[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"productUpdate-en::codatum-cli-a-command-line-tool-for-collaborating-with-ai-agents-now-available-in-beta:en":3,"productUpdatesNearDate-en:timestamp-2026-08-04T00:00+09:00:en":18},{"id":4,"title":5,"slug":6,"description":7,"body":8,"tags":9,"coverUrl":7,"coverMediaUrl":13,"ogImageUrl":14,"createdAt":15,"updatedAt":15,"datePublished":16,"locale":17},"1vVyWDV9hrx1FWBSw4YIrC","Codatum CLI, a Command-Line Tool for Collaborating with AI Agents, Now Available in Beta","codatum-cli-a-command-line-tool-for-collaborating-with-ai-agents-now-available-in-beta","","\u003Cp>We've launched the beta version of \"Codatum CLI\" — Codatum's functionality, now operable from your local environment, in collaboration with AI agents.\u003C\u002Fp>\u003Cp>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.\u003C\u002Fp>\u003Cp>Notebooks can be retrieved as plain text files in Markdown format (\u003Ccode class=\"hljs\">.cnb.md\u003C\u002Fcode>), enabling a true \"BI as Code\" workflow: edit in your favorite editor, version control with Git, and review through Pull Requests.\u003C\u002Fp>\u003Cp>Analytics work that was previously confined to the browser can now be completed entirely with just a terminal and an editor.\u003C\u002Fp>\u003Cp>\u003Cb>Key Features\u003C\u002Fb>\u003C\u002Fp>\u003Cp>\u003Cb>Edit notebooks as text files\u003C\u002Fb>: Use \u003Ccode class=\"hljs\">cdm notebook clone\u003C\u002Fcode> to pull a notebook to your local machine, and sync with the server via \u003Ccode class=\"hljs\">push\u003C\u002Fcode> \u002F \u003Ccode class=\"hljs\">pull\u003C\u002Fcode>. You can check diffs anytime with \u003Ccode class=\"hljs\">cdm notebook diff\u003C\u002Fcode>.\u003C\u002Fp>\u003Cp>\u003Cb>Run and validate SQL\u003C\u002Fb>: Execute SQL directly against a connection with \u003Ccode class=\"hljs\">cdm \u003Cspan class=\"hljs-keyword\">sql\u003C\u002Fspan>\u003C\u002Fcode>, and pre-check the validity of SQL and schemas within a notebook using \u003Ccode class=\"hljs\">cdm notebook validate\u003C\u002Fcode> \u002F \u003Ccode class=\"hljs\">\u003Cspan class=\"hljs-built_in\">format\u003C\u002Fspan>\u003C\u002Fcode>.\u003C\u002Fp>\u003Cp>\u003Cb>Search data sources\u003C\u002Fb>: List connections with \u003Ccode class=\"hljs\">cdm connection list\u003C\u002Fcode> and search table\u002Fcolumn information with \u003Ccode class=\"hljs\">cdm catalog \u003Cspan class=\"hljs-keyword\">search\u003C\u002Fspan>\u003Cspan class=\"hljs-operator\">-\u003C\u002Fspan>tables\u003C\u002Fcode> — understand what data is available without opening the GUI.\u003C\u002Fp>\u003Cp>\u003Cb>Live sync preview with the browser\u003C\u002Fb>: \u003Ccode class=\"hljs\">cdm notebook preview\u003C\u002Fcode> bidirectionally syncs your local files with the browser, letting you edit interactively while viewing execution results and charts.\u003C\u002Fp>\u003Cp>\u003Cb>CI\u002FCD integration\u003C\u002Fb>: Since the same CLI commands run in CI as well, you can build pre-merge validation and rendering checks directly into your pipeline.\u003C\u002Fp>\u003Cp>\u003Cb>Designed for AI agent collaboration\u003C\u002Fb>: Agents can reference Codatum's specifications directly via \u003Ccode class=\"hljs\">cdm doc\u003C\u002Fcode>, preventing incorrect SQL generation caused by schema assumptions — so you can hand off notebook editing to agents like Cursor and Claude Code with confidence.\u003C\u002Fp>\u003Cp>\u003Cb>Use Cases\u003C\u002Fb>\u003C\u002Fp>\u003Cp>\u003Cb>Build dashboards through conversation\u003C\u002Fb>\u003Cbr>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.\u003C\u002Fp>\u003Cp>\u003Cb>Turn routine work into templates\u003C\u002Fb>\u003Cbr>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.