Changelog

We've been busy at Brainfish, introducing new multimodal support in search alongside this month's search engine upgrades:

Native Video Uploads and Videos in Answers

In response to customer feedback, we've upgraded our multimodal search with native video support. Now, Brainfish can deliver videos in Help Center answers, as well as images (when enabled from Search Configuration). To support this new advancement, we have incorporated native video support within the editor. Customers can now upload videos up to 500MB in size directly into the editor, eliminating the need for external hosting platforms such as YouTube, Vimeo, or Loom.

Brainfish Brand Guidelines

We've also launched our own Brand Guidelines to assist with the increasing demand for design and PR. The guidelines offer a curated set of specifications for Brainfish in a user-friendly format. This makes it easier for everyone to represent our brand accurately and consistently.

We're delighted to announce another significant update aimed at amplifying our answer experience:

Combination Language Models (LLM) for More Customers

We are now expanding the reach of our combination LLM models to serve more customers. These advanced models perform multiple queries and generations in real time behind the scenes to create a "best of all" answer for users. This key advancement will lead to more precise, comprehensive, and satisfactory answers.

‍

We've also improved our spell checking capability on our search engine, to better handle misspelled searches contextually depending on the business.

We're excited to announce a series of significant updates this week, especially designed to expand our reach and enhance user experience:

Financial Services Support

In our journey to support various industries, we've launched several functionalities specifically designed for regulated sectors like financial services. With these new tools, we can now guarantee that our AI search answers will pass all necessary legal checks. This furthers our commitment to provide accurate, relevant, and prompt customer service across diverse domains.

Markdown in Help Center's Supporting Text

To improve visibility and user interaction, we now allow markdown formatted information text underneath the Search bar on the Help Center. This feature can be configured using Markdown in the Search configuration tab of Settings.

Zendesk Import Cleanup

Understanding the need for seamless integration, we've undertaken a comprehensive cleanup of the Zendesk import function. This will better support weird formats and broken articles when importing from an old Zendesk account.

Taking AI-generative search to the next level, we bring you a significant update this week:

Machine Learning Relevancy Checks and Precision

We're implementing Machine Learning (ML) relevancy checks and precision features to further improve our service's efficiency and accuracy. These new additions will facilitate better background scoring of answers and enable our models to self-check their performance in real time when generating responses. Consequently, this will ensure answers generated are more direct, relevant, and significantly reduce the risk of incorrect information (hallucination).

This state-of-the-art, self-checking function will guarantee the highest degree of precision in our deliverables – making sure that your customers are getting the most accurate and prompt information every time.