We've launched the beta version of "Codatum CLI" — Codatum's functionality, now operable from your local environment, in collaboration with AI agents.

From fetching, editing, running, and syncing notebooks to executing SQL and searching data sources, you can complete your entire analytics workflow from the command line alone, without ever opening a browser.

Notebooks can be retrieved as plain text files in Markdown format (.cnb.md), enabling a true "BI as Code" workflow: edit in your favorite editor, version control with Git, and review through Pull Requests.

Analytics work that was previously confined to the browser can now be completed entirely with just a terminal and an editor.

Key Features

Edit notebooks as text files: Use cdm notebook clone to pull a notebook to your local machine, and sync with the server via push / pull. You can check diffs anytime with cdm notebook diff.

Run and validate SQL: Execute SQL directly against a connection with cdm sql, and pre-check the validity of SQL and schemas within a notebook using cdm notebook validate / format.

Search data sources: List connections with cdm connection list and search table/column information with cdm catalog search-tables — understand what data is available without opening the GUI.

Live sync preview with the browser: cdm notebook preview bidirectionally syncs your local files with the browser, letting you edit interactively while viewing execution results and charts.

CI/CD integration: Since the same CLI commands run in CI as well, you can build pre-merge validation and rendering checks directly into your pipeline.

Designed for AI agent collaboration: Agents can reference Codatum's specifications directly via cdm doc, preventing incorrect SQL generation caused by schema assumptions — so you can hand off notebook editing to agents like Cursor and Claude Code with confidence.

Use Cases

Build dashboards through conversation
Just tell it "I want to build a dashboard from this data," and Claude Code will explore the tables, construct the SQL, and turn it into charts. Watch the browser preview and simply say "fix this part" to shape the dashboard interactively.

Turn routine work into templates
Once you've built a template, you can hand off everything — from updating data to writing up insights to pushing to the server — with the same standard prompt each time. Weekly and monthly report creation is done with a single prompt.

Manage with GitHub
Manage notebooks on GitHub, review changes via Pull Request, and merge to main — changes sync to Codatum automatically. Even with multiple contributors, you can track who changed what and grow your dashboards safely.

For installation instructions and command details, please see the support documentation. (The support documentation is written in Japanese. Feel free to have your AI read and make use of it.)
Specifications are subject to change without notice.

We hope this helps with your data analysis! We'd love to hear your feedback and feature requests as you try it out.

An "Agent Usage" page has been added to workspace settings. Users with Owner permissions can check AI agent usage across the workspace.

You can view summaries of session count, active users, turn count, and total tokens, along with trends over time and breakdowns by AI profile and by member. You can also filter by member, report, AI profile, source, and status.

In addition, enabling "Save conversation message content to logs" for a given AI profile lets you view the message content and tool call details for each turn in sessions using that profile.
※ This setting is off by default, and message content is not shown unless it's enabled.

Use cases

Since this makes it possible to visualize how AI agents are being used across the workspace, it can help with understanding usage patterns, catching unexpected cost increases early, and reviewing session content as needed for troubleshooting or governance purposes.

※ Specifications are subject to change without notice.

We hope this helps with understanding your team's AI usage! If you have any feedback or requests about this feature, we'd love to hear from you.

A new "Workspace Policy" setting has been added, allowing you to centrally manage security policies across your entire workspace.

What's new

A "Workspace Policy" page has been added to workspace settings. Users with owner permissions can manage policies that apply across the entire workspace using simple toggles.

The newly added policy is "Disallow guest invitations by editors to reports". When this policy is enabled, members with editor permissions will no longer be able to invite guests to reports, centralizing external sharing control to owners only.

Use cases

This prevents the risk of reports containing sensitive internal data being unintentionally shared externally by members with editor permissions. By centralizing external sharing to owners, it becomes easier to enforce data governance policies and meet compliance requirements.

Workspace Policy is available on the Enterprise plan only. Please contact us if you'd like to use this feature.

※Specifications are subject to change without notice.

We hope this helps strengthen your data management and security!
We'd love to hear your feedback and feature requests.

