> ## Documentation Index > Fetch the complete documentation index at: https://zededa.mintlify.site/llms.txt > Use this file to discover all available pages before exploring further. > ## Agent Instructions > Use the documentation index to find relevant pages, then read the linked Markdown before answering and cite the source URL. > Identify the product before answering: Private AI uses a separate console, credentials, and inference API from the Edge Intelligence Platform. Do not apply instructions from one product to the other. > Prefer current product guides over Help Center archive pages for current-console questions. Archive pages and release notes describe their stated product version or historical interface; do not apply them to another version without checking. > Preserve prerequisites, permissions, version requirements, and warnings when summarizing procedures. Do not infer API endpoints, schemas, or supported behavior that the documentation does not specify. # Use ZEIA to Query and Operate Your Fleet > Use ZEIA (ZEDEDA Edge Intelligence Agent) to ask questions, run fleet queries, and get answers grounded in your live edge data and ZEDEDA documentation. > [!NOTE] > > ZEIA is not yet available in production. The ZEIA panel currently shows a Coming Soon placeholder. This article describes the intended functionality. ZEIA is the AI assistant built into the Edge Intelligence Platform console. You describe what you want in plain language, and ZEIA fetches the answer from your live fleet data, EVE-OS (Edge Virtualization Engine) telemetry, and the ZEDEDA documentation. ZEIA is read-only by default: it queries, reports, and summarizes, but does not change configuration. You can access ZEIA from any page in the console using the terminal at the bottom of the screen, or from the **Build with ZEIA** workspace in the Inference service area for longer sessions. ## Before You Start ### Prerequisites * You must have an active account with access to the Edge Intelligence Platform console. * ZEIA operates within your assigned role and permissions. It cannot return data you do not have access to. * For fleet queries, at least one node must be onboarded to your enterprise. ## Open ZEIA You can open ZEIA in two ways depending on how much screen space you need. ### From any page in the console 1. Select the **> ask zeia...** terminal at the bottom of any page. 2. The ZEIA side panel opens. You can expand or collapse it at any time without losing your conversation. 3. Type your question or request and press **Enter**. ### From the Inference service area 1. In the bottom navigation bar, select **Inference**. 2. In the left sidebar, select **Build > Build with ZEIA**. 3. The full-screen ZEIA workspace opens. Use this view for longer sessions or when you want to read responses alongside follow-up questions. ## Ask a Question Type your question in the input field and press **Enter**. ZEIA searches your live fleet data, EVE-OS events, and ZEDEDA documentation to produce a grounded answer. Examples of questions you can ask: * "How do I register and onboard my first node?" * "How many nodes are offline right now?" * "What recent events occurred on edge-cluster-12 in the last 30 minutes?" * "How do I configure a project with a node Policy?" * "How do I use Edge View to establish an SSH connection to a node?" ZEIA includes source citations alongside answers drawn from documentation. Each citation shows the document title and a link so you can verify or read further. ## Run a Fleet Query For queries that span your entire fleet, ZEIA paginates through all records before answering, so results are complete rather than truncated to the first page. You can refine results with follow-up messages in the same conversation. Examples of fleet queries: * "Show me all nodes with tag `prod:west`." * "Give me a table of nodes ranked by memory usage, highest to lowest." * "List nodes that have almost exhausted their storage." * "Show me all edge app instances with crashes in the last 24 hours." For large result sets, ZEIA returns up to 50 items at a time. Ask "show me the next page" to continue through the results. ## Visualize Fleet Data You can ask ZEIA to generate a chart from your fleet data. ZEIA produces bar, line, pie, map, and sankey chart specifications on demand. Examples: * "Plot CPU and memory usage across my nodes over the last 24 hours." * "Show me a bar chart of nodes by EVE-OS version." * "Give me a map of my nodes by region." ## Generate an API Payload You can ask ZEIA to