diff --git a/dashboards/datadog-dashboard.json b/dashboards/datadog-dashboard.json
index 468b065..775a5d2 100644
--- a/dashboards/datadog-dashboard.json
+++ b/dashboards/datadog-dashboard.json
@@ -85,13 +85,13 @@
     {
       "id": 4,
       "definition": {
-        "title": "Error Rate by System",
+        "title": "Error Rate by Provider",
         "title_size": "16",
         "title_align": "left",
         "type": "query_value",
         "requests": [
           {
-            "q": "sum:gen_ai.client.operation.error{*} by {gen_ai.system}.as_rate() / sum:gen_ai.client.operation.duration{*} by {gen_ai.system}.as_count()",
+            "q": "sum:gen_ai.client.operation.error{*} by {gen_ai.provider.name}.as_rate() / sum:gen_ai.client.operation.duration{*} by {gen_ai.provider.name}.as_count()",
             "aggregator": "last"
           }
         ],
@@ -232,9 +232,9 @@
       "prefix": "gen_ai.request.model"
     },
     {
-      "name": "system",
+      "name": "provider",
       "default": "*",
-      "prefix": "gen_ai.system"
+      "prefix": "gen_ai.provider.name"
     }
   ],
   "layout_type": "ordered",
diff --git a/docs/contract/eval2otel-v1.md b/docs/contract/eval2otel-v1.md
index c617544..f7fc311 100644
--- a/docs/contract/eval2otel-v1.md
+++ b/docs/contract/eval2otel-v1.md
@@ -19,7 +19,7 @@ Every converted evaluation creates one client span named by operation:
 Every span must include:
 
 - `gen_ai.operation.name`
-- `gen_ai.system`
+- `gen_ai.provider.name`
 - `evalops.contract.version`
 - `evalops.semconv.version`
 - `evalops.eval.id`
@@ -28,8 +28,9 @@ Every span must include:
 - `evalops.redacted_content_count`
 - `evalops.truncated_content_count`
 
-Provider-aware conversions should include `gen_ai.provider.name` using the
-normalized provider names exported by `normalizeProviderName`.
+`gen_ai.provider.name` uses the normalized provider names exported by
+`normalizeProviderName`. `gen_ai.system` is intentionally not emitted because it
+is no longer present in the upstream OpenTelemetry GenAI registry.
 
 ## Attribute Registry
 
diff --git a/package-lock.json b/package-lock.json
index 2fdf143..26bd74f 100644
--- a/package-lock.json
+++ b/package-lock.json
@@ -27,7 +27,8 @@
         "jest": "^29.5.0",
         "prettier": "^3.0.0",
         "ts-jest": "^29.1.0",
-        "typescript": "^5.0.0"
+        "typescript": "^5.0.0",
+        "yaml": "^2.9.0"
       }
     },
     "node_modules/@ampproject/remapping": {
diff --git a/package.json b/package.json
index 799120b..193022c 100644
--- a/package.json
+++ b/package.json
@@ -50,7 +50,8 @@
     "jest": "^29.5.0",
     "prettier": "^3.0.0",
     "ts-jest": "^29.1.0",
-    "typescript": "^5.0.0"
+    "typescript": "^5.0.0",
+    "yaml": "^2.9.0"
   },
   "dependencies": {
     "@opentelemetry/api": "^1.9.1",
diff --git a/python/eval2otel/contract.py b/python/eval2otel/contract.py
index 66e5756..eedeaa1 100644
--- a/python/eval2otel/contract.py
+++ b/python/eval2otel/contract.py
@@ -12,6 +12,23 @@
 UNKNOWN_SEMCONV_VERSION = "unspecified"
 
 
+def normalize_provider_name(system: str | None) -> str | None:
+    if not system:
+        return None
+    value = system.lower()
+    if "azure" in value:
+        return "azure.openai"
+    if "bedrock" in value or "aws" in value:
+        return "aws.bedrock"
+    if "vertex" in value or "gemini" in value or "google" in value:
+        return "google.vertex"
+    if "anthropic" in value or "claude" in value:
+        return "anthropic"
+    if "openai" in value:
+        return "openai"
+    return value
+
+
 def sha256_payload(value: Any) -> str:
     encoded = json.dumps(value, sort_keys=True, separators=(",", ":"), default=str).encode("utf-8")
     return hashlib.sha256(encoded).hexdigest()
@@ -302,7 +319,7 @@ def build_span_attributes(
 ) -> MutableMapping[str, str | int | float]:
     attrs: MutableMapping[str, str | int | float] = build_eval2otel_attributes(eval_result, semconv_version)
     attrs["gen_ai.operation.name"] = eval_result.operation
-    attrs["gen_ai.system"] = eval_result.system or "unknown"
+    attrs["gen_ai.provider.name"] = normalize_provider_name(eval_result.system) or "unknown"
     if eval_result.request.get("model") is not None:
         attrs["gen_ai.request.model"] = str(eval_result.request["model"])
     if eval_result.response.get("model") is not None:
diff --git a/python/tests/test_contract.py b/python/tests/test_contract.py
index 61859ed..b17cc0f 100644
--- a/python/tests/test_contract.py
+++ b/python/tests/test_contract.py
@@ -100,7 +100,8 @@ def test_process_evaluation_emits_span_and_content_events_with_injected_tracer(s
 
         self.assertEqual(report.event_count, 2)
         self.assertEqual(tracer.spans[0].name, "gen_ai.chat")
-        self.assertEqual(tracer.spans[0].attributes["gen_ai.system"], "openai")
+        self.assertEqual(tracer.spans[0].attributes["gen_ai.provider.name"], "openai")
+        self.assertNotIn("gen_ai.system", tracer.spans[0].attributes)
         self.assertEqual(tracer.spans[0].attributes["gen_ai.usage.input_tokens"], 3)
         self.assertEqual(tracer.spans[0].events[0][0], "gen_ai.user.message")
         self.assertIn("evalops.content_sha256", tracer.spans[0].events[0][1])
diff --git a/src/converter.ts b/src/converter.ts
index f0a93e8..3f43745 100644
--- a/src/converter.ts
+++ b/src/converter.ts
@@ -246,18 +246,13 @@ export class Eval2OtelConverter {
     evalResult: EvalResult, 
     additionalAttributes?: Record<string, string | number | boolean>
   ): GenAIAttributes {
+    const provider = normalizeProviderName(evalResult.system) ?? 'unknown';
     const attributes: GenAIAttributes = {
       'gen_ai.operation.name': evalResult.operation,
-      'gen_ai.system': evalResult.system ?? 'unknown',
+      [ATTR.PROVIDER_NAME]: provider,
       ...buildEval2OtelAttributes(evalResult, this.config),
     };
 
-    // Provider discriminator aligned with latest GenAI semconv
-    const provider = normalizeProviderName(evalResult.system);
-    if (provider) {
-      (attributes as any)[ATTR.PROVIDER_NAME] = provider;
-    }
-
     // Add service attributes
     if (this.config.environment) {
       attributes['deployment.environment'] = this.config.environment;
@@ -454,7 +449,6 @@ export class Eval2OtelConverter {
     evalResult.conversation.messages.forEach((message, index) => {
       const eventName = `gen_ai.${message.role}.message`;
       const attributes: Record<string, string | number | boolean> = {
-        'gen_ai.system': evalResult.system ?? 'unknown',
         [ATTR.PROVIDER_NAME]: normalizeProviderName(evalResult.system) ?? 'unknown',
         [ATTR.MESSAGE_ROLE]: message.role,
         [ATTR.MESSAGE_INDEX]: index,
@@ -524,7 +518,6 @@ export class Eval2OtelConverter {
 
     evalResult.response.choices.forEach((choice) => {
       const attributes: Record<string, string | number | boolean> = {
-        'gen_ai.system': evalResult.system ?? 'unknown',
         [ATTR.PROVIDER_NAME]: normalizeProviderName(evalResult.system) ?? 'unknown',
         [ATTR.RESPONSE_CHOICE_INDEX]: choice.index,
         [ATTR.RESPONSE_FINISH_REASON]: choice.finishReason,
@@ -583,7 +576,7 @@ export class Eval2OtelConverter {
             : JSON.stringify(toolCall.function.arguments);
           if (this.canAddEvent(span)) {
             span.addEvent('gen_ai.tool.message', {
-            'gen_ai.system': evalResult.system ?? 'unknown',
+            [ATTR.PROVIDER_NAME]: normalizeProviderName(evalResult.system) ?? 'unknown',
             [ATTR.TOOL_NAME]: toolCall.function.name,
             [ATTR.TOOL_CALL_ID]: toolCall.id,
             [ATTR.RESPONSE_CHOICE_INDEX]: choice.index,
diff --git a/src/metrics.ts b/src/metrics.ts
index 1dd2aaa..5d3a58e 100644
--- a/src/metrics.ts
+++ b/src/metrics.ts
@@ -1,4 +1,5 @@
 import { metrics, Counter, Histogram, Meter, context as otContext } from '@opentelemetry/api';
+import { ATTR } from './attributes';
 import { normalizeProviderName } from './contract';
 import { getRagMetricValue } from './rag';
 import { ConversionReport, EvalResult, OtelConfig, ProcessOptions } from './types';
@@ -208,17 +209,11 @@ export class Eval2OtelMetrics {
   recordMetrics(evalResult: EvalResult, options?: ProcessOptions): void {
     const baseAttributes = {
       'gen_ai.operation.name': evalResult.operation,
-      'gen_ai.system': evalResult.system ?? 'unknown',
+      [ATTR.PROVIDER_NAME]: normalizeProviderName(evalResult.system) ?? 'unknown',
       'gen_ai.request.model': evalResult.request.model,
       'gen_ai.response.model': evalResult.response.model ?? evalResult.request.model,
     };
 
-    // Provider discriminator aligned with latest GenAI semconv
-    const provider = normalizeProviderName(evalResult.system);
-    if (provider) {
-      (baseAttributes as any)['gen_ai.provider.name'] = provider;
-    }
-
     // Add error type if present
     const attributes: Record<string, string | number> = { ...baseAttributes };
     if (evalResult.error) {
@@ -388,9 +383,8 @@ export class Eval2OtelMetrics {
       attrs['gen_ai.operation.name'] = evalResult.operation;
     }
     if (evalResult?.system) {
-      attrs['gen_ai.system'] = evalResult.system;
       const provider = normalizeProviderName(evalResult.system);
-      if (provider) attrs['gen_ai.provider.name'] = provider;
+      if (provider) attrs[ATTR.PROVIDER_NAME] = provider;
     }
     if (evalResult?.request?.model) {
       attrs['gen_ai.request.model'] = evalResult.request.model;
@@ -506,7 +500,7 @@ export class Eval2OtelMetrics {
   }): void {
     const baseAttributes = {
       'gen_ai.operation.name': evalResult.operation,
-      'gen_ai.system': evalResult.system ?? 'unknown',
+      [ATTR.PROVIDER_NAME]: normalizeProviderName(evalResult.system) ?? 'unknown',
       'gen_ai.request.model': evalResult.request.model,
     };
 
diff --git a/src/semconv.ts b/src/semconv.ts
index 83670fe..9ef72a8 100644
--- a/src/semconv.ts
+++ b/src/semconv.ts
@@ -12,7 +12,6 @@ export interface AttributeSpec {
 
 export const ATTRIBUTE_REGISTRY: AttributeSpec[] = [
   { key: 'gen_ai.operation.name', source: 'otel-genai', signal: 'all', stability: 'stable', description: 'GenAI operation name.' },
