For all its amazing achievements in past decades, Information Technology had yet to solve a problem that all of us face every day: quickly and easily finding the information we need. Whether we’re looking for the latest version of the company travel policy, or asking a more technical question like “How many members can I invite in my Monday account?”, we never seem to be able to get the correct answer right away. Sometimes, we never get it at all!
Not only are these issues frustrating for users, they’re also responsible for major productivity losses. According to an IDC study, the cost of inefficient search is $5,700 per employee per year: for a 1,000-employee company, $5.7 million evaporate every year, not counting the liability and compliance risks imposed by low accuracy search. Factor in customer facing documentation and further untold millions are lost due to frustrated customers not being able to find what they need to get the job done with the product.
This problem has several causes. First, most enterprise data is unstructured, making it difficult to pinpoint the information you need. Second, data is often spread across silos, specialized knowledge bases and stored in heterogeneous backends: network shares, relational databases, 3rd party applications, one-off vendors and more. Lastly, keyword-based search systems require figuring out the right combination of keywords, and usually return a large number of hits, most of them irrelevant to our query.
Taking note of these pain points, we decided to help Monday users build the search capabilities that they deserve.
What it does
With just a few clicks, Monday QnA enables users and customers to index structured and unstructured data stored in different backends, such as file systems, applications, Intranet, and relational databases as long as their link is accessible and present in Monday.com. Monday QnA is optimized to understand complex language across domains and can auto-train itself based on the content and documents it encounters. This multi-domain expertise allows Monday QnA to find more accurate answers. In addition, it allows for explicit fine-tuning of the relevance of results, using criteria such as authoritative data sources or document freshness.
Even when a query matches a large number of documents, Monday QnA can come up with a suggested high confidence answer to present to the user and point specifically to a highlighted word or line in the supporting document. For more factoid type questions (who, when) it can go one step further by returning the exact answer from the document, instead of just returning the document itself. This is enabled by QnA being able to understand context and extract relationships within the content.