> For the complete documentation index, see [llms.txt](https://help.rhythms.ai/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://help.rhythms.ai/release-notes/july-15-2026-release-notes.md). # July 15, 2026 Release Notes ***This week:*** *Author Mermaid diagrams directly in any document, preview CSV files as scrollable tables, and see check-in labels as a column across your OKR views. Plus the Smart Activity Log is now on for everyone, and long-running chats now complete cleanly.* ## New Features πŸ’» **Diagrams in Documents** Drawing architecture flows, process maps, or timelines used to mean leaving Rhythms to paste in a screenshot. Now you can author Mermaid diagrams directly inside any document β€” flowcharts, sequence diagrams, Gantt charts, mind maps, and more. The AI agent can generate and edit them too, so you can describe what you want in chat and get a live diagram back. Diagrams render as interactive SVGs and round-trip cleanly through markdown, so they stay editable no matter how they were created. *Try it: Open any document β†’ ask the AI agent to draw a diagram, or type a mermaid code block directly.* πŸ’» **CSV File Previews** Uploading a CSV used to mean downloading it again just to see what was in it. Now CSV files render as a scrollable, accessible table right in the Review panel and on chat artifact cards, so you can verify the data before acting on it. Previews cap at 100 rows and 50 columns; the full file is always available to download. *Try it: Upload a CSV file in chat β†’ click Review on the artifact card to see it as a table.* πŸ’» **Check-in Label Columns** Labels you apply at check-in time were only visible in the moment β€” they disappeared from the Explorer view the second you moved on. Now the last check-in label for each goal surfaces as a dedicated column, a filter, and a CSV export field across every OKR Explorer view. Filter your whole portfolio by label, spot patterns across teams, and pull the data into external reports without any manual work. *Try it: Open the OKR Explorer β†’ add the Last Check-in Label column from the column picker.* πŸ’» **Smart Activity Log for Everyone** Seeing who changed what in a document β€” and when β€” used to mean digging through version history or asking around. The Smart Activity Log now shows a live feed of edits, check-ins, and goal updates in a panel inside every document and goal, so you can see what moved and who touched it at a glance. It’s on by default for all workspaces. *Try it: Open any document or goal β†’ look for the activity panel on the right side.* ## Key Improvements * **One Continuous Reply Across Chat Steps** β€” Multi-step chat responses now stream as a single reply instead of appearing in disconnected fragments. Watch the answer come together in one flow, not piece by piece. * **Long-Running Chats Complete Cleanly** β€” Multi-step and backgrounded chat sessions now run to completion, even across long tool calls and large response streams. * **Sharing Insights Posts a Comment, Not an Email** β€” When you ask Rhythms to share document-tied insights with a colleague, it posts a comment directly on the document and @mentions the recipient β€” keeping the insight anchored to its source and easy to navigate back to. * **Live Updates Stay On When You Share** β€” Sharing a document now leaves its live-update refresh setting untouched, so your dashboard stays current after you send the link. --- # Agent Instructions This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com. ## Querying This Documentation If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question. Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters: ``` GET https://help.rhythms.ai/release-notes/july-15-2026-release-notes.md?ask=&goal= ``` `ask` is the immediate question: it should be specific, self-contained, and written in natural language. `goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `build a script that syncs our docs to a CMS` lets GitBook tailor the answer to that use case. The response will contain a direct answer to the question and relevant excerpts and sources from the documentation. Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.