-  { key: 'gen_ai.system', source: 'otel-genai', signal: 'all', stability: 'stable', description: 'AI system or provider family.' },
   { key: 'error.type', source: 'otel-genai', signal: 'all', stability: 'stable', description: 'Error type for failed operations.' },
   { key: 'deployment.environment', source: 'otel-genai', signal: 'all', stability: 'stable', description: 'Deployment environment resource/context attribute.' },
   { key: ATTR.PROVIDER_NAME, source: 'otel-genai', signal: 'all', stability: 'stable', description: 'Normalized provider name.' },
diff --git a/src/types.ts b/src/types.ts
index 9375021..028eb75 100644
--- a/src/types.ts
+++ b/src/types.ts
@@ -338,7 +338,7 @@ export interface ProcessOptions {
 export interface GenAIAttributes {
   // Required
   'gen_ai.operation.name': string;
-  'gen_ai.system': string;
+  'gen_ai.provider.name': string;
   
   // Conditionally required
   'error.type'?: string;
diff --git a/test-harness/README.md b/test-harness/README.md
index 5e97467..1b9af16 100644
--- a/test-harness/README.md
+++ b/test-harness/README.md
@@ -74,7 +74,7 @@ curl "http://localhost:16686/api/traces?service=eval2otel-e2e-test"
 ### Traces in Jaeger
 - Service: `eval2otel-e2e-test`
 - Span names: `gen_ai.chat`, `gen_ai.embeddings`, `gen_ai.execute_tool`
-- Attributes: `gen_ai.system=openai`, `gen_ai.request.model=gpt-4`, etc.
+- Attributes: `gen_ai.provider.name=openai`, `gen_ai.request.model=gpt-4`, etc.
 - Events: Message events (when `captureContent=true`)
 
 ### Metrics in Prometheus
diff --git a/test/fixtures/otel/gen-ai-registry.yaml b/test/fixtures/otel/gen-ai-registry.yaml
new file mode 100644
index 0000000..7a477bb
--- /dev/null
+++ b/test/fixtures/otel/gen-ai-registry.yaml
@@ -0,0 +1,780 @@
+file_format: definition/2
+attributes:
+  - key: gen_ai.provider.name
+    type:
+      members:
+        - id: openai
+          stability: development
+          value: "openai"
+          brief: '[OpenAI](https://openai.com/)'
+        - id: gcp.gen_ai
+          stability: development
+          value: "gcp.gen_ai"
+          brief: "Any Google generative AI endpoint"
+          note: >
+            May be used when specific backend is unknown.
+        - id: gcp.vertex_ai
+          stability: development
+          value: "gcp.vertex_ai"
+          brief: "[Vertex AI](https://cloud.google.com/vertex-ai)"
+          note: >
+            Used when accessing the 'aiplatform.googleapis.com' endpoint.
+        - id: gcp.gemini
+          stability: development
+          value: "gcp.gemini"
+          brief: '[Gemini](https://cloud.google.com/products/gemini)'
+          note: >
+            Used when accessing the 'generativelanguage.googleapis.com' endpoint.
+            Also known as the AI Studio API.
+        - id: anthropic
+          stability: development
+          value: "anthropic"
+          brief: '[Anthropic](https://www.anthropic.com/)'
+        - id: cohere
+          stability: development
+          value: "cohere"
+          brief: '[Cohere](https://cohere.com/)'
+        - id: azure.ai.inference
+          stability: development
+          value: "azure.ai.inference"
+          brief: 'Azure AI Inference'
+        - id: azure.ai.openai
+          stability: development
+          value: "azure.ai.openai"
+          brief: '[Azure OpenAI](https://learn.microsoft.com/en-us/azure/ai-services/openai/overview)'
+        - id: ibm.watsonx.ai
+          stability: development
+          value: "ibm.watsonx.ai"
+          brief: '[IBM Watsonx AI](https://www.ibm.com/products/watsonx-ai)'
+        - id: aws.bedrock
+          stability: development
+          value: "aws.bedrock"
+          brief: '[AWS Bedrock](https://aws.amazon.com/bedrock)'
+        - id: perplexity
+          stability: development
+          value: "perplexity"
+          brief: '[Perplexity](https://www.perplexity.ai/)'
+        - id: x_ai
+          stability: development
+          value: "x_ai"
+          brief: '[xAI](https://x.ai/)'
+        - id: deepseek
+          stability: development
+          value: "deepseek"
+          brief: '[DeepSeek](https://www.deepseek.com/)'
+        - id: groq
+          stability: development
+          value: "groq"
+          brief: '[Groq](https://groq.com/)'
+        - id: mistral_ai
+          stability: development
+          value: "mistral_ai"
+          brief: '[Mistral AI](https://mistral.ai/)'
+
+    brief: The Generative AI provider as identified by the client or server instrumentation.
+    note: |
+      The attribute SHOULD be set based on the instrumentation's best
+      knowledge and may differ from the actual model provider.
+
+      Multiple providers, including Azure OpenAI, Gemini, and AI hosting platforms
+      are accessible using the OpenAI REST API and corresponding client libraries,
+      but may proxy or host models from different providers.
+
+      The `gen_ai.request.model`, `gen_ai.response.model`, and `server.address`
+      attributes may help identify the actual system in use.
