Getting Started

Most likely, your users utilize at least one of the following prominent websites: YouTube, Amazon, and Facebook. All these platforms share a crucial aspect: exceptional search functionality. The reason for their superior search capabilities is due to the hundreds or even thousands of employees working full-time on search optimization.

As a result of experiencing exceptional search on these platforms, users now anticipate the same level of search functionality on every website and application they use. However, if your company is not primarily a search company, it may not be practical to hire a dedicated team of developers to create a new search engine. offers a solution by providing software and tools that allow you to efficiently and flexibly implement insightful search functionality on your own sites and applications. Zevi recently launched chatscout- an AI based shopping assistant which delivers human-like conversations and relevant products.

How does work ?​

To get started with Zevi.AI, the first step is to onboard and send your data in the proper format to our servers. Once the data is uploaded, you can start testing the search functionality using simple requests with your preferred choice of API clients by writing the code. This creates the basic structure of a ZeviAI search solution.

What is search?

An AI-driven NLP search, lets users search in the way that comes most naturally to them - and this is just the beginning. Our goal is to challenge the status quo in a space that hasn’t changed for decades, and transition context-powered search from a ‘good-to-have’ to an absolute essential for any growth-focused brand.

What is chat?

Chat offers a search feature where users can ask questions and receive answers through a chat interface, typically powered by artificial intelligence (AI) and natural language processing (NLP) technologies. Chat-based search can be implemented on various platforms, including mobile apps, web browsers, and messaging apps. With chat-based search, users can ask questions in a conversational style, using natural language. The AI-powered system then analyzes the question, understands the context and intent, and generates a response with a list of products that best suit the user's query in a human-like manner. The system can also learn from the user's behavior and preferences and improve its responses over time.


Neural Search

Neural Search combines the precision of keyword search with the deep understanding of natural language and contextual relevance provided by AI-based vector search .On every keystroke, Neural Search performs a hybrid keyword and vector search, merges the results, and ranks them based on relevance so that searchers get fast and accurate results that align with their search intent.

What are total no of searches​ ?

This metric refers to the total number of searches conducted by users on a website or search engine within a given time frame. It provides an overall measure of user engagement with the search functionality and can help website owners to identify trends in search behavior.

What is Click-through rate (CTR)​ ?

This metric measures the percentage of users who click on a search result after conducting a search. It is calculated by dividing the number of clicks on a search result by the total number of times that result was shown (i.e., the number of impressions). CTR is often used as an indicator of the relevance and effectiveness of search results, and can be used to optimize search functionality and improve user engagement.

What are broken searches​ ?

This term may refer to searches that return no results or to searches that result in errors or broken links. Broken searches can be a frustrating experience for users and can lead to reduced engagement with the website or search engine. Identifying and addressing broken searches is important for improving the overall user experience and ensuring that users are able to find the information they are looking for.