produce a sample API payload for any ZEDEDA operation. This is useful when automating onboarding, deploying edge applications through CI/CD pipelines, or testing API integrations. Examples: * "Generate a sample API payload for onboarding a node with zero-touch provisioning." * "Provide an example API request to create a project with a node Policy." Review the generated payload before use and replace any placeholder values with your actual environment values. ## Understand a Response Each ZEIA response includes: * **The answer**, grounded in live fleet data, EVE-OS telemetry, or ZEDEDA documentation. * **Source citations** when the answer draws from documentation, shown as document titles and links. * **A verification note** if ZEIA detects a claim it could not confirm against a known source. ZEIA never returns data outside your role and permissions. If you ask about a resource you cannot access, ZEIA indicates that the resource is not available to you rather than returning partial or incorrect data. ## Escalate to Support If ZEIA cannot resolve your issue, you can escalate directly to ZEDEDA support without leaving the conversation. 1. At the bottom of a ZEIA response, select **Escalate to support**. 2. ZEIA creates a support ticket and attaches the full conversation context. 3. A support engineer follows up through your normal support channel. ## Give Feedback You can rate each ZEIA response to help improve future answers. 1. At the bottom of any response, select **thumbs up** if the answer was helpful or **thumbs down** if it was not. 2. Optionally, add a comment to explain what was correct or incorrect. 3. To report a bug, select the **bug report** icon and describe the issue. ## What ZEIA Does Not Do ZEIA is focused on edge orchestration. It does not build or manage Edge AI components such as models, model registries, or inference engines. For those workflows, see [Edge Inference Services](https://zededa.mintlify.site/new-ui/edge-inference-services/overview.md). ZEIA does not make configuration changes in Phase 1. All operations are read-only. The ability to execute mutating actions may be introduced in a later phase. ## In This Section * [Edge Inference Services Overview](https://zededa.mintlify.site/new-ui/edge-inference-services/overview.md) * [Inference Dashboard](https://zededa.mintlify.site/new-ui/edge-inference-services/inference-dashboard.md) * [Inference Quick Start](https://zededa.mintlify.site/new-ui/edge-inference-services/inference-quick-start.md) * [Access and Navigate Edge Inference Services](https://zededa.mintlify.site/new-ui/edge-inference-services/access-and-navigation.md) * [Organizations, Users, and Roles](https://zededa.mintlify.site/new-ui/edge-inference-services/organizations-users-and-roles.md) * [Manage Providers](https://zededa.mintlify.site/new-ui/edge-inference-services/inference-model-providers.md) * [Manage Providers Using Jupyter Notebook Integration](https://zededa.mintlify.site/new-ui/edge-inference-services/providers-jupyter.md) * [Manage Models](https://zededa.mintlify.site/new-ui/edge-inference-services/manage-inference-models.md) * [Manage Models Using Jupyter Notebook Integration](https://zededa.mintlify.site/new-ui/edge-inference-services/models-jupyter.md) * [Benchmark Models and Manage Device Pools](https://zededa.mintlify.site/new-ui/edge-inference-services/inference-model-benchmarking.md) * [Monitor Benchmark Runs and Interpret Results](https://zededa.mintlify.site/new-ui/edge-inference-services/use-ondevice-eval-agent.md) * [Submit Model Deployment Requests](https://zededa.mintlify.site/new-ui/edge-inference-services/submit-model-deployment-requests.md) * [Approve and Validate Models](https://zededa.mintlify.site/new-ui/edge-inference-services/deployments-and-validation.md) * [Monitor Inference Jobs](https://zededa.mintlify.site/new-ui/edge-inference-services/jobs-and-monitoring.md) * [Use ZEIA to Query and Operate Your Fleet](https://zededa.mintlify.site/new-ui/edge-inference-services/zeia.md) * [Use Prevalidated Agents](https://zededa.mintlify.site/new-ui/edge-inference-services/prevalidated-agents.md) * [Use the Faulty Printed Circuit Board Detection Agent](https://zededa.mintlify.site/new-ui/edge-inference-services/faulty-pcb-detection-agent.md) * [Use the Autonomous Retail Billing Agent](https://zededa.mintlify.site/new-ui/edge-inference-services/autonomous-retail-billing-agent.md) * [Inference Troubleshooting](https://zededa.mintlify.site/new-ui/edge-inference-services/inference-troubleshooting.md)