+
+      The `gen_ai.provider.name` attribute acts as a discriminator that
+      identifies the GenAI telemetry format flavor specific to that provider
+      within GenAI semantic conventions.
+      It SHOULD be set consistently with provider-specific attributes and signals.
+      For example, GenAI spans, metrics, and events related to AWS Bedrock
+      should have the `gen_ai.provider.name` set to `aws.bedrock` and include
+      applicable `aws.bedrock.*` attributes and are not expected to include
+      `openai.*` attributes.
+    stability: development
+  - key: gen_ai.request.model
+    type: string
+    brief: The name of the GenAI model a request is being made to.
+    examples: 'gpt-4'
+    stability: development
+  - key: gen_ai.request.max_tokens
+    type: int
+    brief: The maximum number of tokens the model generates for a request.
+    examples: [100]
+    stability: development
+  - key: gen_ai.request.choice.count
+    type: int
+    brief: The target number of candidate completions to return.
+    examples: [3]
+    stability: development
+  - key: gen_ai.request.temperature
+    type: double
+    brief: The temperature setting for the GenAI request.
+    examples: [0.0]
+    stability: development
+  - key: gen_ai.request.top_p
+    type: double
+    brief: The top_p sampling setting for the GenAI request.
+    examples: [1.0]
+    stability: development
+  - key: gen_ai.request.top_k
+    type: double
+    brief: The top_k sampling setting for the GenAI request.
+    examples: [1.0]
+    stability: development
+  - key: gen_ai.request.stop_sequences
+    type: string[]
+    brief: List of sequences that the model will use to stop generating further tokens.
+    examples:
+      - [forest, lived]
+    stability: development
+  - key: gen_ai.request.frequency_penalty
+    type: double
+    brief: The frequency penalty setting for the GenAI request.
+    examples: [0.1]
+    stability: development
+  - key: gen_ai.request.presence_penalty
+    type: double
+    brief: The presence penalty setting for the GenAI request.
+    examples: [0.1]
+    stability: development
+  - key: gen_ai.request.encoding_formats
+    type: string[]
+    brief: The encoding formats requested in an embeddings operation, if specified.
+    note: >
+      In some GenAI systems the encoding formats are called embedding types.
+      Also, some GenAI systems only accept a single format per request.
+    examples:
+      - ['base64']
+      - ['float', 'binary']
+    stability: development
+  - key: gen_ai.request.seed
+    type: int
+    brief: Requests with same seed value more likely to return same result.
+    examples: [100]
+    stability: development
+  - key: gen_ai.request.stream
+    type: boolean
+    brief: Indicates whether the GenAI request was made in streaming mode.
+    stability: development
+  - key: gen_ai.response.id
+    type: string
+    brief: The unique identifier for the completion.
+    examples: ['chatcmpl-123']
+    stability: development
+  - key: gen_ai.response.model
+    type: string
+    brief: The name of the model that generated the response.
+    examples: ['gpt-4-0613']
+    stability: development
+  - key: gen_ai.response.finish_reasons
+    type: string[]
+    brief: Array of reasons the model stopped generating tokens, corresponding to each generation received.
+    examples:
+      - [stop]
+      - [stop, length]
+    stability: development
+  - key: gen_ai.response.time_to_first_chunk
+    type: double
+    brief: >
+      Time to first chunk in a streaming response, measured from request issuance, in seconds.
+      The value is measured from when the client issues the generation request to when the first
+      chunk is received in the response stream.
+    examples: [0.5, 1.2]
+    stability: development
+  - key: gen_ai.usage.input_tokens
+    type: int
+    brief: The number of tokens used in the GenAI input (prompt).
+    note: |
+      This value SHOULD include all types of input tokens, including cached tokens.
+      Instrumentations SHOULD make a best effort to populate this value, using a total
+      provided by the provider when available or, depending on the provider API,
+      by summing different token types parsed from the provider output.
+    examples: [100]
+    stability: development
+  - key: gen_ai.usage.cache_read.input_tokens
+    type: int
+    brief: The number of input tokens served from a provider-managed cache.
+    note: >
+      The value SHOULD be included in `gen_ai.usage.input_tokens`.
+    examples: [50]
+    stability: development
+  - key: gen_ai.usage.cache_creation.input_tokens
+    type: int
+    brief: The number of input tokens written to a provider-managed cache.
+    note: >
+      The value SHOULD be included in `gen_ai.usage.input_tokens`.
+    examples: [25]
+    stability: development
+  - key: gen_ai.usage.output_tokens
+    type: int
+    brief: The number of tokens used in the GenAI response (completion).
+    examples: [180]
+    stability: development
+  - key: gen_ai.usage.reasoning.output_tokens
+    type: int
+    brief: The number of output tokens used for reasoning (e.g. chain-of-thought, extended thinking).
+    note: >
+      The value SHOULD be included in `gen_ai.usage.output_tokens`.
+    examples: [50]
+    stability: development
+  - key: gen_ai.token.type
+    type:
+      members:
+        - id: input
+          stability: development
+          value: "input"
+          brief: 'Input tokens (prompt, input, etc.)'
+        - id: output
+          stability: development
+          value: "output"
+          brief: 'Output tokens (completion, response, etc.)'
+    brief: The type of token being counted.
+    examples: ['input', 'output']
+    stability: development
+  - key: gen_ai.conversation.id
+    type: string
+    brief: The unique identifier for a conversation (session, thread), used to store and correlate messages within this conversation.
+    examples: ["conv_5j66UpCpwteGg4YSxUnt7lPY"]
+    stability: development
+  - key: gen_ai.agent.id
+    type: string
+    brief: The unique identifier of the GenAI agent.
