Accelerated AI Agent Editor and More with Cognigy.AI 2025.19 Release

5 min read

Authors name: Nhu Ho September 22, 2025

A-A+

The latest Cognigy.AI release introduces a sleek new interface for managing AI Agent Jobs and Tools, significantly improving usability and speed. It adds a powerful additional way to control, edit, and orchestrate AI Agents - fully compatible with existing Agents and the Flow Editor. Alongside this, the release also brings enhanced control over data retention in Cognigy Live Agent through a new time-to-live (TTL) setting for conversations.

Accelerated Agent and Job Editor for Increased Productivity

We’ve rolled out a faster, more intuitive interface for configuring AI Agents and their associated Jobs and Tools. Instead of navigating through Flows, users can now also use a new unified view to easily see, edit, and manage components tied to an AI Agent. The Interaction Panel is directly accessible, so changes can be tested immediately, streamlining development and reducing iteration time.

Importantly, the new interface complements the existing AI Agent management via Flow Editor. While the Flow Editor continues to provide full flexibility for designing advanced conversational experiences, the new Agent Editor offers an alternative, simplified approach for everyday management and demos. Key benefits:

Speed and Simplicity: No more clicks through Flows to find and tweak a Job or Tool.
Enhanced Visibility: A clear overview makes it easy to catch misalignments, apply changes, and preview user experiences and Tool execution in real time.
Focused Workflows: Prompt updates and minor modifications can now be done quickly, while the advanced Editor remains easily accessible for full Flow logic customization.

Want to see the new Agent Editor in action? Don’t miss our upcoming Cognigy.AI Tech Update session.

Enhanced Conversation Data Handling in Cognigy Live Agent

Another highlight of this release is the ability to setTTL (time‑to‑live) for conversations in Account Settings. Once configured, old conversations are automatically deleted both from the UI and from the Live Agent OData Endpoint after the defined period.

This gives administrators maximum control and governance over data retention, contributing to:

Improved Compliance: Shorter TTLs reduce the window in which customer data is stored, which helps meet GDPR/other retention policies where data minimization is required.
User Trust: Responsible handling of customer-sensitive data shows commitment to privacy, increasing user trust and loyalty.
Efficient Storage & IT Ops: Shorter retention keeps datasets lean, minimizes manual cleanup, and curbs storage and analytics footprint.

Other Improvements:

Cognigy.AI

Added the message id key to the transcript Input object to uniquely identify each message within a conversation transcript
Added a loading banner to show progress when creating Knowledge Sources
Added the End Handover on Participant Change setting to the Handover to Agent Node for the Salesforce MIAW provider. Enabling this setting ends the handover when an agent is removed, relying on the participant change event because Salesforce can't always guarantee receipt of the conversation close event
Enhanced Playbook text assertions with advanced fuzzy search that handles case differences, extra spaces, tabs, newlines, and escaped characters

Cognigy Insights

Removed the charts related to the understood/misunderstood message concept from the Overview and NLU Performance reports to simplify the reports and focus on more actionable metrics
Removed the Top Tasks chart from the Engagement report because the chart was already included in the Overview report, avoiding duplication and improving clarity

For further information, check out our complete Release Notes here.