Agent context settings are now more flexible and easier to manage.

What's New

You can now create a dedicated context page for any Notebook by adding a page named .agent inside it. Adding SQL blocks to this page lets you pass metric definitions and calculation logic directly to the Agent.

You can now link specific Notebooks or folders to an AI Profile as context.

• Notebooks and folders from your workspace or teamspaces can be added as context to an AI Profile

• You can restrict access to context (editor/viewer) by managing teamspace permissions

We've also updated the behavior of .agent folders at the workspace level.

• The workspace-level.agent folder has been deprecated and will no longer be loaded automatically

• Existing workspace-level.agent folders have been automatically migrated to link with existing AI Profiles

• .agent folders under teamspaces and private spaces are not affected

Please note that AI Profile context is not loaded during workflow execution.For setup details, please refer to the support documentation.

Specifications are subject to change without notice.

We hope this helps with your data analysis!
We'd love to hear your feedback and suggestions about this feature.

We've added two new actions to Workflows: Run Report and Screenshot. You can now build workflows that automatically refresh your reports with the latest data and deliver the images via email or Slack.

Key Features

Run Report: Execute any saved report directly from a workflow. Enable "Use default parameters" to reset parameters to their defaults before execution, or enable "Update report after execution" to save the results back to the report.

Screenshot: Capture a specific page of a report as a PNG image. You can configure the theme (light/dark) and locale (English/Japanese). When placed after a Run Report step, the screenshot reflects the latest data. The generated image can be attached to downstream Email or Slack actions.

Use Cases

• Automatically run your daily sales report and post the screenshot to a Slack channel

• Refresh weekly KPI reports and send the image to your team by email

• Run and capture multiple reports in sequence to automatically distribute materials for recurring meetings

For setup instructions, please refer to the support documentation.

Specifications are subject to change without notice.

We hope this helps take your data analysis even further!

We'd love to hear your thoughts and feedback on this feature.

We’re pleased to announce the beta release of Codatum Agent, an agent that autonomously performs data analysis, creates Notebooks, and adds charts—all through natural language instructions.

Simply type requests such as “I want to visualize KPIs from this table” or “Analyze last week’s sales trend” in chat, and Codatum Agent will handle everything from SQL generation and execution to Notebook editing.

Even users who have previously spent time operating analytics tools or writing SQL can now move their analysis forward simply by having a conversation.

Two modes for different use cases

• ASK Mode

  • This mode is for when you want to inspect data or Notebook contents, or run queries to check something. It allows you to investigate and validate safely without modifying existing Notebooks.

• Agent Mode

  • This mode is for actually performing actions such as creating or editing Notebooks and adding charts.With a single instruction like “Create a graph of this metric’s trend and add it to the Notebook,” the task can be completed end to end.

Key features

• Operate with natural language

  • You don’t need to write SQL. Simply type something like “Aggregate monthly sales and turn it into a chart,” and the AI will generate and run the query, then add the chart to your Notebook.

• Automatically discovers relevant tables

  • Based on catalog information and table schema details, the agent automatically identifies the tables needed for analysis. You don’t need to manually search for the right tables yourself.

• Flexible context control

  • You can specify a Notebook or catalog as context, allowing the agent to perform analysis with reference to a particular context.

Switch models with AI Profiles based on your use case

You can switch the AI model used depending on the scale of analysis or your accuracy requirements. (Paid option)

Example use cases

• “Create a chart of sales trends by channel using last week’s order data”

  → Automatically identifies the relevant tables, generates and runs SQL, and adds the chart

• “Add a summary of monthly KPIs to this Notebook”

  → Appends content while referencing the existing Notebook

• “Investigate why the conversion rate dropped”

  → Cross-analyzes multiple tables, aggregates findings, and reports the results

• “Create a new Notebook for a sales report”

  → Automatically creates everything from the Notebook structure onward

For setup instructions and detailed usage, please refer to the support documentation.

Service site is here.

Specifications are subject to change without notice.

We hope this helps make your data analysis more effective.

Please give it a try, and we would greatly appreciate any feedback or feature requests you may have.

