Changelog

On this page you will see production updates for eva

version 3.4.1 | May 5, 2022

Fixes included in this fix version:

Intent Navigator: Ability to send the Intent directly to the eva CAI avoiding having to call the NLP engine and using it to resolve the answer. It is an interesting feature if you are integrating external tools or channels which are using their own NLP
Masking: Now is possible to send the Project and Channel information to the masking module to improve the logic of how the data is obfuscated. We also have included support for custom Entity masking
Dialogflow Multiregion: With this enhancement, Dialogflow offers three new data regions: London, for all of Western Europe; Tokyo, for Northeast Asia; and Sydney for Southeast Australia
Data Improvement: Intent and Entity information returned by the NLP engine has been included in the USER INTERACTION table.

Fixes included in this fix version:

Fixes included in this fix version:

EVASUPP-1837 - An invalid channel existed in a specific response in a Template Channel, but it was never validated and cleared after filtering bot channels, leading to a transient object save error.
EVASUPP-1918 - It is not possible to train a cloned bot as long as it is in the original bot.
EVASUPP-1987 - Error trying to view the flow.
EVASUPP-1932, EVASUPP-1919 - Slowness issues when trying to insert an existing intention.
EVASUPP-1745 - Error deleting cells in sequence.
EVASUPP-1635, EVASUPP-1897 - Error importing bot, due to duplicated intents in eva.
EVASUPP-1832 - Cached data is never cleaned.
ASSETEVA-2471 - Rule or Code cell is not processed correctly after input.

Fixes included in this fix version:

EVASUPP-1644 - When using regex type entities, user input did not match the corresponding entity.
EVASUPP-1680 - When there is a text answer registered in the Watson dialog and this is the name of an answer registered in eva, the answer to be returned to the user should be the content that is registered in eva.
EVASUPP-1696 - Only the user who runs the automated test is able to see the results while the other users only see a warning popup.
EVASUPP-1696 - There is a gap in the condition that classifies utterances. Some values were being discarded as they did not match any of the conditions.
EVASUPP-1696 - When uploading the automated test template if there is some special character the upload fails.
EVASUPP-1786/EVASUPP-1790 Bot does not respond using Whatsapp channel (Infobip).
ASSETEVA-2484 - When cloning a bot, it doesn't go to the first page.

Code Cell, a new feature that works with information available in eva’s system that doesn’t depend on APIs
The new Rule Cell feature allows you to manage and customize the flows according to the variations of the business rule. It’s a resource to make your dialog more assertive and much more precise, as the virtual agent will respond to any changeable scenario
Variable Answers: Now, with eva, it is possible to predict in your flow different responses for the same Intent
Agent Template: a template with 38 ready-made flows fitting in 10 banking use cases that you can customize as you like. Designed with eva and market best practices, so you and your team can optimize time and processes when building a virtual agent.

The new Automated Learning feature enables answering users by searching documents for answers. Upload your documents and train the virtual agent, no intents required

Improved dialog management
Edit your flows by changing the cells in the middle of the dialog, create reusable Jump flows and let the user leave for another flows even if they did not end it (but wants to ask something else)

Last updated 1 year ago