Skip to contentSkip to navigationSkip to topbar
On this page

Voice Insights - Intelligent Discovery AI Assistant


(information)

Public Beta

The Voice Insights - Intelligent Discovery AI Assistant for call insights is currently offered as a Public Beta, exclusively available to Voice Insights advanced features customers. Information contained in this document is subject to change. Public Beta products aren't covered by a Twilio Service Level Agreement. Learn more in the "Twilio Beta Product Support" Help Center article(link takes you to an external page).

The Voice Insights - Intelligent Discovery AI Assistant is an AI-driven assistant enabling you to interact with your voice data using natural language. The Assistant helps you troubleshoot Voice-related issues, including deliverability(connection rate), answer rate, networking related and other behavioral issues such as silent calls. It can assist with data analysis and dive deeper into your voice data to find potential root causes. The Assistant provides recommendations to solve voice errors and potential issues. You can provide feedback on each response and the overall Assistant experience. Activate Voice Insights Advanced Features to use this feature.


Why Intelligent Discovery?

why-intelligent-discovery page anchor

Twilio customers often encounter difficulties in finding the right information within the Twilio Console, making the troubleshooting process potentially lengthy and frustrating. This can lead to increased support tickets, operational disruptions, significant costs, delays, and a decline in customer trust. The longer an issue takes to resolve, the higher these risks become.

While the Voice Insights-Call Insights page provides a self-serve experience, it can be enhanced further with an AI assistant. Such a tool would empower businesses to maintain smooth operations without immediately resorting to support tickets. This assistant would extend timely assistance to all users, helping them resolve issues swiftly and manage challenges without compromising customer trust.

Intelligent Discovery enhances self-service capabilities for both non-technical business users and technical experts, helping users meet their needs more effectively.


How Intelligent Discovery can help you

how-intelligent-discovery-can-help-you page anchor

The Assistant can help you with various tasks related to Twilio's voice services. Here are some of the things it can do:

Natural language processing and support

natural-language-processing-and-support page anchor
  • Accept questions in natural language and provide answers in natural language.
  • You can start with one of our guided flows or ask questions directly using the chat feature.

Here are some example questions you can ask the Assistant:

  • How is latency calculated in voice calls, and what are the latency thresholds?
  • How many calls failed in the last 30 days?
  • How are network-related calls flagged?
  • How many calls had network-related issues in the last 30 days?
  • How many calls were silent in the last 7 days?
  • How many Voice SDK calls were affected by network issues?

Analyze voice issues and troubleshoot

analyze-voice-issues-and-troubleshoot page anchor
  • Call Statess: The Assistant can analyze your voice data to identify various call states, such as failed, completed, busy, no-answer and cancelled calls. It can also answer questions related to countries, call duration and more. Prompt: Give me the breakdown of the call states of my calls ?
  • SIP Response: Provide a list of the most common sip response for your calls. Prompt: What was the sip response of my calls ?
  • Country-specific issues: Identify countries where your calls are facing delivery problems.
  • Network Related issues issues: Get a breakdown of the network related issues such as packet loss, jitter, or latency.
  • Who Hung Up: Get a breakdown of call disconnection states and determine the split between calls hung up by the caller or the callee. Prompt: Who hung up, the caller or the callee ?
  • Retention: The Assistant supports analysis on the voice data generated in the last 30 days.
  • Context: The Assistant carries the context of previously asked questions in order to formulate the next response.
  • Actionable recommendations: Offer advanced and personalized recommendations to resolve specific issues identified in your calls history.
  • Knowledge base lookup: Search the Twilio knowledge base for solutions to specific SIP response codes or call states.
  • Twilio service status: Provide the current status of Twilio services, including any downtimes, outages, or maintenance.
  • Product information: Answer questions about Twilio products and services.
  • Best practices: Share best practices for using Twilio's voice services effectively.
  1. Rapid execution: Sorted summary tables are included in the responses, allowing you to take action more quickly.
  2. Trust and transparency: The What's showing button provides the query equivalent to offer transparency to you.
  3. Assistant boundaries: The Assistant adheres to legal boundaries.
  4. Quick navigation to home screen: A back button is available for quick navigation to the home screen.
  5. Interaction history: When you log in, signing off deletes your history, and navigating to the home page also removes it.
  6. Various ways to provide feedback: You can give feedback using thumbs up and thumbs down, as well as providing overall session comments.
  7. Ease of use: The Assistant uses natural language responses.
  8. Guided flows: The Assistant provides guided flows for ease of use.
  9. Free-form chat flows: You can engage in free-form chat flows.

Intelligent Discovery AI Assistant uses third-party artificial technology and machine learning technologies.

Twilio's AI Nutrition Facts(link takes you to an external page) provide an overview of the AI feature you're using. This should help you better understand how the AI interacts with your data. Intelligent Discovery AI Assistant qualities are outlined in the following Intelligent Discovery AI Assistant Nutrition Facts label. To learn more and review the glossary regarding the AI Nutrition Facts Label, consult Twilio's AI Nutrition Facts page(link takes you to an external page).

AI Nutrition Facts

Intelligent Discovery AI Assistant

Description
The Intelligent Discovery AI Assistant is an AI-driven assistant that allows users to interact with voice call data using natural language. The Assistant helps troubleshoot call-related issues. It assists with data analysis and explores your call data to identify potential root causes. The Assistant provides recommendations to solve call errors and potential issues. Customers can provide feedback on each response and the overall Assistant experience. Customers can request to talk to a live Twilio support representative if they continue to experience unresolved issues.
Privacy Ladder Level
1
Feature is Optional
No
Model Type
Generative
Base Model
Twilio Proprietary + OpenAI GPT-4

Trust Ingredients

Base Model Trained with Customer Data
No
Customer Data is Shared with Model Vendor
Yes

This is only for the interaction and intent aspect of the conversation the user has with the Intelligent Discovery AI Assistant. Twilio doesn't share PII with the model vendor.

Training Data Anonymized
N/A
Data Deletion
Yes

Twilio only deletes conversation data created during the interactions with the Assistant.

Human in the Loop
Yes

Customers can opt to talk to a Twilio human agent if the Assistant isn't able to solve their issues, but it isn't required. The human agent can also collect feedback to improve the Assistant

Data Retention
30 days

Compliance

Logging & Auditing
Yes
Guardrails
Yes

Twilio is leveraging the model vendor for this.

Input/Output Consistency
Yes

Twilio is leveraging the model vendor for this purpose.

Other Resources
See Twilio public documentation.

Next steps and additional resources

next-steps-and-additional-resources page anchor

Intelligent Discovery for voice Insights democratizes actionable insights from voice data, making them accessible to both developers and non-technical business users. By leveraging AI-driven natural language processing, this feature simplifies troubleshooting and enhances the ability to gain valuable insights from communications data. Here are some possible next steps and additional resources to help you get started: