NeMo Studio Suggestions¶
Use NeMo Studio Agents > Suggestions to review optimizer suggestions for agents in the selected workspace.
What NeMo Studio Shows¶
NeMo Studio loads the latest optimizer snapshot and suggestions from the platform files service. Suggestions can be scoped to a workspace or to a specific agent.
The Suggestions page summarizes:
- The number of agents and models observed in the latest optimizer snapshot.
- Suggestion counts by priority.
- Workspace-wide suggestions.
- Agent-specific suggestions grouped by agent.
Filter Suggestions¶
Use the table filters to narrow suggestions by:
| Filter | Purpose |
|---|---|
| Type | Focus on model optimization, guardrail, data safety, or new-model suggestions. |
| Priority | Show high-, medium-, or low-priority suggestions. |
| Scope | Separate workspace-wide suggestions from agent-specific suggestions. |
| Agent | Review suggestions for one agent at a time. |
Run an Optimization Pass¶
If there are no suggestions, or if the latest snapshot is stale, NeMo Studio starts a new optimizer pass for the workspace. The optimizer analyzes deployed agents and writes updated suggestions back to the platform files service.
Apply Suggestions¶
NeMo Studio can apply supported suggestions from the Suggestions page. Model optimization suggestions may ask you to choose an evaluation config before applying the change.
Next Steps¶
- NeMo Studio Agents: review, deploy, chat with, and delete agents from NeMo Studio.
- NeMo Studio Monitor: inspect recent agent telemetry, token usage, and inference logs.
- Optimize Agents: run CLI-driven optimization and review the underlying checks.