+    examples: ['asst_5j66UpCpwteGg4YSxUnt7lPY']
+    stability: development
+  - key: gen_ai.agent.name
+    type: string
+    brief: Human-readable name of the GenAI agent provided by the application.
+    examples: ["Math Tutor", "Fiction Writer"]
+    stability: development
+  - key: gen_ai.agent.description
+    type: string
+    brief: Free-form description of the GenAI agent provided by the application.
+    examples: ["Helps with math problems", "Generates fiction stories"]
+    stability: development
+  - key: gen_ai.agent.version
+    type: string
+    brief: The version of the GenAI agent.
+    examples: ["1.0.0", "2025-05-01"]
+    stability: development
+  - key: gen_ai.tool.name
+    type: string
+    brief: Name of the tool utilized by the agent.
+    examples: ["Flights"]
+    stability: development
+  - key: gen_ai.tool.call.id
+    type: string
+    brief: The tool call identifier.
+    examples: ['call_mszuSIzqtI65i1wAUOE8w5H4']
+    stability: development
+  - key: gen_ai.tool.description
+    type: string
+    brief: The tool description.
+    examples: ["Multiply two numbers"]
+    stability: development
+  - key: gen_ai.tool.type
+    type: string
+    brief: Type of the tool utilized by the agent
+    note: >
+      Extension: A tool executed on the agent-side to directly call external APIs, bridging the gap between the agent and real-world systems.
+        Agent-side operations involve actions that are performed by the agent on the server or within the agent's controlled environment.
+      Function: A tool executed on the client-side, where the agent generates parameters for a predefined function, and the client executes the logic.
+        Client-side operations are actions taken on the user's end or within the client application.
+      Datastore: A tool used by the agent to access and query structured or unstructured external data for retrieval-augmented tasks or knowledge updates.
+    examples: ['function', 'extension', 'datastore']
+    stability: development
+  - key: gen_ai.tool.call.arguments
+    type: any
+    brief: Parameters passed to the tool call.
+    note: |
+      > [!WARNING]
+      > This attribute may contain sensitive information.
+
+      It's expected to be an object - in case a serialized string is available
+      to the instrumentation, the instrumentation SHOULD do the best effort to
+      deserialize it to an object. When recorded on spans, it MAY be recorded as a JSON string if structured format is not supported and SHOULD be recorded in structured form otherwise.
+    examples:
+      - |
+        {
+            "location": "San Francisco?",
+            "date": "2025-10-01"
+        }
+
+    stability: development
+  - key: gen_ai.tool.call.result
+    type: any
+    brief: The result returned by the tool call (if any and if execution was successful).
+    note: |
+      > [!WARNING]
+      > This attribute may contain sensitive information.
+
+      It's expected to be an object - in case a serialized string is available
+      to the instrumentation, the instrumentation SHOULD do the best effort to
+      deserialize it to an object. When recorded on spans, it MAY be recorded as a JSON string if structured format is not supported and SHOULD be recorded in structured form otherwise.
+    examples:
+      - |
+        {
+          "temperature_range": {
+            "high": 75,
+            "low": 60
+          },
+          "conditions": "sunny"
+        }
+
+    stability: development
+  - key: gen_ai.tool.definitions
+    type: any
+    brief: The list of tool definitions available to the GenAI agent or model.
+    note: |
+      Instrumentations MUST follow [Tool Definitions JSON Schema](/docs/gen-ai/gen-ai-tool-definitions.json).
+
+      When the attribute is recorded on events, it MUST be recorded in structured
+      form. When recorded on spans, it MAY be recorded as a JSON string if structured
+      format is not supported and SHOULD be recorded in structured form otherwise.
+
+      Since this attribute could be large, it's NOT RECOMMENDED to populate
+      non-required properties by default. Instrumentations MAY provide a way
+      to enable populating optional properties.
+    examples:
+      - |
+        [
+          {
+            "type": "function",
+            "name": "get_current_weather",
+            "description": "Get the current weather in a given location",
+            "parameters": {
+              "type": "object",
+              "properties": {
+                "location": {
+                  "type": "string",
+                  "description": "The city and state, e.g. San Francisco, CA"
+                },
+                "unit": {
+                  "type": "string",
+                  "enum": [
+                    "celsius",
+                    "fahrenheit"
+                  ]
+                }
+              },
+              "required": [
+                "location",
+                "unit"
+              ]
+            }
+          }
+        ]
+
+    stability: development
+  - key: gen_ai.data_source.id
+    type: string
+    brief: The data source identifier.
+    note: >
+      Data sources are used by AI agents and RAG applications to store grounding data.
+      A data source may be an external database, object store, document collection, website, or any other storage system used by the GenAI agent or application.
+      The `gen_ai.data_source.id` SHOULD match the identifier used by the GenAI system rather than a name specific to the external storage, such as a database or
+      object store. Semantic conventions referencing `gen_ai.data_source.id` MAY also leverage additional attributes, such as `db.*`, to further identify and describe the data source.