You can now split XY charts into separate vertical panels per series when multiple series are configured. Each panel uses its own independent Y-axis scale, making it easy to compare metrics with different units or vastly different value ranges side by side.

Highlights

• Independent panel per series: When multiple series are defined, a "Split display by series" option becomes available. Enabling it arranges each series in its own vertical panel with an independent Y-axis, so you can read each metric accurately without overlapping scales.

Use Cases

• Compare trends of revenue (¥) and conversion rate (%) side by side in a single view

• Monitor KPIs across multiple products or channels in aligned panels

• Visualize absolute values alongside ratios where scale differences would otherwise distort the chart

For setup details, see the support documentation.

Specifications are subject to change without notice.

We hope this helps you get more out of your data analysis!
We'd love to hear your thoughts and feedback on this feature.

We've added a new display mode called Grid Layout to the Frame feature. It splits your chart by the values of a selected column and displays multiple small charts side by side. Since each chart shares the same axes and scale, it's easy to spot trends and differences across categories or time periods at a glance.

Highlights

• View up to 16 frames in a grid: Charts are split based on the values of a selected column and displayed in a grid. The number of columns is automatically adjusted to keep the layout as close to square as possible.

• Switch between Grid and Timeline layouts: You can toggle between Grid Layout and Timeline Layout (with playback controls) using the same frame settings. Use Timeline to trace changes over time, or Grid to get a full overview — whichever fits your analysis.

Use cases

• Compare sales trends across regions, stores, or product categories on a single screen

• Evaluate conversion rates side by side by owner or channel

• Spot seasonality by viewing monthly or weekly KPIs across periods

For setup instructions and more details, please refer to the support documentation.

Specifications are subject to change without notice.

We hope this helps take your data analysis further!

We'd love to hear your thoughts and feedback on this feature.

We’ve added a new chart type: Word Cloud. It provides an intuitive way to represent aggregated text data through word size, making it easy to spot frequently appearing keywords and important trends at a glance.

Key features

• Selectable font-size scaling methods

  Choose from three scaling options: linear, square root, and logarithmic. By adjusting the scaling to match your data distribution, you can optimize the layout for better readability.

• Fine-grained control over font size range and spacing

  You can adjust the font size range and spacing between words to suit different use cases.

• Color linked to values

  By default, colors change according to the magnitude of the values, allowing the chart to convey data intensity through both size and color.

• Frame feature supported

  You can switch between word clouds by category or time period, making comparisons easier.

Use cases

• Quickly identify key issue themes by analyzing frequently occurring keywords in inquiries or reviews

• Visually compare access counts or purchase counts by product tag

• Use category distributions from survey responses in presentations for executives

For more details, including setup instructions, please refer to the support documentation.

Specifications are subject to change without notice.

We hope this feature helps support your data analysis.

If you have any feedback or feature requests, we would love to hear from you.

We've added a Frame feature that lets you split and switch chart views by the values of a specific column. You can now explore how data changes over time or compare across categories using a slider or animated playback — making it easier than ever to tell compelling stories with your data. Give it a try!

Key Features

• Slider & Animation Playback: Use the frame controls at the bottom of the chart to manually step through frames or play them as an animation, giving you an intuitive view of how data evolves

• Unified Axis Scaling: To make cross-frame comparisons easier, the Y-axis range, bubble size scale, and heatmap color scale are shared across all frames by default

• Independent Scale Option: You can switch to per-frame independent scaling via Advanced Settings > Frame > Independent Axis Scale

Use Cases

• Animate monthly or quarterly sales trends to highlight growth patterns in presentations

• Step through regional or product category performance comparisons with a slider

• Visualize how correlations shift over time using an animated bubble chart

Supported Chart Types

XY Chart / Circular Chart / XYZ Chart / Hierarchical Chart / Graph Chart (except Drilldown Bar Chart) / Funnel Chart / Waterfall Chart

For setup instructions and more details, please refer to the support documentation.

※ Specifications are subject to change without notice.

We hope this helps take your data analysis to the next level!

We'd love to hear your thoughts and feedback on this feature.