> For the complete documentation index, see [llms.txt](https://docs.growthfactor.ai/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.growthfactor.ai/study/annotations-and-comments.md). # Annotations and Comments ## Working in a Shared Study Your work lives in the study itself, so every change you make lands for everyone who can open it. Edits are saved automatically. Each study keeps a live connection open and applies changes as they're saved, so a teammate's new pin, shape, or comment shows up on your map while you're both looking at it. Commenting is an edit. With view-only access you can open and read every thread but can't post, edit, or delete — the toolbar, the right-click options, and the input boxes are all hidden. See [Sharing and Exporting Studies](/study/sharing-and-exporting-studies.md). *** ## What's Shared and What's Personal | Shared with everyone who can see the study | Yours alone | | ----------------------------------------------------------------- | ------------------------------------------------------------------------------------------ | | Pins, shapes, and trade zones | Your agent conversation — a teammate opening the same study gets their own chat | | Annotations and their comment threads | Whether you've starred the study | | Comments on pins and shapes | The layers you've added to the study and which ones are toggled on (kept in your browser) | | Your existing stores, and any custom layers and territories | Personal edits to tracked businesses, which revert to the workspace defaults after 2 hours | | What the agent remembers — memory is shared across your workspace | | *** ## Annotations An annotation is a comment thread pinned to a point on the map. It isn't attached to a pin or a shape — it marks a location and holds a conversation. Annotations are their own map layer. The **Annotations** row in the Layers panel counts them (**3 notes · 7 comments**, or **No annotations yet**) and toggles every marker off and on at once. ### Adding an Annotation Click **Add annotation** (shortcut `A`) in the map toolbar, then click the point you want. The hint below the toolbar reads **Click on the map to add an annotation**. You can also right-click any empty spot on the map and choose **Add annotation here**. A composer opens at that point with the placeholder **Add a comment…**. Type the first comment and press Enter, or click **Add (Enter)**; Shift+Enter starts a new line. An annotation is always created with its first comment, so there's no such thing as an empty one. A confirmation message reads **Annotation added**. You can't move an annotation once it's placed. To relocate a note, remove it and add a new one. ### Replying to a Thread Click an annotation's marker to open its card, headed **Annotation** with a count line (**3 comments**). Type in the box at the bottom — **Reply…** — and press Enter or click **Post (Enter)**. Once a thread has more than one comment, the marker carries a badge with the count. The card stays anchored to its map point as you pan and zoom. Close it with the X or press `ESC`. Threads are flat: every reply lands at the bottom of the same list, and there's no replying to a reply. ### Editing and Deleting Your Comments Comments you wrote have **Edit** and **Delete** controls; comments from other people don't. Editing opens the text inline with **Save** and **Cancel**, and a changed comment is marked **(edited)** afterwards. Deleting the last comment in a thread removes the annotation along with it. A single undo brings both back. ### Removing an Annotation **Delete all** in the thread header clears the whole thread and takes the annotation with it. Its tooltip spells this out: **Delete all comments and remove this annotation**. Anyone who can edit the study can do this to any thread, not only their own. *** ## Comments on Pins and Shapes Pins and shapes carry threads of their own. Select one and open the **Comments** tab in its detail panel, where the tab shows a count, or right-click the pin or shape and choose **Add comment** — that jumps to the tab with the box already focused. The first comment's placeholder is **Add a comment to this pin…** or **Add a comment to this shape…**; after that it's **Reply…** with **Post (Enter)**. An empty thread reads **No comments yet.** These threads behave like annotation threads, except that deleting the last comment leaves the pin or shape in place. Existing stores don't take comments, and a study has no overall thread — use an annotation for a note that isn't about one pin or shape. *** ## Notes Written by the Agent You can ask the agent to write notes and comments for you. Anything it writes is stored against you and shows your name with a **via Agent** badge (**Written by the assistant**). In the PDF appendix, the author prints as **Agent**. Where the note lands depends on what you point the agent at: * **A pin** (`P1`) — a floating annotation at the pin's coordinates. It does not go into the pin's **Comments** tab; the agent can't write there. * **A shape** (`S1`) — a comment on that shape's own thread. * **An address or coordinates** — a floating annotation at that point. The agent can read the annotations and comments in the study you have open, so you can ask it to summarize a thread or pick up where one left off. --- # 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 current page URL with the `ask` query parameter, and the optional `goal` query parameter: ``` GET https://docs.growthfactor.ai/study/annotations-and-comments.md?ask=&goal= ``` `ask` is the immediate question: it should be specific, self-contained, and written in natural language. `goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal. 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.