diff --git a/docs/domain-entity-rename.md b/docs/domain-entity-rename.md
index 9a5c0e71..10f4131b 100644
--- a/docs/domain-entity-rename.md
+++ b/docs/domain-entity-rename.md
@@ -45,8 +45,8 @@ stream = AgentStream.get(name="prod-traces", project_name="my-project")
 streams = AgentStream.list(project_name="my-project")
 
 # Enable evaluators on the stream
-from splunk_ao.schema.metrics import SplunkAOMetrics
-stream.enable_evaluators([SplunkAOMetrics.correctness, SplunkAOMetrics.completeness])
+from splunk_ao.schema.metrics import SplunkAOEvaluators
+stream.enable_evaluators([SplunkAOEvaluators.correctness, SplunkAOEvaluators.completeness])
 ```
 
 ```python
diff --git a/examples/agent/langgraph-fsi-agent/after/test.py b/examples/agent/langgraph-fsi-agent/after/test.py
index 3e1035a7..c5a49aed 100644
--- a/examples/agent/langgraph-fsi-agent/after/test.py
+++ b/examples/agent/langgraph-fsi-agent/after/test.py
@@ -15,7 +15,7 @@
 from langchain_core.callbacks import Callbacks
 from langchain_core.messages import HumanMessage
 
-from splunk_ao import SplunkAOMetrics, splunk_ao_context
+from splunk_ao import SplunkAOEvaluators, splunk_ao_context
 from splunk_ao.datasets import create_dataset, get_dataset, delete_dataset
 from splunk_ao.experiments import get_experiment, run_experiment
 from splunk_ao.handlers.langchain import SplunkAOCallback
@@ -108,7 +108,7 @@ def test_run_experiment_with_dataset():
         experiment_name="langgraph-fsi-experiment",
         dataset_name=DATASET_NAME,
         function=send_message_to_supervisor_agent,
-        metrics=[SplunkAOMetrics.action_advancement, SplunkAOMetrics.action_completion, SplunkAOMetrics.tool_error_rate, SplunkAOMetrics.tool_selection_quality],
+        metrics=[SplunkAOEvaluators.action_advancement, SplunkAOEvaluators.action_completion, SplunkAOEvaluators.tool_error_rate, SplunkAOEvaluators.tool_selection_quality],
         project=os.getenv("SPLUNK_AO_PROJECT"),
     )
 
diff --git a/examples/chatbot/sample-project-chatbot/anthropic/test.py b/examples/chatbot/sample-project-chatbot/anthropic/test.py
index 50412891..8a5fa447 100644
--- a/examples/chatbot/sample-project-chatbot/anthropic/test.py
+++ b/examples/chatbot/sample-project-chatbot/anthropic/test.py
@@ -12,7 +12,7 @@
 
 from dotenv import load_dotenv
 
-from splunk_ao import SplunkAOMetrics
+from splunk_ao import SplunkAOEvaluators
 from splunk_ao.datasets import create_dataset, get_dataset
 from splunk_ao.experiments import get_experiment, run_experiment
 
@@ -75,8 +75,8 @@ def test_run_experiment_with_dataset():
         dataset_name="simple-chatbot-unit-test-dataset",
         function=chat_with_llm,
         metrics=[
-            SplunkAOMetrics.correctness,
-            SplunkAOMetrics.instruction_adherence,
+            SplunkAOEvaluators.correctness,
+            SplunkAOEvaluators.instruction_adherence,
         ],
         project=os.getenv("SPLUNK_AO_PROJECT"),
     )
diff --git a/examples/chatbot/sample-project-chatbot/azure-inference/test.py b/examples/chatbot/sample-project-chatbot/azure-inference/test.py
index 50412891..8a5fa447 100644
--- a/examples/chatbot/sample-project-chatbot/azure-inference/test.py
+++ b/examples/chatbot/sample-project-chatbot/azure-inference/test.py
@@ -12,7 +12,7 @@
 
 from dotenv import load_dotenv
 
-from splunk_ao import SplunkAOMetrics
+from splunk_ao import SplunkAOEvaluators
 from splunk_ao.datasets import create_dataset, get_dataset
 from splunk_ao.experiments import get_experiment, run_experiment
 
@@ -75,8 +75,8 @@ def test_run_experiment_with_dataset():
         dataset_name="simple-chatbot-unit-test-dataset",
         function=chat_with_llm,
         metrics=[
-            SplunkAOMetrics.correctness,
-            SplunkAOMetrics.instruction_adherence,
+            SplunkAOEvaluators.correctness,
+            SplunkAOEvaluators.instruction_adherence,
         ],
         project=os.getenv("SPLUNK_AO_PROJECT"),
     )
diff --git a/examples/chatbot/sample-project-chatbot/openai-ollama/test.py b/examples/chatbot/sample-project-chatbot/openai-ollama/test.py
index 50412891..8a5fa447 100644
--- a/examples/chatbot/sample-project-chatbot/openai-ollama/test.py
+++ b/examples/chatbot/sample-project-chatbot/openai-ollama/test.py
@@ -12,7 +12,7 @@
 
 from dotenv import load_dotenv
 
-from splunk_ao import SplunkAOMetrics
+from splunk_ao import SplunkAOEvaluators
 from splunk_ao.datasets import create_dataset, get_dataset
 from splunk_ao.experiments import get_experiment, run_experiment
 
@@ -75,8 +75,8 @@ def test_run_experiment_with_dataset():
         dataset_name="simple-chatbot-unit-test-dataset",
         function=chat_with_llm,
         metrics=[
-            SplunkAOMetrics.correctness,
-            SplunkAOMetrics.instruction_adherence,
+            SplunkAOEvaluators.correctness,
+            SplunkAOEvaluators.instruction_adherence,
         ],
         project=os.getenv("SPLUNK_AO_PROJECT"),
     )
diff --git a/examples/experiments/multi-turn/README.md b/examples/experiments/multi-turn/README.md
index f81f61dc..ac09920b 100644
--- a/examples/experiments/multi-turn/README.md
+++ b/examples/experiments/multi-turn/README.md
@@ -61,13 +61,13 @@ The `METRIC_NAME` variable in this script cites a session-level metric.
 
 Pre-defined session-level metrics include:
 
-- `SplunkAOMetrics.conversation_quality`
-- `SplunkAOMetrics.action_completion`
-- `SplunkAOMetrics.action_advancement`
-- `SplunkAOMetrics.agent_efficiency`
-- `SplunkAOMetrics.context_adherence`
-- `SplunkAOMetrics.context_relevance`
-- `SplunkAOMetrics.tool_error_rate`
+- `SplunkAOEvaluators.conversation_quality`
+- `SplunkAOEvaluators.action_completion`
+- `SplunkAOEvaluators.action_advancement`
+- `SplunkAOEvaluators.agent_efficiency`
+- `SplunkAOEvaluators.context_adherence`
+- `SplunkAOEvaluators.context_relevance`
+- `SplunkAOEvaluators.tool_error_rate`
 
 Related documentation: [Metrics Comparison](https://agent-observability-docs.splunk.com/concepts/metrics/metric-comparison)
 
diff --git a/examples/experiments/multi-turn/basic-example.py b/examples/experiments/multi-turn/basic-example.py
index 5d6189fc..5e167532 100644
--- a/examples/experiments/multi-turn/basic-example.py
+++ b/examples/experiments/multi-turn/basic-example.py
@@ -1,7 +1,7 @@
 import os
 import time
 
-from splunk_ao import SplunkAOMetrics, splunk_ao_context
+from splunk_ao import SplunkAOEvaluators, splunk_ao_context
 from splunk_ao.experiments import create_experiment
 from splunk_ao.projects import create_project, get_project
 from splunk_ao.resources.models import MetricSuccess
@@ -9,7 +9,7 @@
 from splunk_ao.utils.metrics import create_metric_configs
 
 # Provide the name of a session-level metric
-METRIC_NAME = SplunkAOMetrics.conversation_quality
+METRIC_NAME = SplunkAOEvaluators.conversation_quality
 
 # example custom metric name (must be set up in advance)
 # METRIC_NAME = "multi-turn-session-test-metric-apples"
diff --git a/examples/experiments/rag-and-tools/experiment.py b/examples/experiments/rag-and-tools/experiment.py
index aa4c19a8..1cca3d6f 100644
--- a/examples/experiments/rag-and-tools/experiment.py
+++ b/examples/experiments/rag-and-tools/experiment.py
@@ -1,6 +1,6 @@
 import os
 
-from splunk_ao import SplunkAOMetrics
+from splunk_ao import SplunkAOEvaluators
 from splunk_ao.experiments import run_experiment
 
 from app import get_users_horoscope
@@ -25,10 +25,10 @@ def main():
         dataset=dataset,
         function=get_users_horoscope,
         metrics=[
-            SplunkAOMetrics.tool_error_rate,
-            SplunkAOMetrics.tool_selection_quality,
-            SplunkAOMetrics.chunk_attribution_utilization,
-            SplunkAOMetrics.context_adherence,
+            SplunkAOEvaluators.tool_error_rate,
+            SplunkAOEvaluators.tool_selection_quality,
+            SplunkAOEvaluators.chunk_attribution_utilization,
+            SplunkAOEvaluators.context_adherence,
         ],
         project=os.environ["SPLUNK_AO_PROJECT"],
     )
diff --git a/examples/experiments/upload_experiment/README.md b/examples/experiments/upload_experiment/README.md
index a17cad83..e5420cdb 100644
--- a/examples/experiments/upload_experiment/README.md
+++ b/examples/experiments/upload_experiment/README.md
@@ -117,12 +117,12 @@ Edit `dataset.json` with your own evaluation data. The example uses space missio
 In `upload_existing_results.py`, modify the `metrics` parameter in `upload_experiment()`:
 
 ```python
-from splunk_ao.schema.metrics import SplunkAOMetrics
+from splunk_ao.schema.metrics import SplunkAOEvaluators
 
 custom_metrics = [
-    SplunkAOMetrics.ground_truth_adherence,
-    SplunkAOMetrics.context_adherence,
-    SplunkAOMetrics.correctness,
+    SplunkAOEvaluators.ground_truth_adherence,
+    SplunkAOEvaluators.context_adherence,
+    SplunkAOEvaluators.correctness,
     # Add any other Splunk AO metrics you want
 ]
 
diff --git a/examples/experiments/upload_experiment/upload_existing_results.py b/examples/experiments/upload_experiment/upload_existing_results.py
index 4673a181..a0a13a4f 100644
--- a/examples/experiments/upload_experiment/upload_existing_results.py
+++ b/examples/experiments/upload_experiment/upload_existing_results.py
@@ -32,7 +32,7 @@
 # Splunk AO imports
 from splunk_ao.datasets import create_dataset, get_dataset
 from splunk_ao.experiments import run_experiment
-from splunk_ao.schema.metrics import SplunkAOMetrics
+from splunk_ao.schema.metrics import SplunkAOEvaluators
 from splunk_ao import splunk_ao_context
 
 
@@ -239,11 +239,11 @@ def upload_experiment(
     # Use default metrics if none provided
     if metrics is None:
         metrics = [
-            SplunkAOMetrics.ground_truth_adherence,
-            SplunkAOMetrics.context_adherence,
-            SplunkAOMetrics.chunk_attribution_utilization,
-            SplunkAOMetrics.completeness,
-            SplunkAOMetrics.correctness,
+            SplunkAOEvaluators.ground_truth_adherence,
+            SplunkAOEvaluators.context_adherence,
+            SplunkAOEvaluators.chunk_attribution_utilization,
+            SplunkAOEvaluators.completeness,
+            SplunkAOEvaluators.correctness,
         ]
 
     # Run experiment with your data
diff --git a/splunk-ao-migration-tool/README.md b/splunk-ao-migration-tool/README.md
index a4b96273..c972e237 100644
--- a/splunk-ao-migration-tool/README.md
+++ b/splunk-ao-migration-tool/README.md
@@ -196,12 +196,12 @@ All sub-module paths follow the same rename pattern:
 | Old | New |
 |-----|-----|
 | `GalileoMetric` | `SplunkAOMetric` |
-| `GalileoMetrics` | `SplunkAOMetrics` |
+| `GalileoMetrics` | `SplunkAOEvaluators` |
 | `GalileoScorers` | **Removed** (see §5.2) |
 
 ```diff
 - from galileo import GalileoMetric, GalileoMetrics
-+ from splunk_ao import SplunkAOMetric, SplunkAOMetrics
++ from splunk_ao import SplunkAOMetric, SplunkAOEvaluators
 ```
 
 ### 3.4 Handlers & Middleware
@@ -330,14 +330,14 @@ The following symbols from `galileo` are **not available** in `splunk-ao`:
 
 ### 5.2 `GalileoScorers` Removed
 
-The `GalileoScorers` enum has been removed entirely. Migrate to `SplunkAOMetrics`:
+The `GalileoScorers` enum has been removed entirely. Migrate to `SplunkAOEvaluators`:
 
 ```diff
 - from galileo.schema.metrics import GalileoScorers
-+ from splunk_ao.schema.metrics import SplunkAOMetrics
++ from splunk_ao.schema.metrics import SplunkAOEvaluators
 
 - scorer = GalileoScorers.completeness
-+ scorer = SplunkAOMetrics.completeness
++ scorer = SplunkAOEvaluators.completeness
 ```
 
 ---
@@ -441,8 +441,8 @@ The following are **unchanged** between galileo and splunk-ao and require no mig
 - [ ] Rename `GalileoLoggerException` → `SplunkAOLoggerException`
 - [ ] Rename `GalileoFutureError` → `SplunkAOFutureError`
 - [ ] Rename `GalileoMetric` → `SplunkAOMetric`
-- [ ] Rename `GalileoMetrics` → `SplunkAOMetrics`
-- [ ] Replace `GalileoScorers` with `SplunkAOMetrics`
+- [ ] Rename `GalileoMetrics` → `SplunkAOEvaluators`
+- [ ] Replace `GalileoScorers` with `SplunkAOEvaluators`
 - [ ] Rename `GalileoAgentControlBridge` → `SplunkAOAgentControlBridge`
 - [ ] Rename all `GALILEO_*` environment variables to `SPLUNK_AO_*`
 - [ ] Update `.env`, `.env.example`, CI/CD secrets, and deployment configs
diff --git a/src/splunk_ao/__init__.py b/src/splunk_ao/__init__.py
index d435ae8a..54d1f98a 100644
--- a/src/splunk_ao/__init__.py
+++ b/src/splunk_ao/__init__.py
@@ -67,7 +67,7 @@
 from splunk_ao.provider import AnthropicProvider, AzureProvider, BedrockProvider, OpenAIProvider, Provider
 from splunk_ao.resources.models.document import Document
 from splunk_ao.schema.message import Message
-from splunk_ao.schema.metrics import SplunkAOMetrics
+from splunk_ao.schema.metrics import SplunkAOEvaluators
 from splunk_ao.shared.base import SyncState
 from splunk_ao.shared.exceptions import (
     AmbiguousConfigurationError,
@@ -149,7 +149,7 @@
     "SplunkAOFutureError",
     "SplunkAOLogger",
     "SplunkAOLoggerException",
-    "SplunkAOMetrics",
+    "SplunkAOEvaluators",
     "StepType",
     "StepWithChildSpans",
     "SyncState",
diff --git a/src/splunk_ao/agent_stream.py b/src/splunk_ao/agent_stream.py
index 23e7c905..5ba50dfc 100644
--- a/src/splunk_ao/agent_stream.py
+++ b/src/splunk_ao/agent_stream.py
@@ -21,7 +21,7 @@
 from splunk_ao.resources.models.log_records_available_columns_response import LogRecordsAvailableColumnsResponse
 from splunk_ao.resources.types import Unset
 from splunk_ao.schema.filters import FilterType
-from splunk_ao.schema.metrics import LocalMetricConfig, Metric, SplunkAOMetrics
+from splunk_ao.schema.metrics import LocalMetricConfig, Metric, SplunkAOEvaluators
 from splunk_ao.search import RecordType, Search
 from splunk_ao.shared.base import StateManagementMixin, SyncState
 from splunk_ao.shared.exceptions import ValidationError
@@ -78,10 +78,10 @@ class AgentStream(StateManagementMixin):
         agent_stream = project.create_agent_stream(name="Production Logs")
 
         # Enable metrics on the log stream
-        from splunk_ao.schema.metrics import SplunkAOMetrics
+        from splunk_ao.schema.metrics import SplunkAOEvaluators
         local_metrics = log_stream.enable_evaluators([
-            SplunkAOMetrics.correctness,
-            SplunkAOMetrics.completeness,
+            SplunkAOEvaluators.correctness,
+            SplunkAOEvaluators.completeness,
             "context_relevance"
         ])
 
@@ -441,7 +441,7 @@ def get_metrics(self) -> builtins.list[str]:
         return metric_names
 
     def set_metrics(
-        self, metrics: builtins.list[SplunkAOMetrics | Metric | LocalMetricConfig | str]
+        self, metrics: builtins.list[SplunkAOEvaluators | Metric | LocalMetricConfig | str]
     ) -> builtins.list[LocalMetricConfig]:
         """
         Set (replace) the metrics on this log stream.
@@ -451,7 +451,7 @@ def set_metrics(
 
         Args:
             metrics: List of metrics to set. Supports:
-                - SplunkAOMetrics enum values (e.g., SplunkAOMetrics.correctness)
+                - SplunkAOEvaluators enum values (e.g., SplunkAOEvaluators.correctness)
                 - Metric objects (including from Metric.get(id="..."))
                 - LocalMetricConfig objects for custom scoring functions
                 - String names of built-in metrics
diff --git a/src/splunk_ao/agent_streams.py b/src/splunk_ao/agent_streams.py
index d3d8c0f6..84ad68e6 100644
--- a/src/splunk_ao/agent_streams.py
+++ b/src/splunk_ao/agent_streams.py
@@ -12,7 +12,7 @@
 from splunk_ao.resources.models.log_stream_create_request import LogStreamCreateRequest
 from splunk_ao.resources.models.log_stream_response import LogStreamResponse
 from splunk_ao.resources.types import Unset
-from splunk_ao.schema.metrics import LocalMetricConfig, Metric, SplunkAOMetrics
+from splunk_ao.schema.metrics import LocalMetricConfig, Metric, SplunkAOEvaluators
 from splunk_ao.utils.env_helpers import _get_agent_stream_from_env, _get_project_from_env
 from splunk_ao.utils.log_config import get_logger
 from splunk_ao.utils.metrics import create_metric_configs
@@ -78,7 +78,7 @@ class AgentStream(LogStreamResponse):
 
     # Enable metrics on a log stream - RECOMMENDED APPROACH
