AutoSummary Updates

​

Intents Self Service Tooling

The Intents Self Service tool in ASAPP’s AI Console provides a streamlined interface for managing intent classification. This automated, self-serve UI allows customers to:

• Upload, create and modify intent labels without support team intervention
• Manage intent label hierarchies during onboarding or as business needs evolve
• Consolidate or create more granular intents
• Deploy changes to production within minutes

The tool leverages GenAI (LLMs) to enable:

• Zero-day customer onboarding
• Self-service intent management through an intuitive frontend
• Real-time intent classification deployment pipeline

​

Structured Data

Structured Data is a powerful, fully customizable feature for extracting customizable data points from conversations through:

• Entity extraction: Automatically identifies key information like product names, dates, amounts, and more
• Question extraction: Answers predefined questions about conversations (e.g., “Was the issue resolved?”)

The dynamic nature of Structured Data allows you to extract data for:

• Generating automated insights and reports at scale
• Populating CRM fields directly from conversations
• Monitoring compliance and script adherence automatically
• And more.

​

Salesforce Integration

ASAPP’s native Salesforce plugin now includes AutoSummary integration. This enables Salesforce administrators to quickly install and configure AutoSummary within their Lightning environment.

The low-code plugin allows administrators to deploy AutoSummary in hours without complex integration work. Once enabled, the system automatically generates and saves conversation summaries to Salesforce records, eliminating the need for manual note-taking by agents.

​

Free-Text and Feedback Feeds for AutoSummary

ASAPP introduces two feeds to retrieve data for free-text summaries generated by AutoSummary and edited versions of summaries submitted by agents as feedback.

These two feeds enable administrators to retrieve AutoSummary data using the File Exporter API:

• Free-text feed: Retrieves data from free-text summaries generated by AutoSummary.
  • This feed has one record per free-text summary produced and can have multiple summaries per conversation.
  • Schema: autosummary_free_text
• Feedback feed: Retrieves data from feedback summaries submitted by the agents.
  • This feed contains the text of the feedback submitted by the agent.
  • Developers can join this feed to the AutoSummary free-text feed using the summary ID.
  • Schema: autosummary_feedback

​

Sandbox for AutoSummary

ASAPP introduces the AutoSummary Sandbox, a testing environment in AI-Console that allows administrators to validate and experiment with summary generation before deploying to production. The Sandbox supports both voice and messaging conversations, letting users simulate interactions or upload existing transcripts to preview how AutoSummary will perform.

The Sandbox starts with baseline contact center models and can be upgraded to use your custom-trained models once deployed. This allows teams to preview summary formatting and validate outputs throughout their implementation journey.

AutoSummary now supports model retraining using agent feedback. The feedback endpoint receives free-text paragraph summaries submitted by agents, and uses the difference between the automatically generated summary and the final submission to improve the model over time.