2025

EvoTech Sentinel Guide for HostedSuite

This guide provides a comprehensive walkthrough of the EvoTech Sentinel process. You will learn how to set up and maximize the Call Insights dashboard to improve call quality and system efficiency within your HostedSuite environment. What is Sentinel in EvoVoice? Sentinel is an advanced monitoring and reporting process that enhances call system reliability, call quality, and overall performance. It combines AI with EvoVoice to provide real-time analytics and call summaries, ensuring the system aligns with your organization’s standards. The main dashboard features AI Call Insights for comprehensive monitoring. How Sentinel Helps Clients - Call Recording – AI Insights records every call within the organization. You can specify which clients will have call insights activated. - Customizable Monitoring Parameters – AI-driven insights allow for fully customizable monitoring based on organizational needs. - Reporting – Generate and export reports based on AI Call Insights data. - Flexible Data Types – Supports multiple data types, including text, numbers, Boolean values, lists, and percentages, to enhance call quality analysis. Learn more here. Key Reasons for QA in Voice Systems Implementing Quality Assurance (QA) ensures consistent and high-quality customer interactions that align with company standards and customer expectations. 1. Customer Satisfaction – Ensures agents provide clear, professional, and helpful support. 2. Compliance & Security – Maintains adherence to company policies, industry regulations, and data protection laws. 3. Agent Performance Monitoring – Identifies training needs and areas for improvement. 4. Call Resolution Efficiency – Helps reduce call handling times and improve first-call resolution rates. 5. Service Standardization – Ensures all customers receive a uniform experience. 6. Error & Issue Detection – Identifies customer pain points and operational bottlenecks. 7. Fraud Prevention & Call Monitoring – Detects suspicious activities or improper handling of customer data. Built-in Features of AI Insights Dashboard The AI Insights dashboard provides several pre-built features to enhance call monitoring. You can expand more metrics by adding custom fields based on your requirements. You can check this GUIDE on how to create custom fields. | Feature | Description | | --- | --- | | Agent | Displays the name and email of the agent who received the call. | | Client | Shows the name of the client the caller is contacting. | | Date | Displays the call date based on the client’s timezone. | | Start Time | Indicates when the call was received. | | Duration | Shows the call length in mm**:ss** format. | | Call Recording | Provides an audio file for playback. | | Transcript | Displays a text transcript of the call. | | Caller Sentiment | Shows a percentage breakdown of caller sentiment (negative, neutral, positive). | | Operator Sentiment | Shows a percentage breakdown of agent sentiment (negative, neutral, positive). | Building Custom Fields Beyond the built-in features, organizations can customize call metrics to fit specific needs. Learn more here. Call Recording and Transcript Review Every recorded call includes an option for reviewing the audio and transcript: - Click the audio icon to replay a recording. - Click the transcript button to view the call transcript. AI Insights Dashboard & Export Options Once set up, AI Insights data is available in real time. To export reports: 1. Navigate to Reports > AI Call Insights Report. 2. Customize the data fields. 3. Export reports for further analysis. The report also includes aggregated data, which is generated based on the options selected during the export process. Here’s an example of an exported report: For a complete guide on reporting options, click HERE. Integrating Call Insights with EvoVoice To enable Call Insights, a recorded audio file must be processed by AI. Once analyzed, the data is pushed to the client’s HostedSuite account. Setup Guide.