     from splunk_ao.agent_streams import enable_evaluators
-    from splunk_ao.schema.metrics import SplunkAOMetrics
+    from splunk_ao.schema.metrics import SplunkAOEvaluators
 
     # Set environment variables first
     # export SPLUNK_AO_AGENT_STREAM="Production Logs"
@@ -86,8 +86,8 @@ class AgentStream(LogStreamResponse):
 
     # Clean and simple - just pass the metrics!
     local_metrics = enable_evaluators([
-        SplunkAOMetrics.correctness,
-        SplunkAOMetrics.completeness,
+        SplunkAOEvaluators.correctness,
+        SplunkAOEvaluators.completeness,
         "context_relevance"
     ])
 
@@ -123,7 +123,7 @@ def __init__(self, agent_stream: None | LogStreamResponse = None):
             return
 
     def enable_evaluators(
-        self, metrics: builtins.list[SplunkAOMetrics | Metric | LocalMetricConfig | str]
+        self, metrics: builtins.list[SplunkAOEvaluators | Metric | LocalMetricConfig | str]
     ) -> builtins.list[LocalMetricConfig]:
         """
         Enable metrics directly on this log stream instance.
@@ -139,10 +139,10 @@ def enable_evaluators(
 
         Parameters
         ----------
-        metrics : builtins.list[Union[SplunkAOMetrics, Metric, LocalMetricConfig, str]]
+        metrics : builtins.list[Union[SplunkAOEvaluators, Metric, LocalMetricConfig, str]]
             List of metrics to enable on this log stream. Supports multiple input formats:
 
-            - **SplunkAOMetrics enum values**: Built-in metrics like `SplunkAOMetrics.correctness`
+            - **SplunkAOEvaluators enum values**: Built-in metrics like `SplunkAOEvaluators.correctness`
             - **Metric objects**: Custom metrics with optional version specifications
             - **LocalMetricConfig objects**: Client-side metrics with custom scoring functions
             - **String names**: Built-in metric names like "correctness" or "toxicity"
@@ -169,7 +169,7 @@ def enable_evaluators(
 
         ```python
         from splunk_ao.agent_streams import AgentStreams
-        from splunk_ao.schema.metrics import SplunkAOMetrics
+        from splunk_ao.schema.metrics import SplunkAOEvaluators
 
         # Get a log stream first
         log_streams = AgentStreams()
@@ -177,8 +177,8 @@ def enable_evaluators(
 
         # Enable metrics directly - clean and intuitive!
         local_metrics = log_stream.enable_evaluators([
-            SplunkAOMetrics.correctness,
-            SplunkAOMetrics.completeness,
+            SplunkAOEvaluators.correctness,
+            SplunkAOEvaluators.completeness,
             "context_relevance",
             "toxicity"
         ])
@@ -196,7 +196,7 @@ def custom_scorer(trace_or_span):
             return 0.75  # Your scoring logic
 
         local_metrics = log_stream.enable_evaluators([
-            SplunkAOMetrics.correctness,
+            SplunkAOEvaluators.correctness,
             "completeness",
             Metric(name="domain_relevance", version=3),
             LocalMetricConfig(name="custom_metric", scorer_fn=custom_scorer)
@@ -481,7 +481,7 @@ def enable_evaluators(
         *,
         agent_stream_name: str | None = None,
         project_name: str | None = None,
-        metrics: builtins.list[SplunkAOMetrics | Metric | LocalMetricConfig | str],
+        metrics: builtins.list[SplunkAOEvaluators | Metric | LocalMetricConfig | str],
     ) -> builtins.list[LocalMetricConfig]:
         """
         Enable metrics for a log stream by configuring scorers.
@@ -498,9 +498,9 @@ def enable_evaluators(
             The name of the log stream. Takes precedence over the SPLUNK_AO_AGENT_STREAM environment variable. Defaults to None.
         project_name : Optional[str], optional
             The name of the project. Takes precedence over the SPLUNK_AO_PROJECT environment variable. Defaults to None.
-        metrics : builtins.list[Union[SplunkAOMetrics, Metric, LocalMetricConfig, str]]
+        metrics : builtins.list[Union[SplunkAOEvaluators, Metric, LocalMetricConfig, str]]
             List of metrics to enable. Can include:
-            - SplunkAOMetrics enum values (e.g., SplunkAOMetrics.correctness)
+            - SplunkAOEvaluators enum values (e.g., SplunkAOEvaluators.correctness)
             - Metric objects with name and optional version
             - LocalMetricConfig objects for custom local metrics
             - String names of built-in metrics
@@ -520,15 +520,15 @@ def enable_evaluators(
         ```python
         # Enable built-in metrics with explicit parameters
         from splunk_ao.agent_streams import AgentStreams
-        from splunk_ao.schema.metrics import SplunkAOMetrics
+        from splunk_ao.schema.metrics import SplunkAOEvaluators
 
         log_streams = AgentStreams()
         scorer_configs, local_metrics = log_streams.enable_evaluators(
             agent_stream_name="Production Logs",
             project_name="My AI Project",
             metrics=[
-                SplunkAOMetrics.correctness,
-                SplunkAOMetrics.completeness,
+                SplunkAOEvaluators.correctness,
+                SplunkAOEvaluators.completeness,
                 "context_relevance",
             ],
         )
@@ -686,7 +686,7 @@ def enable_evaluators(
     *,
     agent_stream_name: str | None = None,
     project_name: str | None = None,
-    metrics: builtins.list[SplunkAOMetrics | Metric | LocalMetricConfig | str],
+    metrics: builtins.list[SplunkAOEvaluators | Metric | LocalMetricConfig | str],
