Feature Request

We have received a request from the customer to include a unique request/response ID in the exported CSV from Eddy Analytics. This would provide a unique reference ID for each user request, helping to avoid duplication and enabling better tracking of valid requests with ID.

Pain Point: Users frequently encounter "no search results" in the knowledge base, indicating missing content or gaps that lead to frustration and incomplete user support. Suggested Feature: Add the capability to analyze "no search results" data and recommend either creating new articles or updating existing ones with relevant information. This would ensure that content gaps are promptly addressed, improving overall user satisfaction and knowledge base comprehensiveness.

As we are aware, AI generators, including Eddy, can sometimes produce inaccurate information when they do not know the answer. This issue, known as "AI hallucination," can be problematic. To address this, we propose creating a private repository where we can store carefully selected and verified content. This repository will serve as a reference for Eddy, allowing it to access accurate answers to questions it previously answered incorrectly. The private repository will be a secure, internal space managed by authorised personnel, ensuring that it contains only verified information. It will not be visible to customers or readers, but Eddy will have access to it to fetch correct answers. Regular updates to the repository will ensure that it covers new areas where Eddy might hallucinate, improving accuracy and reliability over time.

The customers are skeptical about enabling Eddy AI assistive search for their document site readers. They want to try the AI assistive search, gain confidence of its capabilities, and then release it to their document site readers. We need to give an option to enable Eddy AI assistive search for only the team accounts, this will help the customers by letting them try Eddy with production data so that they can experience what their document site readers would experience.

Essie Writer should pop up also for larger selections. Currently I can only select blocks of the same type so the popup menu comes up, for example, body text blocks, or numbered blocks. If I select for example body text and numbered blocks, I don't get a popup menu and hence no Essie Writer. What I want to do is select a whole big bunch of content and then tell Essie to work on that, instead of going paragraph by paragraph.

To enable AI Assistive search inside the Freshdesk and Freshservice extensions, On reply to tickets in freshservice and freshdesk extensions, we can use algolia search to search the knowledge base, we can enable Eddy here to help the users capitalize on their purchased AI Assistive search add-on.

We don't have much control over how AI responds that's specific to our brand outside of "friendly" and other tones. It would be great if we can teach AI specific Voice and Tone. For example: Refer to "Agents" as "Heroes" avoid using the word "disabled" and use "deactivated" instead It would also be great to have hallucination checks where if AI seems to hallucinate by attempting to provide an interpretation of an answer in our KB but is not completely accurate, it would be great if there's a feature that flags Admins of a possible response that AI attempted to create but did not because it might incorrect, then allow admins to review that response to determine how it could be improved.

Implement an integration between Document360 and version control systems like Git and Azure DevOps to enable automatic generation of documentation based on code repositories. This feature would allow Document360 to: Read source code: Access and analyze code directly from Git or ADO repositories. Generate documentation: Automatically create and update documentation based on the code structure, comments, and metadata, ensuring that documentation stays in sync with the latest code changes. Support multiple languages: Recognize and support documentation generation for various programming languages and frameworks.

Customer has requested for a possible integration or availability to Microsoft Copilot Studio Services, which can ideally help them build their own chatbot to read through their site.

It would be great if Eddy search able to include a clickable link in the generated answer rathar than providing citation.