Displayr

Problem: Customers are increasingly using Claude as part of their research and analysis workflow. In this case, Yousician already uses MCP connections with Snowflake and Atlassian, allowing Claude to pull product data and Confluence context directly into Claude conversations. It would be great if Claude could connect to Displayr in the same way. Request: Enable Displayr to connect with Claude via MCP, so users can query, retrieve, or work with Displayr project content, survey data, outputs, and analysis context from within Claude. Why it matters: Claude is becoming a potential alternative to Displayr for both qualitative and quantitative analysis. If Displayr can integrate with Claude rather than sit outside that workflow, it becomes easier for customers to justify keeping Displayr as part of their analysis stack.

There should be a function explicitly to summarize the entire report, to create an executive summary, for example, at the start of the report. This should consider all outputs and commentary, whether previously created via AI or the user.

Do not force the Chat panel to open by default for all users. Proposed behavior: New users → Chat panel opens by default Existing users → Properties panel opens by default (or retain previous behavior) Alternative (preferred if simpler): Persist the last-used side panel per user (Chat or Properties) and restore on load Problem being solved: Current default (Chat open) introduces unnecessary friction for experienced users who primarily use the Properties panel for variable and table configuration.

I want more control over the AI-driven renaming of variables in Displayr. The current automatic renaming is not intuitive and I would prefer to have the option to rename variables myself.

I would like the ability to create custom agents within Displayr to analyze data in a way that meets my specific requirements or my client's needs.

Example: a tracking survey where the user must translate the responses for the new wave of data. Re-running the AI Text Translation variable with new responses can change previously translated responses and impact Text Classification. Add an option for the user to be able to run the AI translations only on new responses, while keeping all previously coded responses intact.

AI tools are unnecessary please put them in the background if you have to keep them and not have them open with every document.

Please automatically put the results of the Research Agent into its own folder.

When combining variables Q8a_1, Q8a_2, Q8a_3... it names the new variable 'Q8a Factors that impact XYZ', rather than just 'Factors that impact XZY'. Currently, it doesn't include the question number in the new variabl,e which makes it difficult to find.

The Data Preparation agent doesn't match how we clean our data. We'd like the ability to customize the data preparation prompt to better suit our needs.