​
AI Context

Inari uses a heavy mixture of LLMs, RAG, and clustering techniques for analyzing customer interactions, surfacing insights, linking feedbacks, and generating issues. If you’ve ever used ChatGPT, Claude, or other AI chatbots, the quality of AI results can literally be improved >100x by providing deep context about your business and problems to the models. We’ve seen dramatic improvement in results throughout Inari after an org fills out all the context accurately - we strongly recommend filling everything out here to get the best experience out of Inari.

​
Org and Space Descriptions

Provide detailed context about your organization, teams, or products in Organization Description and Space Context. This context is added in every single AI action for the org or space - this enables the model to know what your company or product is about, what features do or don’t exist, and preferences your team may have for improving the AI results Example: 
Inari is an AI copilot for product teams that surfaces customer insights and revenue generating product opportunities from customer data auto-magically using AI.

Inari consolidates customer feedback across data sources, automatically analyzes feedbac, surfaces insightful customer insights, uncovers actionable product opportunities, and provides detailed qualitative product analytics.

​
Projects [Coming Soon]

This is coming soon but you will be able to provide web links to Projects about your organization such as developer documentation, help centers, and other wikis so that Inari can fetch it, index it, and retrieve the specific chunk of context when using LLMs to generate personalized results. We strongly recommend providing a link to your developer docs or help center so that Inari can fully understand the context behind your business and improve its results.

​
Domain

You can set a Domain for your organization. Inari will look for customers with emails linked to this domain across your feedback and filter them out of the analysis so that results are not impacted by comments from internal teammates. This is most relevant when connecting sources such as Gong, Intercom, or Zendesk where the majority of a customer interaction might come from an internal teammate which you don’t want to collect feedback from.

​
Competition

You can set a list of Competition for your organization. Inari will look for exact competitor name matches across all of your feedback then adjust the treatment of the analysis accordingly. For example: if a customer says something positive about a competitor, the sentiment score will be treated negatively instead of positively.

​
Language and Region

You can customize which Language to return all AI results in across feedback analyzed, summaries generated, and insight and issues created.

​
Personalizing Feedback Analysis

You can customize how the AI feedback analysis runs in Inari in the Feedback page. You can set custom prompt instructions for how the feedback is analyzed, context around which types of quotes to extract, and instructions on which types of feedback to ignore when filtering spam. Feedback highlights that are manually approved in each highlight card will also show up in the Feedback Settings page. You can set whether those highlights are used as examples of the types of feedback that you’d like Inari’s AI to extract moving forward.