\u003C\u002Fp>\u003Cp>\u003Cb>Manage with GitHub\u003C\u002Fb>\u003Cbr>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.\u003C\u002Fp>\u003Cp>\u003C\u002Fp>\u003Cp>For installation instructions and command details, please see the \u003Ca href=\"https:\u002F\u002Fcli-docs.codatum.com\u002F\" target=\"_blank\" rel=\"noopener noreferrer\">support documentation\u003C\u002Fa>. (The support documentation is written in Japanese. Feel free to have your AI read and make use of it.)\u003Cbr>\u003Ci>Specifications are subject to change without notice.\u003C\u002Fi>\u003C\u002Fp>\u003Cp>We hope this helps with your data analysis! We'd love to hear your feedback and feature requests as you try it out.\u003C\u002Fp>",[10],{"id":11,"name":12},"new_feature","New Feature","https:\u002F\u002Fvideos.ctfassets.net\u002Fggtw2zqmifs5\u002F2rIPfkD2KWg1kEUqSsppEs\u002Ff43357df534292489b31c4f73c3983e8\u002Fcli_short2_full.mp4","https:\u002F\u002Fimages.ctfassets.net\u002Fggtw2zqmifs5\u002F4Atj1jrQQFIrs164vRx9QJ\u002F0b27b9d4362af0d4dc050067fabc0b81\u002Fog_update.png","2026-08-04T11:00:10.553Z","2026-08-04T00:00+09:00","en",[19,29],{"id":20,"title":21,"slug":22,"description":7,"body":23,"tags":24,"coverUrl":7,"coverMediaUrl":26,"ogImageUrl":26,"createdAt":27,"updatedAt":27,"datePublished":28,"locale":17},"4iCBwduEb173bCFBKuRAXN","Agent Usage page added","agent-usage-page-added","\u003Cp>An \"Agent Usage\" page has been added to workspace settings. Users with Owner permissions can check AI agent usage across the workspace.\u003C\u002Fp>\u003Cp>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.\u003C\u002Fp>\u003Cp>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.\u003Cbr>※ This setting is off by default, and message content is not shown unless it's enabled.\u003C\u002Fp>\u003Cp>\u003Cb>Use cases\u003C\u002Fb>\u003C\u002Fp>\u003Cp>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.\u003C\u002Fp>\u003Cp>※ Specifications are subject to change without notice.\u003C\u002Fp>\u003Cp>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.\u003C\u002Fp>",[25],{"id":11,"name":12},"https:\u002F\u002Fimages.ctfassets.net\u002Fggtw2zqmifs5\u002F76LuUL2QBLAXIqBsOtJJOh\u002Fbf058b69489f50c6276599021c3ac0fc\u002Fe6818345-7f06-4bba-96cc-d702493ea49e.png","2026-07-30T23:00:09.363Z","2026-07-31T00:00+09:00",{"id":30,"title":31,"slug":32,"description":7,"body":33,"tags":34,"coverUrl":7,"coverMediaUrl":35,"ogImageUrl":35,"createdAt":36,"updatedAt":36,"datePublished":37,"locale":17},"4kEJ85Q0oSfA1tzd7Xtk0P","Workspace Policy Feature Added","workspace-policy-feature-added","\u003Cp>A new \"Workspace Policy\" setting has been added, allowing you to centrally manage security policies across your entire workspace.\u003C\u002Fp>\u003Cp>\u003Cb>What's new\u003C\u002Fb>\u003C\u002Fp>\u003Cp>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.\u003C\u002Fp>\u003Cp>The newly added policy is \u003Cb>"Disallow guest invitations by editors to reports"\u003C\u002Fb>. 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.\u003C\u002Fp>\u003Cp>\u003Cb>Use cases\u003C\u002Fb>\u003C\u002Fp>\u003Cp>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.\u003C\u002Fp>\u003Cp>\u003Cb>Workspace Policy is available on the Enterprise plan only.\u003C\u002Fb> Please contact us if you'd like to use this feature.\u003C\u002Fp>\u003Cp>※Specifications are subject to change without notice.\u003C\u002Fp>\u003Cp>We hope this helps strengthen your data management and security!\u003Cbr>We'd love to hear your feedback and feature requests.\u003C\u002Fp>",[],"https:\u002F\u002Fimages.ctfassets.net\u002Fggtw2zqmifs5\u002F4SamJcJYadviuHduVj0xiV\u002F8b967ebdb620e463645f21af9451c5cc\u002FFrame_1.png","2026-06-01T00:00:05.621Z","2026-05-29T00:00+09:00"]