 ) -> builtins.list[LocalMetricConfig]:
     """
     Enable metrics for a log stream with flexible parameter and environment variable support.
@@ -714,9 +714,9 @@ def enable_evaluators(
     project_name : Optional[str], optional
         The name of the project. Takes precedence over SPLUNK_AO_PROJECT environment variable.
         If None, will use SPLUNK_AO_PROJECT env var. Defaults to None.
-    metrics : builtins.list[Union[SplunkAOMetrics, Metric, LocalMetricConfig, str]]
+    metrics : builtins.list[Union[SplunkAOEvaluators, Metric, LocalMetricConfig, str]]
         List of metrics to enable on the log stream. Can include:
-        - SplunkAOMetrics enum values (e.g., SplunkAOMetrics.correctness)
+        - SplunkAOEvaluators enum values (e.g., SplunkAOEvaluators.correctness)
         - Metric objects with name and optional version for custom metrics
         - LocalMetricConfig objects for client-side custom scoring functions
         - String names of built-in metrics (e.g., "correctness", "toxicity")
@@ -742,14 +742,14 @@ def enable_evaluators(
     ```python
     # Enable built-in metrics with explicit parameters
     from splunk_ao.agent_streams import enable_evaluators
-    from splunk_ao.schema.metrics import SplunkAOMetrics
+    from splunk_ao.schema.metrics import SplunkAOEvaluators
 
     local_metrics = enable_evaluators(
         agent_stream_name="Production Logs",
         project_name="My AI Project",
         metrics=[
-            SplunkAOMetrics.correctness,
-            SplunkAOMetrics.completeness,
+            SplunkAOEvaluators.correctness,
+            SplunkAOEvaluators.completeness,
             "context_relevance",
         ],
     )
@@ -772,7 +772,7 @@ def response_length_scorer(trace_or_span):
     local_metrics = enable_evaluators(
         agent_stream_name="Development Logs",
         metrics=[
-            SplunkAOMetrics.correctness,
+            SplunkAOEvaluators.correctness,
             "toxicity",
             Metric(name="my_custom_metric", version=2),
             LocalMetricConfig(
diff --git a/src/splunk_ao/evaluator.py b/src/splunk_ao/evaluator.py
index ef64164c..310db4a2 100644
--- a/src/splunk_ao/evaluator.py
+++ b/src/splunk_ao/evaluator.py
@@ -39,7 +39,7 @@
 )
 from splunk_ao.resources.models.invalid_result import InvalidResult
 from splunk_ao.resources.types import UNSET, File, Unset
-from splunk_ao.schema.metrics import LocalMetricConfig, SplunkAOMetrics
+from splunk_ao.schema.metrics import LocalMetricConfig, SplunkAOEvaluators
 from splunk_ao.schema.metrics import Metric as SchemaMetric
 from splunk_ao.scorers import Scorers
 from splunk_ao.shared.base import StateManagementMixin, SyncState
@@ -68,17 +68,17 @@ class BuiltInEvaluators:
         Evaluator.metrics.toxicity
     """
 
-    def __getattr__(self, name: str) -> SplunkAOMetrics:
+    def __getattr__(self, name: str) -> SplunkAOEvaluators:
         """Allow attribute-style access to built-in metrics."""
         # Try to find the metric by name (enum names match UI-visible names)
-        for scorer in SplunkAOMetrics:
+        for scorer in SplunkAOEvaluators:
             if scorer.name == name:
                 return scorer
-        raise AttributeError(f"Built-in metric '{name}' not found. Available: {[s.name for s in SplunkAOMetrics]}")
+        raise AttributeError(f"Built-in metric '{name}' not found. Available: {[s.name for s in SplunkAOEvaluators]}")
 
     def __dir__(self) -> list[str]:
         """Return list of available metric names for autocomplete."""
-        return [scorer.name for scorer in SplunkAOMetrics]
+        return [scorer.name for scorer in SplunkAOEvaluators]
 
 
 # Backwards-compatible alias
diff --git a/src/splunk_ao/experiment.py b/src/splunk_ao/experiment.py
index bb432c10..6cd4bc8b 100644
--- a/src/splunk_ao/experiment.py
+++ b/src/splunk_ao/experiment.py
@@ -45,7 +45,7 @@
 # TODO: DatasetRecord needed for function-based experiments
 # from splunk_ao.schema.datasets import DatasetRecord
 from splunk_ao.schema.filters import FilterType
-from splunk_ao.schema.metrics import LocalMetricConfig, Metric, SplunkAOMetrics
+from splunk_ao.schema.metrics import LocalMetricConfig, Metric, SplunkAOEvaluators
 from splunk_ao.search import RecordType, Search
 from splunk_ao.shared.base import StateManagementMixin, SyncState
 from splunk_ao.shared.exceptions import ValidationError
@@ -176,7 +176,7 @@ class Experiment(StateManagementMixin):
     prompt_name: str | None
     created_at: datetime.datetime | None
     updated_at: datetime.datetime | None
-    metrics: builtins.list[SplunkAOMetrics | Metric | LocalMetricConfig | str] | None
+    metrics: builtins.list[SplunkAOEvaluators | Metric | LocalMetricConfig | str] | None
     # TODO: Function-based experiments temporarily disabled - need to validate implementation
     # function: Callable | None
     model_alias: str | None
@@ -209,7 +209,7 @@ def __init__(
         prompt: Prompt | PromptTemplate | str | None = None,
         prompt_name: str | None = None,
         model: Model | str | None = None,
-        metrics: builtins.list[SplunkAOMetrics | Metric | LocalMetricConfig | str] | None = None,
+        metrics: builtins.list[SplunkAOEvaluators | Metric | LocalMetricConfig | str] | None = None,
         project_id: str | None = None,
         project_name: str | None = None,
         prompt_settings: PromptRunSettings | None = None,
@@ -2031,14 +2031,14 @@ def experiment_columns(self) -> ColumnCollection:
         columns = [Column(col) for col in response.columns]
         return ColumnCollection(columns)
 
-    def get_metric_aggregate(self, metric: SplunkAOMetrics | str) -> MetricAggregates | None:
+    def get_metric_aggregate(self, metric: SplunkAOEvaluators | str) -> MetricAggregates | None:
         """Return aggregate statistics for a specific metric.
 
         Looks up a metric by any of the following identifiers, tried in order:
 
-        1. :class:`~splunk_ao.schema.metrics.SplunkAOMetrics` enum value — its
+        1. :class:`~splunk_ao.schema.metrics.SplunkAOEvaluators` enum value — its
            ``value`` IS the human-readable label (e.g.
-           ``SplunkAOMetrics.correctness`` → ``"Correctness"``).
+           ``SplunkAOEvaluators.correctness`` → ``"Correctness"``).
         2. Scorer UUID string — direct lookup in :attr:`metric_aggregates`,
            no column resolution needed.
         3. Human-readable label string (e.g. ``"Correctness"``) — resolved
@@ -2052,7 +2052,7 @@ def get_metric_aggregate(self, metric: SplunkAOMetrics | str) -> MetricAggregate
         Parameters
         ----------
         metric :
-            Any of: a :class:`SplunkAOMetrics` enum value, scorer UUID string,
+            Any of: a :class:`SplunkAOEvaluators` enum value, scorer UUID string,
             human-readable label, or legacy metric_key_alias.
 
         Returns
@@ -2066,21 +2066,21 @@ def get_metric_aggregate(self, metric: SplunkAOMetrics | str) -> MetricAggregate
         --------
         Poll until a specific metric is computed, then assert::
 
-            from splunk_ao.schema.metrics import SplunkAOMetrics
+            from splunk_ao.schema.metrics import SplunkAOEvaluators
 
-            while experiment.get_metric_aggregate(SplunkAOMetrics.correctness) is None:
+            while experiment.get_metric_aggregate(SplunkAOEvaluators.correctness) is None:
                 time.sleep(5)
                 experiment.refresh()
 
-            agg = experiment.get_metric_aggregate(SplunkAOMetrics.correctness)
+            agg = experiment.get_metric_aggregate(SplunkAOEvaluators.correctness)
             assert agg.avg >= 0.95
         """
         aggregates = self.metric_aggregates
         if not aggregates:
             return None
 
-        # SplunkAOMetrics.value IS the human-readable label (e.g. "Correctness")
-        metric_str = metric.value if isinstance(metric, SplunkAOMetrics) else metric
+        # SplunkAOEvaluators.value IS the human-readable label (e.g. "Correctness")
+        metric_str = metric.value if isinstance(metric, SplunkAOEvaluators) else metric
 
         # Scorer UUID → direct lookup, no column resolution needed
         if _UUID_RE.fullmatch(metric_str):
diff --git a/src/splunk_ao/experiments.py b/src/splunk_ao/experiments.py
index b61b6fbe..52e5d1e5 100644
--- a/src/splunk_ao/experiments.py
+++ b/src/splunk_ao/experiments.py
@@ -28,7 +28,7 @@
 )
 from splunk_ao.schema.datasets import DatasetRecord
 from splunk_ao.schema.experiment_group import ExperimentGroupResponse
-from splunk_ao.schema.metrics import LocalMetricConfig, Metric, SplunkAOMetrics
+from splunk_ao.schema.metrics import LocalMetricConfig, Metric, SplunkAOEvaluators
 from splunk_ao.utils.datasets import create_rows_from_records, load_dataset
 from splunk_ao.utils.exceptions import _format_http_validation_error
 from splunk_ao.utils.headers_data import get_sdk_header
@@ -318,7 +318,7 @@ def run_experiment(
     dataset: Dataset | list[dict[str, Any] | str] | str | None = None,
     dataset_id: str | None = None,
     dataset_name: str | None = None,
-    metrics: list[SplunkAOMetrics | Metric | LocalMetricConfig | str] | None = None,
+    metrics: list[SplunkAOEvaluators | Metric | LocalMetricConfig | str] | None = None,
     function: Callable | None = None,
     experiment_tags: dict[str, str] | None = None,
     on_error: Callable[[Exception], None] | None = None,
diff --git a/src/splunk_ao/schema/metrics.py b/src/splunk_ao/schema/metrics.py
index 04c022dd..c41896ce 100644
--- a/src/splunk_ao/schema/metrics.py
+++ b/src/splunk_ao/schema/metrics.py
@@ -11,7 +11,7 @@
 from galileo_core.schemas.shared.metric import MetricValueType
 
 
-class SplunkAOMetrics(StrEnum):
+class SplunkAOEvaluators(StrEnum):
     """Built-in Splunk AO metric scorers.
 
     Values are human-readable UI labels used for scorer lookup via the API.
diff --git a/src/splunk_ao/types.py b/src/splunk_ao/types.py
index dda394e2..778189c7 100644
--- a/src/splunk_ao/types.py
+++ b/src/splunk_ao/types.py
@@ -6,11 +6,11 @@
 """
 
 from splunk_ao.evaluator import Evaluator
-from splunk_ao.schema.metrics import LocalMetricConfig, SplunkAOMetrics
+from splunk_ao.schema.metrics import LocalMetricConfig, SplunkAOEvaluators
 
 # Unified metric type that accepts all valid metric specifications
 MetricSpec = (
-    SplunkAOMetrics  # Built-in scorer enum (e.g., SplunkAOMetrics.correctness)
+    SplunkAOEvaluators  # Built-in scorer enum (e.g., SplunkAOEvaluators.correctness)
     | Evaluator  # Custom or local evaluator object
     | LocalMetricConfig  # Legacy local metric config
     | str  # String name of built-in metric (e.g., "correctness")
diff --git a/src/splunk_ao/utils/metrics.py b/src/splunk_ao/utils/metrics.py
index ceb05621..93b33884 100644
--- a/src/splunk_ao/utils/metrics.py
+++ b/src/splunk_ao/utils/metrics.py
@@ -9,7 +9,7 @@
 from galileo_core.schemas.shared.metric import MetricValueType
 from splunk_ao.resources.models.scorer_config import ScorerConfig