+    examples: ['H7STPQYOND']
+    stability: development
+  - key: gen_ai.operation.name
+    type:
+      members:
+        - id: chat
+          value: "chat"
+          brief: 'Chat completion operation such as [OpenAI Chat API](https://platform.openai.com/docs/api-reference/chat)'
+          stability: development
+        - id: generate_content
+          value: "generate_content"
+          brief: 'Multimodal content generation operation such as [Gemini Generate Content](https://ai.google.dev/api/generate-content)'
+          stability: development
+        - id: text_completion
+          value: "text_completion"
+          brief: 'Text completions operation such as [OpenAI Completions API (Legacy)](https://platform.openai.com/docs/api-reference/completions)'
+          stability: development
+        - id: embeddings
+          value: "embeddings"
+          brief: 'Embeddings operation such as [OpenAI Create embeddings API](https://platform.openai.com/docs/api-reference/embeddings/create)'
+          stability: development
+        - id: retrieval
+          value: "retrieval"
+          brief: 'Retrieval operation such as [OpenAI Search Vector Store API](https://platform.openai.com/docs/api-reference/vector-stores/search)'
+          stability: development
+        - id: create_agent
+          value: "create_agent"
+          brief: 'Create GenAI agent'
+          stability: development
+        - id: invoke_agent
+          value: "invoke_agent"
+          brief: 'Invoke GenAI agent'
+          stability: development
+        - id: execute_tool
+          value: "execute_tool"
+          brief: 'Execute a tool'
+          stability: development
+        - id: invoke_workflow
+          value: "invoke_workflow"
+          brief: 'Invoke GenAI workflow'
+          stability: development
+        - id: plan
+          value: "plan"
+          brief: 'Agent planning or task decomposition phase'
+          stability: development
+        - id: search_memory
+          value: "search_memory"
+          brief: 'Search/query memories from a memory store'
+          stability: development
+        - id: create_memory
+          value: "create_memory"
+          brief: 'Create new memory records'
+          stability: development
+        - id: update_memory
+          value: "update_memory"
+          brief: 'Update existing memory records'
+          stability: development
+        - id: upsert_memory
+          value: "upsert_memory"
+          brief: 'Create or update memory records without the caller choosing which'
+          stability: development
+        - id: delete_memory
+          value: "delete_memory"
+          brief: 'Delete memory records'
+          stability: development
+        - id: create_memory_store
+          value: "create_memory_store"
+          brief: 'Create or initialize a memory store'
+          stability: development
+        - id: delete_memory_store
+          value: "delete_memory_store"
+          brief: 'Delete or deprovision a memory store'
+          stability: development
+    brief: The name of the operation being performed.
+    note: >
+      If one of the predefined values applies, but specific system uses a different name it's RECOMMENDED to document it in the semantic
+      conventions for specific GenAI system and use system-specific name in the instrumentation.
+      If a different name is not documented, instrumentation libraries SHOULD use applicable predefined value.
+    stability: development
+  - key: gen_ai.output.type
+    type:
+      members:
+        - id: text
+          value: "text"
+          brief: 'Plain text'
+          stability: development
+        - id: json
+          value: "json"
+          brief: 'JSON object with known or unknown schema'
+          stability: development
+        - id: image
+          value: "image"
+          brief: 'Image'
+          stability: development
+        - id: speech
+          value: "speech"
+          brief: 'Speech'
+          stability: development
+        # we might need to record requested and actual output types on the same span/event
+        # at some point. In this case, we might need to add a new attribute.
+        # we may also need to record an array of types if multiple are requested/returned.
+    brief: Represents the content type requested by the client.
+    note: >
+      This attribute SHOULD be used when the client requests output of a
+      specific type. The model may return zero or more outputs of this type.
+
+      This attribute specifies the output modality and not the actual output format.
+      For example, if an image is requested, the actual output could be a
+      URL pointing to an image file.
+
+      Additional output format details may be recorded in the future in the
+      `gen_ai.output.{type}.*` attributes.
+    stability: development
+  - key: gen_ai.embeddings.dimension.count
+    type: int
+    brief: The number of dimensions the resulting output embeddings should have.
+    examples: [512, 1024]
+    stability: development
+  - key: gen_ai.retrieval.documents
+    type: any
+    brief: The documents retrieved.
+    note: |
+      Instrumentations MUST follow [Retrieval documents JSON schema](/docs/gen-ai/gen-ai-retrieval-documents.json).
+      When the attribute is recorded on events, it MUST be recorded in structured
+      form. When recorded on spans, it MAY be recorded as a JSON string if structured
+      format is not supported and SHOULD be recorded in structured form otherwise.
+
+      Each document object SHOULD contain at least the following properties:
+      `id` (string): A unique identifier for the document, `score` (double): The relevance score of the document
+    examples:
+      - |
+        [
+          {
+            "id": "doc_123",
+            "score": 0.95
+          },
+          {
+            "id": "doc_456",
+            "score": 0.87
+          },
+          {
+            "id": "doc_789",
+            "score": 0.82
+          }
+        ]
+    stability: development
+  - key: gen_ai.retrieval.query.text
+    type: string
+    brief: The query text used for retrieval.
+    note: |
+      > [!Warning]
+      > This attribute may contain sensitive information.
+    examples: ["What is the capital of France?", "weather in Paris"]
+    stability: development
+  - key: gen_ai.memory.store.id
+    type: string
+    brief: The unique identifier of the memory store.
+    note: >
+      Semantic conventions for individual components SHOULD document what `gen_ai.memory.store.id` maps
+      to within the implementation.
+    examples: ["ms_abc123", "user-preferences-store"]
+    stability: development
+  - key: gen_ai.memory.record.id
+    type: string
+    brief: The unique identifier of the memory record.
+    examples: ["mem_5j66UpCpwteGg4YSxUnt7lPY"]
+    stability: development
+  - key: gen_ai.memory.record.count
+    type: int
+    brief: The number of memory records relevant to the operation.
+    note: >
+      For `search_memory` operations, this is the number of memory records returned by the operation.
+      For `create_memory` operations, this is the number of memory records the operation attempted to create.
+      For `update_memory` operations, this is the number of memory records the operation attempted to
+      modify. For `upsert_memory` operations, this is the number of memory records the operation
+      attempted to create or update. For `delete_memory` operations, this is the number of memory
+      records the operation attempted to delete.
