Uncover rich insights instantly with your ultimate AI research agent

Gen is an AI Research Agent that allows you to have a conversation with your own structured and unstructured data in a chat format – all within Yabble’s secure, walled garden data environment. Gen uses natural language and SQL tools allowing you to ask your data all types of questions with Gen able to answer your question instantly and conversationally. Gen allows you to ask questions on your own proprietary dataset – whatever topic that might be. Once your dataset is uploaded into the Yabble platform you can prompt Gen to query your dataset and provide high-level insights, generate tables, filter by custom variables, or dive deeper to explore your data holistically – all with data security peace of mind. 

Simply type a question related to your own dataset, and Gen will do all the work for you.

You can specify which particular part of your project your question relates to, or for more general questions, ask them across ‘All Questions’. 

Yes, Gen can chat with any type of qualitative and quantitative data you have in the Yabble platform, including raw transcripts, open-ends, quantitative studies, and more. 

While Gen can chat with data you upload through our Count tool, it has not been built to chat directly with the themes, sub-themes and sentiment generated by Count. Gen can identify themes from this data using the tools in its toolbox and via your natural language querying, but results may differ from the output from Yabble Count.How do I get the most out of Gen? 

As Gen is an agent utilizing natural language processing, it will understand what you are trying to achieve even if you do make the odd spelling mistake. However, Gen will not like characters such as ‘[' or '>' as these are not generally used in conversational text. 

Being specific always helps. Rather than asking ‘What are the main complaints people had?’, ask something like ‘What are the main comments people made with respect to pricing?’. By saying the word ‘pricing’ in the question, Gen is able to apply a hybrid search that picks up the word pricing, and everything related, allowing for a better response. 

As an example, I want to know what’s really driving people's opinion about the prices at Walmart. 

• OK: Why?
• Good: Why did people say that?
• Better: Why did people say that about pricing?
• Best: Why did people have those concerns about pricing at Walmart? 

Gen has its own context builder and should be able to handle most questions it receives. However, it is helpful to be as specific as possible. 

Gen isn't specifically designed to extract verbatim quotes from transcripts, but it can provide varied responses when asked for examples of what respondents have said on a topic. The responses are randomized, meaning you may receive different quotes each time you ask. 

Try phrasing your question like: 

• "Can you give me a direct quote about X topic?"
• "Can you provide some examples of what respondents have said about Y topic?" 

Gen will aim to surface relevant responses, but the exact quotes may differ with each query. If you're looking for a broader selection, you can refine your request or ask multiple times. 

You can ask Gen about specific transcripts, but results may vary. It does not retrieve all responses at once, and the selection of quotes is randomized. 

To improve accuracy, try referencing details such as the respondent's name (if available) or the file name. For example: 

• "Can you tell me what [respondent name] said about [topic]?"
• "What are respondents saying about [Y topic] in the file 'interview.3'?" 

Gen will attempt to surface relevant responses based on the dataset, but results may differ each time you ask. 

Yes! While Gen started as a language model, we have now enabled an SQL querying process in Gen, allowing for you to get quantitative insights from your structured data conversationally. You can ask Gen for percentages and totals, as well as to present these in tables, and provide summaries. 

Note: This feature works on structured variables only, not unstructured question responses. 

Asking Gen an identical/similar question in the same chat will often give different responses due to the way Large Language Models work. Often the subsequent responses can add more detail, as Gen will not want to repeat itself. However, the insight that is extracted should remain consistent. 

The more detail you give, the more information Gen has to work with. However, you can simply ask a question like ‘Why?’ and Gen will go and find context from your previous conversation. 

Gen will find responses related to your question in order to give an insightful answer. It may not need your entire dataset to give an answer like ‘most people preferred…’ 

Further, survey data can contain irrelevant answers. Gen will filter these answers out or ignore them in its response generation. 

For now, Gen is designed to analyze data in English. However, as Large Language Models are improving their multi-lingual capabilities, we have found that Gen will respond in other languages if prompted. Please watch this space while Gen becomes multi-lingual!