Changelog

When scrolling through an exploration, we now skip database queries for blocks that you quickly move past, reducing load on your data warehouse.

Evals let you systematically test how well Supersimple's AI follows your intended logic and rules.

Build a suite of questions (cases), each with one or more checks written in plain language. An AI judge grades the answers against your checks, such as whether the AI used the right metric and model, applied a specific filter, or excluded certain records.

Author suites as YAML and run them from the UI or CLI, including in CI. Our updated AI coding agent skill also helps your coding agent write and run evals.

See the Evals docs to get started.

CLI v2.30.0 brings two new features to help you manage answer guidance as code:

• Answer guidance can now be imported and exported as YAML using supersimple export and supersimple import.
• A new supersimple sources list command lists database connections and other integrations, together with their IDs, so you can reference them in your answer guidance YAML.

A few UI tweaks to allow more compact reports:

• The notebook grid has been updated to allow six blocks side-by-side.
• Variable blocks now take up much less space.

When Supersimple detects that an Inbox finding may have been addressed, it now suggests closing it and shows the supporting conversations.

Custom formulas can now reference fields of related data models. In the autocomplete dropdown, pick a field from the current model or click through relations until you reach the model that you need.

You can now drag and drop explorations between folders and Personal/Team sections in the left sidebar.

Click the new + button in an exploration's tab bar to create a tab inline, without opening the sidebar.

Click an exploration's name to open a menu with actions to save, pin, download, or schedule an export. You can also edit its details, move it to another folder, or delete it from the same menu.

You can now turn horizontal scrollbars on or off for tables. Scrollbars are enabled by default on Windows and Linux, and disabled by default on Mac.

You can turn them on or off under Settings → Appearance or from the command menu.

AI can now look up your saved explorations, copy over any content and reuse their logic. It can use both personal and team explorations you have access to and link back to the blocks it used.

supersimple export now includes your own Personal space explorations alongside Team ones, so they can be kept in step with data model changes too. They're marked with visibility: personal in the YAML:

explorations:
  # Team exploration – no visibility needed
  revenue-overview:
    name: Revenue overview
    folder: Finance
    view:
      cells: [...]
 
  # Personal exploration – imported into your own Personal space
  weekly-signups:
    name: Weekly signups
    visibility: personal
    folder: My drafts
    view:
      cells: [...]

When imported, they land back in your own Personal space. Other users' personal explorations are never included in your export.

Read more in the CLI docs.

Each Inbox item can now be opened up in a detail page. You can use this to share specific inbox items with teammates.

You can now hide individual columns of a data model from users who shouldn't see them. Add an access block to any model property, and only users matching its conditions can see, filter or use that column – everyone else still gets the rest of the model.

properties:
  salary:
    name: Salary
    type: Number
    access:
      user_parameters:
        department: hr

To avoid repeating the same conditions across models and columns, define them once under access_rules and reference them by name, like access: hr.

Read more in the model access control guide.

When you pick a field for a filter, a grouping, or another step, the list now has a Relations section. Open a relation to see the fields of the related model, and keep going through its own relations. For example, filter users by the payment plan of their account, without adding the payment plan column first.

Multi-select dropdowns across Supersimple (including Variables) now have an Only button on each option for quickly deselecting everything else and selecting just the one option.

Press ⌘K to navigate Supersimple and take quick actions without lifting your fingers off the keyboard.

Use the command menu to:

• Jump between saved explorations, Inbox, and Settings.
• Ask AI about the selected block or start a new question.
• Select, duplicate, or delete blocks.
• Save or rename explorations.
• Switch between light and dark mode.

Under account settings, each configured Alert now shows its author, and your personal alerts are shown separately from team alerts.

Code blocks now support TypeScript and Scala alongside Python. Use data from other blocks in your exploration to write custom calculations and display the results alongside your charts and tables.

The new Restricted user role lets you give partners and contractors access to selected parts of your workspace. Restricted users can only see exploration folders and data models you explicitly grant them access to, keeping the rest of your team's work private.

SQL blocks can now use exploration variables; autocomplete will suggest variables and set up the right syntax as you type their name.

Reference a variable by name with {{variables.Payment plan}}. Date range variables also expose .from and .to, so one control can set both ends of a date filter.

Saved explorations can now be organized into folders across separate Personal and Team spaces.

Folders are available directly in the sidebar and data catalog, making saved explorations easier to organize and find as your team's library grows.

Personal explorations remain private, but you can share a point-in-time snapshot with teammates using Copy link.

Previous edits to saved explorations can now be found under Version history in the right sidebar.

Each version shows a summary of what changed, as well as individual changes to each block. Edit history can also be accessed by your AI agents through Supersimple's MCP server.

Saved explorations can now be exported from the top menu bar on a recurring schedule or as a one-time download.

For scheduled exports, choose the frequency, delivery cadence and timing, and recipients. Both options let you choose between light/dark mode and the width at which your report should be captured.

Guide AI behavior to document gold-standard paths for dealing with specific types of questions. When answering user questions, AI dynamically loads in relevant guidance entries.

For database questions, you can copy finished tables and charts from an exploration and paste them directly into a guide.

Written guidance can be used to provide additional instructions for how to analyze and present answers, or what to search for from where.

Manage answer guidance under Settings → AI → Answer guidance.

Your history of exploring data in Supersimple is now automatically saved and summarized in your personal activity history. Open the new Activity tab on the History page to pick up exactly where you left off.

Your history is grouped into sessions based on both time and context-switching, summarized, and displayed with a full timeline of the steps you took.

Other improvements

• You can now rename your database connections and adjust their connection timeout under the Integrations tab in Settings.
• AI is now aware of your disabled (unchecked) integrations, so it can let you know when you seem to be trying to use one of them.

Date fields in your data model can now declare the calendar precision they represent. For example, if a field contains one value per month, set its precision to month:

properties:
  subscription_month:
    name: Subscription month
    type: Date
    precision: month

Supersimple uses the declared precision by default when grouping the field, while still letting you choose a different precision in an exploration. It also preserves the precision through derived models, custom formulas, funnels, and date aggregations.

Supported precisions are year, quarter, month, week, day, and hour.

Read more in the docs.

Supersimple now continuously analyzes AI agent traces against your data models and provided context. It proactively surfaces missing data, ambiguous definitions, missing context, and unclear business terminology.

Supersimple's Inbox detects trends across different conversations, workflows, and users, grouping related findings into actionable items with links to the original conversations.

Data teams use the Inbox to prioritize high-impact improvements to data models and AI context, then mark them as resolved once addressed.

Inbox is also accessible via the Supersimple MCP, allowing your favorite coding agent to use the Inbox as input for future work.

Read more about Supersimple Inbox.

Supersimple's Model Context Protocol (MCP) server now lets you use Supersimple's AI with your entire company's context, right from inside Claude, Cursor, or any other MCP-capable assistant.

Once it's connected, your favorite AI assistant gains an Ask Supersimple tool to use whenever it needs to access any of the data you've connected to Supersimple. Answers respect your access, just like when asking from inside Supersimple's app.

See our MCP server docs to get set up.

If you are deciding whether to connect Claude directly to your data stack or use a governed analytics layer underneath it, see our Supersimple vs Claude for BI comparison.

You can now connect any custom MCP (Model Context Protocol) server to Supersimple. Users can select it under the AI sources selector, alongside Supersimple's native integrations.

To enable proper access control, each user can separately log in to every given MCP server – authenticating it to act on their behalf.

Learn more in our docs