> For clean Markdown of any page, append .md to the page URL. > For a complete documentation index, see https://docs.nvidia.com/nemo-platform/llms.txt. > For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://docs.nvidia.com/nemo-platform/_mcp/server. # About NVIDIA NeMo Studio Studio is still in early development. Many features are missing or should be expected to change. NeMo Studio is the web app for AI development with NVIDIA NeMo Platform. It provides a workspace-oriented UI for managing local platform resources, reviewing agents, running agent optimization workflows, monitoring agent telemetry, and working with filesets, jobs, and secrets. --- ## Getting Started NeMo Studio is included with the platform. Follow the [Setup guide](/documentation/get-started) to start NeMo Platform, then access Studio at `/studio` on your running server. ## Features ### Agents Use the Studio Agents area to review platform-managed NeMo Agent Toolkit workflows, inspect agent details, deploy agents, open a chat session against a running deployment, and clean up deployments that are no longer needed. For the full workflow, see [Studio Agents](/documentation/studio/agents). ### Suggestions Use **Agents > Suggestions** to review optimizer suggestions for deployed agents. Studio groups suggestions by workspace or agent and lets you filter by type, priority, scope, and agent. For the full workflow, see [Studio Suggestions](/documentation/studio/suggestions). ### Monitor Use **Agents > Monitor** to inspect agent telemetry stored by the platform, including recent inference logs and token usage summaries. For the full workflow, see [Studio Monitor](/documentation/studio/monitor). ### Guardrails Use **Guardrails** to view NeMo Guardrails configurations for the current workspace. The list shows each config's name, attached task model count, and rail count. Select a row to open the detail page, which displays the full configuration payload as formatted JSON. Guardrail configurations are created through the `nemo guardrail` CLI or Guardrails API. For the full workflow, see [Studio Guardrail Configs](/documentation/studio/guardrails). ### Virtual Models Use **Virtual Models** to inspect inference routes managed by the Inference Gateway. The list shows all user-created virtual models in the workspace — auto-provisioned passthrough routes are hidden. Select a row to open the details panel, which shows the default backend model when configured, and the ordered request, response, and post-response middleware pipelines attached to the route. Virtual models are created through the `nemo inference virtual-models` CLI or the Inference Gateway API. For the full workflow, see [Studio Virtual Models](/documentation/studio/virtual-models). ### Models Use **Models > Base Models** to browse model entities available in the current workspace. Base models include models registered in the workspace and default platform models. The Base Models page supports searching by model name, filtering by creation or update date, sorting alphabetically or by creation time, and showing only customizable models. Select a model card to open the model details side panel. The model details side panel shows model metadata, parameters, and available actions. From the side panel you can open the chat playground for chat-capable models or navigate to model evaluation results. ### Workspaces Keep models and data organized in dedicated workspaces. ### Filesets Use **Filesets** to organize files by **purpose**, which determines which metadata fields are available. Purpose is chosen at creation time and can't be changed afterward. | Purpose | Use for | | ------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | | Generic | Default. Files that don't fit the Dataset or Model categories. Doesn't add purpose-specific metadata fields. | | Dataset | Training and evaluation data. Enables dataset-specific metadata, including schema information. Use built-in tools to transform data schemas with LLM assistance or create train/test splits. | | Model | Model weights and checkpoints. Enables model-specific metadata, including tool-calling and model configuration fields. | **Supported file formats:** JSON (`.json`), JSONL (`.jsonl`), CSV (`.csv`), and Parquet (`.parquet`). PDF, image, and other binary formats are not currently supported. You can upload any file type into a fileset. However, each service supports specific input file types: | Service | Supported File Types | | ----------------------------------------------------- | ------------------------------------- | | [Data Designer](/documentation/design-synthetic-data) | `.json`, `.jsonl`, `.csv`, `.parquet` | ### Evaluations **Evaluations** appears in two separate sidebar groups because it covers two distinct scopes: | Location | What it shows | | -------------------------- | ---------------------------------------------------------------------------------------------- | | **Agents > Evaluations** | Evaluation runs scoped to a specific agent — results tied to agent deployments and versions. | | **Evaluate > Evaluations** | All evaluation results across the workspace, regardless of which agent or model was evaluated. | Use **Agents > Evaluations** when reviewing how a specific agent performed. Use **Evaluate > Evaluations** for a broader view of evaluation history across the workspace. ### Jobs Track and manage all platform jobs from a single view. The Jobs page aggregates jobs across enabled capabilities, such as Data Designer, so you can monitor progress, view logs, download artifacts, and cancel jobs in one place. Navigate to **Jobs** in the workspace sidebar to see all jobs in the current workspace. **Search and filter** — Find jobs by name, filter by status, or narrow results by creation or update date range. **Status tracking** — Each job displays its current status: | Status | Description | | ---------- | ------------------------------------------ | | Created | Job has been created but not yet scheduled | | Pending | Job is queued and waiting for resources | | Active | Job is currently running | | Completed | Job finished successfully | | Error | Job encountered an error | | Cancelled | Job was cancelled by a user | | Cancelling | Cancellation is in progress | | Paused | Job execution is paused | | Pausing | Job is transitioning to paused | | Resuming | Paused job is restarting | **Service routing** — Clicking a job navigates to its service-specific detail view when one exists. Jobs from services that aren't enabled fall back to the generic job detail view. **Cancelling a job** — Active or pending jobs can be cancelled from the job list or the detail page. Cancelling a job permanently stops it and cannot be undone. ### Secrets Store API keys and credentials to securely connect with external providers. See [manage-secrets](/documentation/get-started/core-concepts/manage-secrets) for details.