+    examples: [3]
+    stability: development
+  - key: gen_ai.memory.query.text
+    type: string
+    brief: The search query used to retrieve memories.
+    note: |
+      Instrumentations SHOULD NOT capture this attribute by default. Capture SHOULD be gated
+      by an explicit user opt-in, for example `OTEL_INSTRUMENTATION_GENAI_CAPTURE_MESSAGE_CONTENT`.
+
+      > [!Warning]
+      > This attribute may contain sensitive information.
+    examples: ["user dietary preferences", "past flight bookings"]
+    stability: development
+  - key: gen_ai.memory.records
+    type: any
+    brief: The memory records stored or retrieved in a memory operation.
+    note: |
+      Instrumentations MUST follow [Memory records JSON schema](/docs/gen-ai/gen-ai-memory-records.json).
+      When the attribute is recorded on events, it MUST be recorded in structured
+      form. When recorded on spans, it MAY be recorded as a JSON string if structured
+      format is not supported and SHOULD be recorded in structured form otherwise.
+
+      Instrumentations SHOULD NOT capture this attribute by default. Capture SHOULD be gated
+      by an explicit user opt-in, for example `OTEL_INSTRUMENTATION_GENAI_CAPTURE_MESSAGE_CONTENT`.
+
+      > [!Warning]
+      > This attribute may contain sensitive information including user/PII data.
+    examples:
+      - |
+        [
+          {
+            "content": "User prefers dark mode",
+            "id": "mem_123",
+            "score": 0.95
+          },
+          {
+            "content": {
+              "preference": "vegetarian meals",
+              "confidence": 0.9
+            },
+            "metadata": {
+              "source": "profile"
+            }
+          }
+        ]
+    stability: development
+  - key: gen_ai.system_instructions
+    type: any
+    brief: The system message or instructions provided to the GenAI model separately from the chat history.
+    note: |
+      This attribute SHOULD be used when the corresponding provider or API
+      allows to provide system instructions or messages separately from the
+      chat history.
+
+      Instructions that are part of the chat history SHOULD be recorded in
+      `gen_ai.input.messages` attribute instead.
+
+      Instrumentations MUST follow [System instructions JSON schema](/docs/gen-ai/gen-ai-system-instructions.json).
+
+      When recorded on spans, it MAY be recorded as a JSON string if structured
+      format is not supported and SHOULD be recorded in structured form otherwise.
+
+      Instrumentations MAY provide a way for users to filter or truncate
+      system instructions.
+
+      > [!Warning]
+      > This attribute may contain sensitive information.
+
+      See [Recording content on attributes](/docs/gen-ai/gen-ai-spans.md#recording-content-on-attributes)
+      section for more details.
+    examples:
+      - |
+        [
+          {
+            "type": "text",
+            "content": "You are an Agent that greet users, always use greetings tool to respond"
+          }
+        ]
+      - |
+        [
+          {
+            "type": "text",
+            "content": "You are a language translator."
+          },
+          {
+            "type": "text",
+            "content": "Your mission is to translate text in English to French."
+          }
+        ]
+    stability: development
+  - key: gen_ai.input.messages
+    type: any
+    brief: >
+      The chat history provided to the model as an input.
+    note: |
+      Instrumentations MUST follow [Input messages JSON schema](/docs/gen-ai/gen-ai-input-messages.json).
+      When the attribute is recorded on events, it MUST be recorded in structured
+      form. When recorded on spans, it MAY be recorded as a JSON string if structured
+      format is not supported and SHOULD be recorded in structured form otherwise.
+
+      Messages MUST be provided in the order they were sent to the model.
+      Instrumentations MAY provide a way for users to filter or truncate
+      input messages.
+
+      > [!Warning]
+      > This attribute is likely to contain sensitive information including user/PII data.
+
+      See [Recording content on attributes](/docs/gen-ai/gen-ai-spans.md#recording-content-on-attributes)
+      section for more details.
+    examples:
+      - |
+        [
+          {
+            "role": "user",
+            "parts": [
+              {
+                "type": "text",
+                "content": "Weather in Paris?"
+              }
+            ]
+          },
+          {
+            "role": "assistant",
+            "parts": [
+              {
+                "type": "tool_call",
+                "id": "call_VSPygqKTWdrhaFErNvMV18Yl",
+                "name": "get_weather",
+                "arguments": {
+                  "location": "Paris"
+                }
+              }
+            ]
+          },
+          {
+            "role": "tool",
+            "parts": [
+              {
+                "type": "tool_call_response",
+                "id": " call_VSPygqKTWdrhaFErNvMV18Yl",
+                "result": "rainy, 57°F"
+              }
+            ]
+          }
+        ]
+    stability: development
+  - key: gen_ai.output.messages
+    type: any
+    brief: Messages returned by the model where each message represents a specific model response (choice, candidate).
+    note: |
+      Instrumentations MUST follow [Output messages JSON schema](/docs/gen-ai/gen-ai-output-messages.json)
+
+      Each message represents a single output choice/candidate generated by
+      the model. Each message corresponds to exactly one generation
+      (choice/candidate) and vice versa - one choice cannot be split across
+      multiple messages or one message cannot contain parts from multiple choices.
+
+      When the attribute is recorded on events, it MUST be recorded in structured
+      form. When recorded on spans, it MAY be recorded as a JSON string if structured
+      format is not supported and SHOULD be recorded in structured form otherwise.
+
+      Instrumentations MAY provide a way for users to filter or truncate
+      output messages.
+
+      > [!Warning]
+      > This attribute is likely to contain sensitive information including user/PII data.
+
+      See [Recording content on attributes](/docs/gen-ai/gen-ai-spans.md#recording-content-on-attributes)
+      section for more details.
