Overview
The conversational Tone Suggestions feature helps market researchers create more engaging, on-brand survey messaging. This AI-powered tool allows researchers to select tone settings for their surveys, providing dynamic suggestions for improving the conversational quality of their survey messaging. Users can tailor the tone to match their brand or project goals without needing advanced writing or copyediting skills.
Key Benefits
Create survey experiences that are conversational, engaging, and on-brand.
Easily adjust tone descriptors and emoji usage to align with specific audience segments or brand voices.
Customize tone suggestions at the message or survey level for flexibility.
Leverage AI-driven suggestions to fine-tune survey messaging for better respondent engagement.
Where to find AI tone suggestions
By default, AI tone suggestions are enabled in a domain. Tone Suggestion Cards will appear beside any messaging based card in your chat script.
You can Click on ✨next to preview button to open the tone suggestion options.
You can disable the tone suggestions by clicking on Disable AI Suggestions option
When you select Refresh Suggestions, a new set of suggestions will appear for each question card.
Edit tone descriptors will open a list of tones available and shows the current selection applied. You have an option to add a custom tone by clicking on 'Add Custom' button.
Editing Tone Descriptors
Tone descriptors allow you to set the desired conversational tone for your survey. You can choose one or more tone descriptors to inform the AI on how the messaging should feel.
Example Tone Descriptors:
Formal, Traditional, Mature for more conservative surveys, such as banking or insurance.
Fun, Spirited, Untucked, Youthful for casual brands, like snowboarding or fashion.
Warm, Supportive, Inclusive for health, wellness, or sensitive topics.
After selecting tone descriptors, the AI generates suggestions to improve the messaging tone.
Steps:
Navigate to the message card you want to enhance.
The AI will present suggested improvements in wording and structure based on the selected tone.
Example:
Initial message: “Please enter your age.”
Formal tone suggestion: “Kindly provide your age for our records.”
Fun/Spirited tone suggestion: “We’re curious—what’s your age? Don’t worry, we won’t tell!”
Tone Suggestions at Card level
You will also be able to manage/edit your tone suggestions at a card level.
Emoji Usage Controls
Control the number of emojis in your survey messaging to match the desired tone. Emoji usage can be adjusted to fit a formal or casual style.
Toggle this action to expose / hide the emoji slider
Steps:
Use the Emoji Usage Slider to set the desired emoji frequency:
None: No emojis in suggestions.
Minimal: Occasional, sparing emoji use.
Moderate: Balanced use for casual, conversational tones.
High: Frequent emojis for playful or highly informal messaging.
Example:
If the Fun tone is selected and the emoji slider is set to Moderate, a message like "Thanks for answering!" could become:
“Thanks for answering! 😊”
Card-Level Tone Settings
You can launch the tone descriptor panel from card level to edit your tone for the particular question card. This panel is similar to the one above but the edited selection will only apply to the particular card.
Tone-Suggestions Refresh
The Refresh button allows you to generate multiple suggestions until you find a result that aligns with your brand and tone.
Apply or Copy Suggestions
The Apply button directly applies the generated/suggested text into the question text space for the particular card. You can also copy and paste the text to the question text field.
Advanced Features
Research domain level Default Tone Settings
Default tone preferences can be defined at the domain level, applying automatically to all new surveys. This feature ensures consistent brand messaging across all surveys.
Steps:
Research domain admins have the permissions to set tone descriptors at the domain level via Settings > ChatGPT. This setting will be applied to all chats in this domain.
Default settings (e.g., Fun, Youthful, Spirited for a retail brand) will be applied to new surveys.
Users can adjust these defaults for specific campaigns if needed.
Technical Details
The Tone Suggestions feature leverages OpenAI’s chat completion endpoint, currently powered by the GPT 4.o Mini LLM.
Users can select from a list of tone descriptors that guide the AI in generating messaging. A one-shot prompt is used to instruct the AI on how to craft messaging that aligns with the selected tone while maintaining a consistent structure. Depending on the type of card, such as multiple-choice cards, specific instructions are provided to the AI for context, enhancing the quality and relevance of the suggestions.
For surveys that require emoji control, users can adjust emoji usage levels with a slider. This feature offers five different levels of emoji frequency, progressively removing one-fifth of the emojis at each level (rounded to the nearest whole emoji). This ensures users have full control over the tone and formality of the messaging.
Risk Mitigation
The Rival Platform adheres to strict privacy and security requirements, including ISO27001:2022, HIPAA, GDPR and SOC 2 Type II. Our partnership with OpenAI falls under the same scrutiny, and we are constantly monitoring for updates to the scope of their services. When we use the OpenAI APIs and LLMs, several data privacy and security features are provided to protect user data and ensure secure interactions. Here are the key features:
Data Encryption:
In Transit: Data transmitted between your systems and OpenAI servers is encrypted using Transport Layer Security (TLS) to prevent interception and unauthorized access.
At Rest: Data stored on OpenAI's servers is encrypted to safeguard it from unauthorized access and breaches.
Access Controls:
API Keys: Secure API key management allows only authorized applications and users to access the API. You can regenerate keys if needed to maintain security.
Role-Based Access: Granular permissions to control who can access and manage your API keys and data.
Data Minimization:
Limited Data Retention: OpenAI retains data only for as long as necessary to provide the service, ensuring that data is not kept longer than required.
Anonymization: Personal data is anonymized to protect user identities.
Compliance with Regulations:
GDPR and CCPA Compliance: Adherence to data protection regulations such as the General Data Protection Regulation (GDPR) and the California Consumer Privacy Act (CCPA), ensuring data subjects' rights are respected and protected.
Logging and Monitoring:
Audit Logs: Detailed logging of API usage to track and monitor access and activities. This helps in detecting and responding to any unauthorized or suspicious activities.
Monitoring: Continuous monitoring of API endpoints for unusual patterns or potential security threats.
Rate Limiting:
Throttling: Rate limiting to prevent abuse and ensure fair usage. This also helps in mitigating denial-of-service (DoS) attacks.
Incident Response:
Security Team: A dedicated security team is in place to respond to and mitigate any security incidents promptly.
Incident Management: Established procedures for detecting, reporting, and addressing security incidents and breaches.
Regular Security Audits:
Third-Party Audits: Regular security assessments and audits by third-party experts to identify and fix vulnerabilities.
Internal Reviews: Ongoing internal security reviews and improvements to maintain high security standards.
Customer Control:
Data Management: Customers have control over their data, including options for data deletion and export as needed.
API Customization: Flexibility to customize API usage according to specific security and privacy needs.
Transparency and Documentation:
Clear Policies: Transparent data privacy and security policies are provided, outlining how data is handled, processed, and protected.
Comprehensive Documentation: Detailed documentation on best practices for securing API keys and using the API securely.
Employee Training:
Security Training: Regular training for employees on data privacy, security best practices, and emerging threats to ensure they are equipped to handle sensitive data securely.
Enterprise privacy page:
Open AI security and privacy page:
Open AI security portal:
Value Creation
Efficiency:
Automates the process of creating engaging, on-brand conversational survey messaging, saving time for market researchers.
Brand Consistency:
Applies predefined tone preferences across all surveys, ensuring a unified voice that matches brand guidelines.
Engagement:
Helps craft engaging, audience-tailored survey experiences, improving response quality and completion rates.
Customization:
Provides flexibility in tone and emoji controls, allowing users to customize messaging at both the chat and message level.
This feature offers market researchers a powerful tool to elevate their surveys, making them more dynamic, engaging, and reflective of their brand’s unique voice.