 from splunk_ao.resources.models.scorer_response import ScorerResponse
-from splunk_ao.schema.metrics import LocalMetricConfig, Metric, SplunkAOMetrics
+from splunk_ao.schema.metrics import LocalMetricConfig, Metric, SplunkAOEvaluators
 from splunk_ao.scorers import Scorers, ScorerSettings
 
 logger = logging.getLogger(__name__)
@@ -95,7 +95,7 @@ def _is_uuid(value: str) -> bool:
 def create_metric_configs(
     project_id: str,
     run_id: str | None,  # Can be experiment_id, agent_stream_id, or None (for trigger=True flow)
-    metrics: builtins.list[SplunkAOMetrics | Metric | LocalMetricConfig | str],
+    metrics: builtins.list[SplunkAOEvaluators | Metric | LocalMetricConfig | str],
 ) -> tuple[builtins.list[ScorerConfig], builtins.list[LocalMetricConfig]]:
     """
     Process metrics and create scorer configurations for experiments or log streams.
@@ -104,7 +104,7 @@ def create_metric_configs(
     validates they exist, and registers server-side metrics with Splunk AO.
 
     Metrics can be specified as:
-    - SplunkAOMetrics enum values (human-readable labels like "Correctness")
+    - SplunkAOEvaluators enum values (human-readable labels like "Correctness")
     - Metric objects with name and optional version
     - UUID strings (scorer IDs for direct lookup)
     - Plain strings (searched by label with name fallback)
@@ -138,7 +138,7 @@ def create_metric_configs(
 
     # Categorize metrics by type
     for metric in metrics:
-        if isinstance(metric, SplunkAOMetrics):
+        if isinstance(metric, SplunkAOEvaluators):
             label_searches.append((metric.value, None))
         elif isinstance(metric, Metric):
             label_searches.append((metric.name, metric.version))
diff --git a/tests/schemas/test_metrics.py b/tests/schemas/test_metrics.py
index c8b0451d..667f0b87 100644
--- a/tests/schemas/test_metrics.py
+++ b/tests/schemas/test_metrics.py
@@ -1,4 +1,4 @@
-from splunk_ao.schema.metrics import Metric, SplunkAOMetrics
+from splunk_ao.schema.metrics import Metric, SplunkAOEvaluators
 
 
 def test_metric_custom_with_version() -> None:
@@ -16,15 +16,15 @@ def test_metric_custom_no_version() -> None:
 
 
 def test_galileo_metrics_values_are_nonempty_strings() -> None:
-    """All SplunkAOMetrics values are non-empty human-readable strings."""
-    for member in SplunkAOMetrics:
+    """All SplunkAOEvaluators values are non-empty human-readable strings."""
+    for member in SplunkAOEvaluators:
         assert isinstance(member.value, str), f"{member.name} value is not a string"
         assert len(member.value.strip()) > 0, f"{member.name} has an empty value"
 
 
 def test_galileo_metrics_is_str_compatible() -> None:
-    """SplunkAOMetrics members are str-compatible (usable as plain strings)."""
-    member = SplunkAOMetrics.correctness
+    """SplunkAOEvaluators members are str-compatible (usable as plain strings)."""
+    member = SplunkAOEvaluators.correctness
     assert isinstance(member, str)
     assert member == "Correctness"
     assert member.value == "Correctness"
@@ -33,15 +33,15 @@ def test_galileo_metrics_is_str_compatible() -> None:
 def test_galileo_metrics_naming_convention() -> None:
     """Base names map to LLM versions, _luna suffix maps to SLM versions."""
     # LLM versions (base names) should NOT have "(SLM)" in the label
-    assert "(SLM)" not in SplunkAOMetrics.input_pii.value
-    assert "(SLM)" not in SplunkAOMetrics.input_tone.value
-    assert "(SLM)" not in SplunkAOMetrics.output_pii.value
-    assert "(SLM)" not in SplunkAOMetrics.output_tone.value
-    assert "(SLM)" not in SplunkAOMetrics.correctness.value
+    assert "(SLM)" not in SplunkAOEvaluators.input_pii.value
+    assert "(SLM)" not in SplunkAOEvaluators.input_tone.value
+    assert "(SLM)" not in SplunkAOEvaluators.output_pii.value
+    assert "(SLM)" not in SplunkAOEvaluators.output_tone.value
+    assert "(SLM)" not in SplunkAOEvaluators.correctness.value
 
     # SLM versions (_luna suffix) should have "(SLM)" in the label
-    assert "(SLM)" in SplunkAOMetrics.input_pii_luna.value
-    assert "(SLM)" in SplunkAOMetrics.input_tone_luna.value
-    assert "(SLM)" in SplunkAOMetrics.output_pii_luna.value
-    assert "(SLM)" in SplunkAOMetrics.output_tone_luna.value
-    assert "(SLM)" in SplunkAOMetrics.completeness_luna.value
+    assert "(SLM)" in SplunkAOEvaluators.input_pii_luna.value
+    assert "(SLM)" in SplunkAOEvaluators.input_tone_luna.value
+    assert "(SLM)" in SplunkAOEvaluators.output_pii_luna.value
+    assert "(SLM)" in SplunkAOEvaluators.output_tone_luna.value
+    assert "(SLM)" in SplunkAOEvaluators.completeness_luna.value
diff --git a/tests/test_agent_streams_evaluators.py b/tests/test_agent_streams_evaluators.py
index 6ba420c1..9247338c 100644
--- a/tests/test_agent_streams_evaluators.py
+++ b/tests/test_agent_streams_evaluators.py
@@ -8,7 +8,7 @@
 from splunk_ao.projects import Project
 from splunk_ao.resources.models import ProjectCreateResponse, ScorerResponse, ScorerTypes
 from splunk_ao.resources.models.log_stream_response import LogStreamResponse
-from splunk_ao.schema.metrics import LocalMetricConfig, SplunkAOMetrics
+from splunk_ao.schema.metrics import LocalMetricConfig, SplunkAOEvaluators
 from splunk_ao.utils.metrics import create_metric_configs
 
 
@@ -90,7 +90,7 @@ def test_create_metric_configs_with_builtin_metrics(
 
         # Test with built-in metrics
         scorers, local_metrics = create_metric_configs(
