Optimize Agents

Use the Agent Optimizer to analyze a deployed agent and act on improvement suggestions. The optimizer inspects the agent's config, the workspace model catalog, any prior optimizer snapshots, and optional evaluation baselines, then writes suggestions you can review from the CLI or hand off to a coding agent.

This page covers the main path: establish a baseline, generate optimization suggestions, apply a candidate change to a sibling agent, and review the evaluation result before promotion.

What the Optimizer Checks

Suggestion type	Signal	Result
Model optimization	An agent uses a single frontier model where a smaller model or route split may preserve quality at lower cost	Suggests a model swap or Switchyard random-routing virtual model
Skill optimization	The agent uses skills and has an evaluation suite	Suggests running nemo agents optimize-skills to improve skill files and keep changes that pass evaluation
Prompt optimization	The agent has an optimization config and baseline dataset	Suggests nemo agents optimize run for NAT prompt or parameter tuning
New model scan	Difference between the current model list and the previous optimizer snapshot	Suggests evaluating or auditing newly available models

Optimizer state is stored in the nemo-agent-optimizer fileset:

• optimizer_suggestions.jsonl: one suggestion per line, including applied state.
• optimizer_snapshot.json: model and agent names from the latest run.

Security-oriented suggestions such as missing guardrails, PII exposure, or leaked secrets are covered in Secure Agents.

Prerequisites

Before running the optimizer, make sure you have:

1. Local services running (nemo services run).
2. The agents plugin installed. For local development from this repository:

   uv pip install -e packages/nemo_platform_plugin -e plugins/nemo-agents
   

3. A workspace with at least one model provider and discovered model entities.
4. At least one deployed platform-managed agent.
5. An evaluation baseline before promoting a candidate agent.

If you need a demo agent, start the platform and create the ReAct example:

nemo services run

In another terminal:

export NMP_BASE_URL=http://127.0.0.1:8080
cd plugins/nemo-agents

printf '%s' "$NVIDIA_API_KEY" | nemo secrets create ngc-api-key --from-file -
nemo inference providers create nvidia-build \
  --host-url https://integrate.api.nvidia.com \
  --api-key-secret-name ngc-api-key
nemo wait inference provider nvidia-build

nemo agents create \
  --name react-agent \
  --agent-config examples/react-agent/react-agent.yml
nemo agents deploy --agent react-agent
nemo agents deployments wait --agent react-agent

The example agent uses nvidia-nemotron-3-nano-30b-a3b, so it can produce a model optimization suggestion when the workspace model catalog contains a smaller compatible model.

Optimize with Switchyard Routing

Switchyard is the inference middleware that lets a virtual model split traffic across multiple backend models. The common optimization pattern is to create a virtual model with a strong model and a weaker, cheaper model, then evaluate whether the route split preserves application quality.

Run nemo models list first and replace the placeholders below with model entity names from your workspace that use the OPENAI_CHAT backend format.

CLISkillPython SDK

The command below creates a virtual model that sends 80% of traffic to the strong model and 20% to the weak one.

nemo inference virtual-models create routed-agent-model \
  --workspace default \
  --models '[
    {"model":"default/<strong-model-entity>","backend_format":"OPENAI_CHAT"},
    {"model":"default/<weak-model-entity>","backend_format":"OPENAI_CHAT"}
  ]' \
  --request-middleware '[{
    "name":"nemo-switchyard",
    "config_type":"random_routing",
    "config":{
      "strong":{"model":"default/<strong-model-entity>"},
      "weak":{"model":"default/<weak-model-entity>"},
      "strong_probability":0.8,
      "enable_stats":false
    }
  }]'

Before wiring the virtual model to an agent, smoke-test the route by making several minimal chat-completions calls and checking the returned model name. The observed split should roughly match strong_probability.

Ask your coding agent:

Optimize my deployed agent.

The agents-optimize skill picks a deployed agent, establishes an evaluation baseline, runs the analysis steps below, and surfaces suggestions for you to apply.

Verify the skill is installed:

nemo skills show agents-optimize

What it does under the hood:

• Lists deployed agents and prompts you to choose one.
• Inspects the agent's llms[*].model_name and looks for cheaper compatible models in the workspace catalog.
• Creates a Switchyard random_routing virtual model with an 80% strong / 20% weak split and smoke-tests the route before wiring it to a sibling agent.
• Suggests skill optimization, prompt tuning, and new-model evaluations where the agent qualifies.
• Persists suggestions to the nemo-agent-optimizer fileset.

import os
from nemo_platform import NeMoPlatform

client = NeMoPlatform(
    base_url=os.environ.get("NMP_BASE_URL", "http://localhost:8080"),
    workspace="default",
)

client.inference.virtual_models.create(
    name="routed-agent-model",
    workspace="default",
    models=[
        {"model": "default/<strong-model-entity>", "backend_format": "OPENAI_CHAT"},
        {"model": "default/<weak-model-entity>", "backend_format": "OPENAI_CHAT"},
    ],
    request_middleware=[{
        "name": "nemo-switchyard",
        "config_type": "random_routing",
        "config": {
            "strong": {"model": "default/<strong-model-entity>"},
            "weak": {"model": "default/<weak-model-entity>"},
            "strong_probability": 0.8,
            "enable_stats": False,
        },
    }],
)

Optimize Skills

Skill optimization applies when the agent depends on local skill files and has an evaluation suite. The loop runs evaluations, analyzes failures, lets the coding agent edit only the configured skills directory, reruns verification, and keeps the change only when the evaluation result improves.