+    examples:
+      - |
+        [
+          {
+            "role": "assistant",
+            "parts": [
+              {
+                "type": "text",
+                "content": "The weather in Paris is currently rainy with a temperature of 57°F."
+              }
+            ],
+            "finish_reason": "stop"
+          }
+        ]
+    stability: development
+  - key: gen_ai.evaluation.name
+    type: string
+    brief: The name of the evaluation metric used for the GenAI response.
+    examples: ["Relevance", "IntentResolution"]
+    stability: development
+  - key: gen_ai.evaluation.score.value
+    type: double
+    brief: The evaluation score returned by the evaluator.
+    examples: [4.0]
+    stability: development
+  - key: gen_ai.evaluation.score.label
+    type: string
+    brief: Human readable label for evaluation.
+    note: >
+      This attribute provides a human-readable interpretation of the evaluation score produced by an evaluator.
+      For example, a score value of 1 could mean "relevant" in one evaluation system and "not relevant" in another, depending on the scoring range and evaluator.
+      The label SHOULD have low cardinality.
+      Possible values depend on the evaluation metric and evaluator used; implementations SHOULD document the possible values.
+    examples: ["relevant", "not_relevant", "correct", "incorrect", "pass", "fail"]
+    stability: development
+  - key: gen_ai.evaluation.explanation
+    type: string
+    brief: A free-form explanation for the assigned score provided by the evaluator.
+    examples: ["The response is factually accurate but lacks sufficient detail to fully address the question."]
+    stability: development
+  - key: gen_ai.prompt.name
+    type: string
+    brief: The name of the prompt that uniquely identifies it.
+    examples: ["analyze-code"]
+    stability: development
+  - key: gen_ai.workflow.name
+    type: string
+    brief: Human-readable name of the GenAI workflow provided by the application.
+    note: |
+      This attribute can be populated in different frameworks; for example, as the name of the first chain in LangChain or the name of the crew in CrewAI.
+      The workflow name is usually provided by the application in a way that is specific to the generative AI framework or library that orchestrates the workflow.
+      It is usually a static name that is expected to be unique within an application.
+
+      `gen_ai.workflow.name` MUST have low cardinality.
+      Semantic conventions for individual Generative AI frameworks SHOULD document what `gen_ai.workflow.name` means in the context of that framework.
+      If there is no low-cardinality workflow name available for a given framework, this attribute MUST NOT be captured by default.
+    examples: ["multi_agent_rag", "customer_support_pipeline"]
+    stability: development
diff --git a/test/metrics-guards.test.ts b/test/metrics-guards.test.ts
index b155f3e..2aa4686 100644
--- a/test/metrics-guards.test.ts
+++ b/test/metrics-guards.test.ts
@@ -16,7 +16,7 @@ describe('Metrics guardrails: allowlist and cap', () => {
     const m = new Eval2OtelMetrics({
       serviceName: 'svc',
       enableExemplars: true,
-      metricAttributeAllowlist: ['gen_ai.operation.name', 'gen_ai.system', 'gen_ai.request.model', 'gen_ai.token.type'],
+      metricAttributeAllowlist: ['gen_ai.operation.name', 'gen_ai.provider.name', 'gen_ai.request.model', 'gen_ai.token.type'],
       maxMetricAttributes: 3,
     } as any);
 
@@ -33,8 +33,7 @@ describe('Metrics guardrails: allowlist and cap', () => {
     // Only allowlisted keys remain and capped to 3 keys
     expect(Object.keys(attrs).sort()).toHaveLength(3);
     Object.keys(attrs).forEach(k => {
-      expect(['gen_ai.operation.name', 'gen_ai.system', 'gen_ai.request.model', 'gen_ai.token.type']).toContain(k);
+      expect(['gen_ai.operation.name', 'gen_ai.provider.name', 'gen_ai.request.model', 'gen_ai.token.type']).toContain(k);
     });
   });
 });
-
diff --git a/test/semconv.test.ts b/test/semconv.test.ts
index 11d2b08..0cceb7b 100644
--- a/test/semconv.test.ts
+++ b/test/semconv.test.ts
@@ -1,5 +1,6 @@
 import * as fs from 'fs';
 import * as path from 'path';
+import { parse } from 'yaml';
 import {
   ATTRIBUTE_REGISTRY,
   assertRegisteredAttributes,
@@ -48,4 +49,27 @@ describe('semantic convention registry', () => {
       }
     }
   });
+
+  it('keeps stable GenAI attributes aligned with the upstream registry fixture', () => {
+    const fixturePath = path.join(__dirname, 'fixtures', 'otel', 'gen-ai-registry.yaml');
+    const registry = parse(fs.readFileSync(fixturePath, 'utf8')) as { attributes?: Array<{ key?: string }> };
+    const upstreamKeys = new Set((registry.attributes ?? [])
+      .map(attribute => attribute.key)
+      .filter((key): key is string => typeof key === 'string'));
+
+    expect(upstreamKeys).toContain(ATTR.PROVIDER_NAME);
+    expect(upstreamKeys).not.toContain('gen_ai.system');
+    expect(isRegisteredAttribute('gen_ai.system')).toBe(false);
+
+    const stableSpanKeys = ATTRIBUTE_REGISTRY
+      .filter(spec => spec.source === 'otel-genai')
+      .filter(spec => spec.stability === 'stable')
+      .filter(spec => spec.signal !== 'metric')
+      .map(spec => spec.key)
+      .filter(key => key.startsWith('gen_ai.'))
+      .sort();
+    const missingFromUpstream = stableSpanKeys.filter(key => !upstreamKeys.has(key));
+
+    expect(missingFromUpstream).toEqual([]);
+  });
 });