Last updated on Feb 07, 2025

AI Agent Onboarding

This knowledge base details the process and necessary configurations for setting up and customizing your Evo Technologies AI Agent. The process is completed via the AI Agent Onboarding Form found in the client console. 1. Accessing the Onboarding Form | Step | Action | Navigation Path | | :--- | :--- | :--- | | 1. | Navigate to Organization | From the left sidebar | | 2. | Select Clients | Under the Organization menu | | 3. | Select your Registered Client | Click on your client's name from the list | | 4. | Access the form | Click the AI Onboarding button | 2. Admin & Customer Settings Configuration The onboarding form is organized into several sections to configure the AI Agent's operation, identity, and behavior. Plan Selection This section determines the features and capacity of your AI Agent based on anticipated usage and the number of agents needed. | Field | Description | Action | | :--- | :--- | :--- | | Plan | Choose the service plan that best fits your business needs. | Select the appropriate plan from the dropdown menu. | Hours of Operation This configuration defines when your AI Agent will actively answer calls. | Field | Description | Options | | :--- | :--- | :--- | | When Should The AI Answer Calls? | Determines the AI Agent's active hours. | * Always (24/7 coverage) | | | | * Business Hours (Active during specified business times) | | | | * Outside Business Hours (Active for after-hours calls) | | It should also answer on no answer of Live Answer Team | Allows the AI Agent to handle voicemail/missed calls. | Check this box for voicemail coverage. | Phone Number This is the primary contact number your AI Agent will use to answer and place calls. | Field | Description | Action | | :--- | :--- | :--- | | Do you have a new or existing number? | Select how the phone number will be provided. | Select Use Existing or Use New (New number requires a request for an area code). | | Enter your existing number | The number the AI Agent will use. | Enter the complete phone number, including the country code (e.g., +16462021375) and area code. | 3. Customer Settings Configuration Business Info This information personalizes the AI Agent's interactions with callers. | Field | Description | Example | | :--- | :--- | :--- | | Enter your company name | The official name of your business. | Bright Smile Dental | | How would you like your AI Agent to greet callers? | The opening message the AI Agent will use. | "Thank you for calling Bright Smile Dental. How may I brighten your day?" | AI Info This section defines the AI Agent's personality and voice. | Field | Description | Action/Options | | :--- | :--- | :--- | | How do you like your AI Agent to refer to themselves? | The name the AI Agent uses when introducing itself. | Enter a name (e.g., Jessica). | | What primary language would you like your AI to speak? | The language the AI Agent will use. | Select from the dropdown (e.g., American English - en-US). | | What voice would you like your AI Agent to have? | The specific voice and tone of the AI Agent. | Browse and select a voice option (samples are usually available to test). | | Describe the personality you would like your AI Agent to have | The overall demeanor and style of interaction. | Enter a description (e.g., Cheerful, friendly, helpful, and knowledgeable about dental services). | Call Handling This defines the specific instructions and procedures the AI Agent must follow for incoming calls. | Field | Description | Key Instruction Areas | | :--- | :--- | :--- | | Enter Call Handling Request | Detailed instructions for the AI Agent to manage different call scenarios. | 1. Determine Caller Intent and Location: Ask clarifying questions to determine the call's purpose (e.g., "Ask clarifying questions to determine which location and service the caller is interested in"). | | | | 2. Post-Information Action: Instructions for call transfers, scheduling, or capturing contact details if a live person is unavailable. | | | | 3. Exceptions/Escalation: Define rules for handling specific cases (e.g., "If the caller requests a 'Book an Appointment,' transfer the call, or send a scheduling link"). | Contacts A list of key people and their contact information for the AI Agent to use for call transfers or reference. | Fields | Purpose | | :--- | :--- | | First Name, Last Name, Email | Essential contact information. | | Position, Department | Defines their role and transfer relevance. | | Instruction | Specific rules on when to transfer a call to this person (e.g., "Transfer billing inquiries to this contact"). | | Phone | Their direct phone number. | SMS Links Allows the AI Agent to send relevant links to callers via SMS. | Field | Purpose | | :--- | :--- | | URL | The complete web address (e.g., for online appointment booking). | | Description | A brief label for the link's purpose (e.g., "Appointment Booking Link"). | Forms Allows you to create custom data collection forms for the AI Agent to fill out during calls (e.g., a New Patient Intake Form). | Field | Purpose | | :--- | :--- | | Name | A clear name for the form (e.g., "Appointment Form"). | | Purpose | Instructions on when the AI should use the form (e.g., "Fill this form for every call"). | | Fields | Each field requires a Field Name (e.g., Patient Name), Field Type (Text, Number, Dropdown), a Description (guide for the AI), and an indication if it is Required. | 4. Submission & Implementation 1. Review all sections for accuracy, especially phone numbers, emails, and all instructions. 2. Click the Submit for Implementation button (located at the bottom right). - The completed form is automatically emailed to the Evo Technologies support team. - Onboarding engineers will review your submission and configure your AI Agent according to your specifications. - You will be contacted if any clarification is needed during the implementation process.

Last updated on Nov 27, 2025