Kineviz Agent Kineviz Agent is a built-in AI assistant for working with graph data in a Kineviz project. Use the Agent to turn natural-language questions and instructions into guided graph exploration, data preparation, and analysis. For example, analysts can use the Agent to move from a question to an actionable graph workflow by suggesting the next operation, explaining graph patterns, and helping prepare data for detailed analysis. Treat generated suggestions as analytical guidance and verify results against your source data. The Agent system prompt includes default canvas context, project context, and interaction mode. A gxr.agent API surfaces sessions, snapshots, and view-copying. In the Agent panel, you can: Set the agent to work on complex exploratory tasks using natural language prompts. Copy Agent code, and Agent responses as .md files to the clipboard. Review skills and tools available to the Agent. Manage chat threads. Manage views created by the Agent. Review current LLM and chat options Show or hide the Agent panel per project using the Project > Settings > UI Configuration interface. Admin users can open the administrator portal to install specific LLM models, review and manage usage levels and per-user budgets. The Agent is currently in beta release. Features and behavior may change as the feature evolves. Agent Quick Start The agent is available by default to any individual Kineviz user. You can try it out as soon as you open a project. Here’s how: Log in to Kineviz or Kineviz Desktop. Create or open a project, and on the left panel menu, click Agent. You can right-click any panel menu item and choose Float to un-dock the panel from the left menu and reposition it conveniently on the project canvas. Click the New thread button. Enter the prompt Create a random graph and click Send. Wait for the result. This prompt resulted in a graph of connections among Persons who work for various Companies. Your result may vary. For examples of Agent workflows for exploring sample data, try a Kineviz Sandbox demo. Create a New Thread A thread (or chat) is the record of a chat session, including your prompts and the Agent responses (code and generated text explanations). Threads persist in the project until you delete them. A thread is labeled with the text of the first prompt you enter (e.g. list my skills), but it will likely include many other prompts. For example, in a single thread you could enter prompts to create graph data, query a connected database, find paths, lay out the graph in a specific pattern, create and save a grove notebook, and more. You can create a new thread at any time. To create a thread: Click New Chat at the top left. Enter a prompt (for example, list my tools) and click the Send icon. The thread (or chat) is now labeled with the initial prompt text. Rename a Thread A thread is labeled with the text of its first prompt. You can rename it to be shorter, or more descriptive of the workflow in the thread. To rename a thread: Click the Settings icon at the top right, and select Rename Enter the new name in the dialog, and click Save. Close or Open an Existing Thread Open threads are shown in separate tabs in the Agent panel. The Thread History menu lists all the threads you’ve created (whether currently open or not) in order of when each was last opened. To close a thread: Click the X icon on the thread tab. The thread is closed (but not deleted). To open a closed thread: Click the Thread History icon at the upper right. Optionally, use the search bar to search for a thread by name. Select the thread from the menu. The thread is opened in a new tab. Delete Threads You can delete one thread, or clear all threads in a single step. To delete one thread: Open the thread you want to delete. Click the Settings icon at the top right. Select Delete thread To clear all threads: Click the Settings icon at the top right. Select Clear threads Click OK (or Cancel) in the dialog to confirm (or cancel) the action. Attach Files to a Thread You can attach files with data or information (text or image) that you want the Agent to evaluate in the context of the current prompt. To include an external file in a prompt: Click the Attach File icon at the bottom left of the panel. Navigate to the file and click Open to add it to the prompt. Enter the prompt (e.g. Find UI elements in the attached image) and click Send. The Agent evaluates the attached file according to the prompt and returns its response. Copy Agent Results Each code block or text response includes an icon to copy results to the clipboard, to transfer to other Kineviz projects or for use in reports. To copy Agent code or text responses: Click the copy icon next to a code block or a response. A code block is copied as code, and a response as an .md file. To copy an entire thread to the clipboard: Click the Settings icon at the top right. Choose either Copy thread, Copy thread as Markdown, or Export as HTML from the menu. Review LLMs and Chat options The LLM menu at the bottom of the Agent panel shows the currently installed LLMs and highlights the one currently in use (e.g. Gemini Flash 3 Preview) Click the Chat Options icon next to the LLM menu to see current thinking level and debug options. To change LLMs and chat options: Open the LLM menu and choose a different LLM from the menu. Click the Chat Options icon and: Select a different option from the thinking level menu. Click the Debug logging radio button to turn logging on (or off). Review Agent Settings In Agent Settings, you can review current skills, view usage status and chat options, add or delete LLM models, and review project connector status. An admin user (either individual, or in a multi-user installation) can access the Admin portal’s Agent panel to include LLMs to be used, and limit daily and overall budgets in terms of both tokens and dollar amounts. Skills To review available agent Skills: Click the Settings icon at the top right. Choose Skills from the settings menu. The agent Settings > Skills panel opens, showing the list of skills available to the project. Click the return arrow at the top left to exit agent Settings. Usage and LLM Options The agent Settings > General panel shows project usage, chat, and LLM options. To review usage, chat, and LLM settings: Click the Settings icon at the top right. Choose Settings from the menu and click to open the General tab. Options include: Review current Usage as the percent used of the total available across all projects for the logged in user. Turn off Group work in chat to control how agent responses are grouped in a chat. It is turned on by default, which folds each turn’s thinking and tool calls into a single collapsible Worked for… row. Turn off the radio button to show every step at the top level. Add LLM models. Click Add model and enter the required Basic and Advanced model details, then click Submit to add the model (or Cancel to exit). Click the return arrow at the top left to exit agent Settings. Connector Status The agent Settings > Connectors panel lets you review the connectors (e.g. Firecrawl, Atlassian, etc.) currently available to your project. Configuration of project connectors is managed through the admin user’s Admin portal. To review Connector status: Click the Settings icon at the top right. Choose Settings from the menu and click to open the Connectors tab. Click the return arrow at the top left to exit agent Settings.