Skip to content

fix(docs): Fix Agent Details docs in Studio #1011

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Closed
steramae-nvidia wants to merge 1 commit into from
Closed

fix(docs): Fix Agent Details docs in Studio #1011

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
28 changes: 19 additions & 9 deletions docs/studio/agents.mdx
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -6,25 +6,35 @@ Use **Agents** in the NeMo Studio workspace sidebar to review and operate agent

## Agent List

The Agents table shows the agents in the selected workspace, including their deployment state and creation time. Select a row to open the agent side panel.
The Agents table shows the agents in the selected workspace, including description, model, deployment health, and creation time. Select a row to open the agent details page.

| Action | Where | Result |
|--------|-------|--------|
| Review details | Select an agent row | Opens the agent side panel with name, workspace, description, and config format. |
| Review details | Select an agent row | Opens the agent details page for that agent. |
| Create an example agent | Page header > **Create Example Agent** | Creates a ready-made example agent in the workspace. |
| Deploy an agent | Row actions > **Deploy** | Creates a deployment for the selected agent. |
| Test models | Row actions > **Test models** | Opens the model playground for the agent's configured model. |
| Clone an agent | Row actions > **Clone** | Creates a copy of the agent definition with a new name. |
| Chat with a deployment | Agent side panel > **Chat Playground** tab | Opens the chat playground for a running deployment. |
| Delete a deployment | Agent side panel > **Details** > **Deployments** > **Delete** | Removes that deployment. |
| Delete an agent | Row actions > **Delete** | Removes the stored agent definition from the workspace. |
| Delete an agent | Row actions > **Delete** | Removes the stored agent definition and all its deployments. |
| Delete several agents | Select rows > **Delete** | Removes the selected agent definitions and their deployments. |

## Agent Details

The agent side panel has three tabs:
The agent details page opens at `Agents > <agent name>`. The header shows the agent name, deployment status, model, and description, along with these actions:

- **Details** shows the stored agent metadata and config format. It includes a **Deployments** section listing active and historical deployments for the agent (endpoint and status), plus recent evaluations.
- **Chat Playground** opens an interactive chat with a running deployment.
- **Logs** shows deployment logs.
- **Open traces** goes to the agent Monitor view for telemetry.
- **Run evaluation** submits an evaluation job for the agent.
- **Deploy** creates a new deployment.

The page has five tabs:

- **Deployments** (default) lists the agent's deployments with status and endpoint, plus per-deployment **Chat**, **Logs**, and **Delete** actions.
- **Logs** shows logs for a selected deployment.
- **Chat** opens an interactive chat with a running deployment.
- **Evaluations** lists recent evaluation jobs for the agent and links through to each run.
- **Details** shows the stored agent metadata and the full config, grouped into Workflow, Models, and Tools panels.

The selected tab is reflected in the URL's `tab` query parameter, so you can link directly to a tab.

Agents are created and updated through the `nemo agents` CLI or Agents API. NeMo Studio reflects the current workspace state after the platform services refresh.

Expand Down
48 changes: 21 additions & 27 deletions docs/studio/index.mdx
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -27,12 +27,6 @@ Use the Studio Agents area to review platform-managed NeMo Agent Toolkit workflo

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.
Expand Down Expand Up @@ -71,27 +65,27 @@ Keep models and data organized in dedicated workspaces.

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. |
| 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. |
| 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 |
| --------------------------------------------------- | ------------------------------------- |
| 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. |
| 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.
Expand All @@ -106,18 +100,18 @@ Navigate to **Jobs** in the workspace sidebar to see all jobs in the current wor

**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 |
| 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.

Expand Down
Loading