-            "project-123", "logstream-456", [SplunkAOMetrics.correctness, "completeness"]
+            "project-123", "logstream-456", [SplunkAOEvaluators.correctness, "completeness"]
         )
 
         # Verify scorers list_by_labels was called
@@ -143,7 +143,7 @@ def custom_scorer(trace_or_span) -> float:
 
         # Test with mixed metrics (only valid ones to avoid decorator error handling)
         scorers, local_metrics = create_metric_configs(
-            "project-123", "logstream-456", [SplunkAOMetrics.correctness, local_metric]
+            "project-123", "logstream-456", [SplunkAOEvaluators.correctness, local_metric]
         )
 
         # Verify local metrics
@@ -431,7 +431,7 @@ def test_mixed_uuid_and_label(self, mock_settings_class, mock_scorers_class) ->
         mock_settings_class.return_value.create.return_value = None
 
         # When: passing both a UUID and an enum
-        scorers, _ = create_metric_configs("project-123", "run-456", [scorer_id, SplunkAOMetrics.completeness])
+        scorers, _ = create_metric_configs("project-123", "run-456", [scorer_id, SplunkAOEvaluators.completeness])
 
         # Then: both lookup methods are called
         mock_scorers_class.return_value.list_by_ids.assert_called_once()
@@ -465,7 +465,7 @@ def test_run_id_none_skips_registration(self, mock_settings_class, mock_scorers_
         ]
 
         # When: run_id is None
-        scorers, _ = create_metric_configs("project-123", None, [SplunkAOMetrics.correctness])
+        scorers, _ = create_metric_configs("project-123", None, [SplunkAOEvaluators.correctness])
 
         # Then: scorers are returned but registration is skipped
         mock_settings_class.return_value.create.assert_not_called()
diff --git a/tests/test_experiment.py b/tests/test_experiment.py
index 83ff8860..665690cd 100644
--- a/tests/test_experiment.py
+++ b/tests/test_experiment.py
@@ -11,7 +11,7 @@
 from splunk_ao.resources.models.column_category import ColumnCategory
 from splunk_ao.resources.models.column_info import ColumnInfo
 from splunk_ao.resources.models.data_type import DataType
-from splunk_ao.schema.metrics import SplunkAOMetrics
+from splunk_ao.schema.metrics import SplunkAOEvaluators
 from splunk_ao.search import RecordType
 from splunk_ao.shared.base import SyncState
 from splunk_ao.shared.column import ColumnCollection
@@ -107,7 +107,7 @@ def test_init_with_prompt_name(self, reset_configuration: None) -> None:
 
     def test_init_with_metrics(self, reset_configuration: None) -> None:
         """Test initializing an experiment with metrics."""
-        metrics = [SplunkAOMetrics.correctness, "completeness"]
+        metrics = [SplunkAOEvaluators.correctness, "completeness"]
         experiment = Experiment(
             name="Test Experiment",
             dataset_name="test-dataset",
@@ -1492,7 +1492,7 @@ def test_returns_none_when_metric_aggregates_empty(
         synced_experiment._experiment_response = mock_response
 
         # When: getting a metric aggregate
-        result = synced_experiment.get_metric_aggregate(SplunkAOMetrics.correctness)
+        result = synced_experiment.get_metric_aggregate(SplunkAOEvaluators.correctness)
 
         # Then: None is returned without error
         assert result is None
@@ -1513,8 +1513,8 @@ def test_lookup_by_galileo_metrics_enum(
         )
         mock_config_class.get.return_value = MagicMock()
 
-        # When: looking up by SplunkAOMetrics enum (value == label "Correctness")
-        result = experiment.get_metric_aggregate(SplunkAOMetrics.correctness)
+        # When: looking up by SplunkAOEvaluators enum (value == label "Correctness")
+        result = experiment.get_metric_aggregate(SplunkAOEvaluators.correctness)
 
         # Then: the aggregate for the scorer UUID is returned
         assert result is not None
diff --git a/tests/test_experiments.py b/tests/test_experiments.py
index 50e9b7d2..323957d5 100644
--- a/tests/test_experiments.py
+++ b/tests/test_experiments.py
@@ -47,7 +47,7 @@
 from splunk_ao.resources.types import UNSET
 from splunk_ao.schema.datasets import DatasetRecord
 from splunk_ao.schema.experiment_group import ExperimentGroupResponse
-from splunk_ao.schema.metrics import LocalMetricConfig, SplunkAOMetrics
+from splunk_ao.schema.metrics import LocalMetricConfig, SplunkAOEvaluators
 from splunk_ao.utils.datasets import load_dataset_and_records
 from splunk_ao.utils.exceptions import _format_http_validation_error
 from tests.testutils.setup import setup_mock_logstreams_client, setup_mock_projects_client, setup_mock_traces_client
@@ -929,7 +929,7 @@ def test_run_experiment_w_prompt_template_and_metrics(
             project="awesome-new-project",
             dataset_id=dataset_id,
             prompt_template=prompt_template(),
-            metrics=[SplunkAOMetrics.correctness],
+            metrics=[SplunkAOEvaluators.correctness],
         )
 
         mock_get_project.assert_called_once_with(id=None, name="awesome-new-project")
diff --git a/tests/test_public_imports.py b/tests/test_public_imports.py
index c6a6eb6a..22da7f07 100644
--- a/tests/test_public_imports.py
+++ b/tests/test_public_imports.py
@@ -18,7 +18,7 @@ def test_scorer_prompt_types_are_exported():
         "Session",
         "Message",
         "Document",
-        "SplunkAOMetrics",
+        "SplunkAOEvaluators",
     ]
     missing = [name for name in types if not hasattr(splunk_ao, name)]
     assert not missing, f"Types missing from `splunk_ao` public API: {missing}"