CLISkillPython SDK

nemo agents optimize-skills --config .agent-improver.yml

Use --open-pr when you want the loop to prepare a reviewable branch.

A sample .agent-improver.yml is in plugins/nemo-agents/examples/agent-improver.example.yml.

Ask your coding agent:

Optimize the skills used by my agent and keep the changes that improve evaluation scores.

The agents-optimize skill drives the skill-optimization loop when the selected agent has skills and an evaluation suite. Verify it is installed:

nemo skills show agents-optimize

What it does under the hood:

• Confirms the agent uses skills (a --skills-path, a .agent-improver.yml, or skill files referenced from the config).
• Runs nemo agents optimize-skills against the configured skills directory.
• Re-runs evaluation and keeps the change only when scores improve.
• Persists outcomes to the nemo-agent-optimizer fileset.

from nemo_agents_plugin.jobs.optimize_skills import OptimizeSkillsJob
from nemo_platform_plugin.scheduler import NemoJobScheduler

NemoJobScheduler().run_local(
    OptimizeSkillsJob,
    {"config": ".agent-improver.yml"},
    workspace="default",
)

Inspect Saved Results

Use the Files service to inspect what the optimizer saved:

nemo files list nemo-agent-optimizer

nemo files download nemo-agent-optimizer \
  --remote-path optimizer_suggestions.jsonl \
  -o optimizer_suggestions.jsonl

nemo files download nemo-agent-optimizer \
  --remote-path optimizer_snapshot.json \
  -o optimizer_snapshot.json

Telemetry is optional. If agents use the nemo_files telemetry exporter, trace files are written to nemo-agent-telemetry, and the optimizer samples the largest JSONL file:

nemo files list nemo-agent-telemetry

Run Prompt and Parameter Tuning

The nemo agents optimize run command runs the NAT optimizer path for parameter or prompt tuning. Use it when you already have a NAT optimization YAML and want to run nat optimize through the Agents plugin.

For the ReAct example:

CLISkillPython SDK

nemo agents optimize run \
  --optimize-config plugins/nemo-agents/examples/react-agent/react-optimize.yml \
  --agent react-agent

Ask your coding agent:

Run prompt tuning on my deployed agent against this optimization config.

The agents-optimize skill suggests nemo agents optimize run when the agent has an optimization config and a baseline dataset. Verify it is installed:

nemo skills show agents-optimize

What it does under the hood:

• Confirms the agent has a NAT optimization YAML.
• Runs nemo agents optimize run (or submit for platform jobs).
• Compares results against the evaluation baseline and surfaces deltas for review.

import os
from pathlib import Path

from nemo_agents_plugin.jobs.optimize_agent import OptimizeAgentJob
from nemo_platform import NeMoPlatform
from nemo_platform_plugin.scheduler import NemoJobScheduler

WORKSPACE = "default"
optimize_config = Path("plugins/nemo-agents/examples/react-agent/react-optimize.yml")

client = NeMoPlatform(
    base_url=os.environ.get("NMP_BASE_URL", "http://localhost:8080"),
    workspace=WORKSPACE,
)

result = NemoJobScheduler().run_local(
    OptimizeAgentJob,
    {
        "optimize_config": str(optimize_config),
        "agent": "react-agent",
        "workspace": WORKSPACE,
    },
    workspace=WORKSPACE,
    sdk=client,
)
print(result)

When --agent is a platform-managed agent name, the job fetches the stored agent config, merges it with the optimization config, injects the Inference Gateway URL, and runs trials locally. When --agent is a raw HTTP endpoint, the endpoint is treated as an opaque remote service, so local parameter sweeps do not change the remote agent behavior.

Troubleshooting

No suggestions appear. Confirm the workspace has agents, model entities, and a model catalog entry smaller than the agent's current model. New-model suggestions require a previous optimizer snapshot, so they do not appear on the first run.

The model evaluation fails. Confirm the judge model in the eval config is available through the workspace Inference Gateway. You can replace the eval files in <agent-name>-eval with your own evaluation config and dataset.

Data safety suggestions do not appear. Telemetry is optional. The optimizer only scans nemo-agent-telemetry when that fileset exists and contains JSONL trace files.

Next steps

• Agent overview: review how platform-managed agents are registered, deployed, invoked, evaluated, and optimized.
• Agent evaluation: configure agents as online evaluation targets and choose the right agent response mapping.
• CLI reference: look up complete command options and global CLI flags for scripted workflows.