.

Author: penguine-ip

docs/content/integrations/frameworks/anthropic.mdx

@@ -4,7 +4,7 @@ title: Anthropic
 sidebar_label: Anthropic
 ---
 
-<IntegrationTagsDisplayer manual={true} cicdEvals={true} traceability={true} />
+<IntegrationTagsDisplayer native={true} cicdEvals={true} traceability={true} />
 
 [Anthropic](https://docs.anthropic.com/) provides the Messages API for Claude, including tool use and streaming.
 

docs/content/integrations/frameworks/crewai.mdx

@@ -4,7 +4,7 @@ title: CrewAI
 sidebar_label: CrewAI
 ---
 
-<IntegrationTagsDisplayer manual={true} cicdEvals={true} traceability={true} />
+<IntegrationTagsDisplayer native={true} cicdEvals={true} traceability={true} />
 
 [CrewAI](https://www.crewai.com/) is a Python framework for orchestrating role-playing autonomous agents that collaborate on multi-step tasks.
 

docs/content/integrations/frameworks/langchain.mdx

@@ -4,7 +4,7 @@ title: LangChain
 sidebar_label: LangChain
 ---
 
-<IntegrationTagsDisplayer manual={true} cicdEvals={true} traceability={true} />
+<IntegrationTagsDisplayer native={true} cicdEvals={true} traceability={true} />
 
 [LangChain](https://www.langchain.com/) is an open-source framework for building LLM applications with models, prompts, tools, retrievers, chains, and agents.
 
@@ -62,7 +62,7 @@ The `deepeval` integration traces LangChain runs through a `CallbackHandler` tha
 
 `deepeval`'s LangChain integration enables you to:
 
-- **Trace any LangChain run manually** — pass `CallbackHandler(...)` through `config={"callbacks": [...]}`.
+- **Trace any LangChain run** — pass `CallbackHandler(...)` through `config={"callbacks": [...]}` per call.
 - **Evaluate traces or individual components** with `deepeval` metrics.
 - **Run evals from scripts or CI/CD** — same callback, different surfaces.
 - **Customize trace and span data** through callback kwargs, LangChain metadata, and `deepeval`'s tool decorator.
@@ -79,7 +79,7 @@ The `deepeval` integration traces LangChain runs through a `CallbackHandler` tha
 pip install -U deepeval langchain langchain-openai
 ```
 
-Unlike OTel integrations, LangChain is manually instrumented. You decide which runs are traced by passing `CallbackHandler(...)` into LangChain's runtime config.
+LangChain is instrumented per-call: you decide which runs are traced by passing `CallbackHandler(...)` into LangChain's runtime config.
 
 </Step>
 
@@ -224,7 +224,7 @@ retriever = vector_store.as_retriever().with_config(
 
 ## Customizing trace and span data
 
-LangChain is manually instrumented, so customization happens at the callback or component config boundary.
+LangChain is instrumented per-call through callbacks, so customization happens at the callback or component config boundary.
 
 - Use `CallbackHandler(...)` kwargs for trace-level defaults like `name`, `tags`, `metadata`, `thread_id`, and `user_id`.
 - Use LangChain metadata for component-level fields on LLM and retriever spans.

docs/content/integrations/frameworks/langgraph.mdx

@@ -4,7 +4,7 @@ title: LangGraph
 sidebar_label: LangGraph
 ---
 
-<IntegrationTagsDisplayer manual={true} cicdEvals={true} traceability={true} />
+<IntegrationTagsDisplayer native={true} cicdEvals={true} traceability={true} />
 
 [LangGraph](https://www.langchain.com/langgraph) is a framework for building stateful, graph-based agent workflows on top of LangChain.
 
@@ -62,7 +62,7 @@ The `deepeval` integration traces LangGraph runs through LangChain's `CallbackHa
 
 `deepeval`'s LangGraph integration enables you to:
 
-- **Trace any LangGraph run manually** — pass `CallbackHandler(...)` through `config={"callbacks": [...]}`.
+- **Trace any LangGraph run** — pass `CallbackHandler(...)` through `config={"callbacks": [...]}` per call.
 - **Evaluate traces or model / agent components** with `deepeval` metrics.
 - **Run evals from scripts or CI/CD** — same callback, different surfaces.
 - **Customize trace and span data** through callback kwargs and LangChain metadata.
@@ -79,7 +79,7 @@ The `deepeval` integration traces LangGraph runs through LangChain's `CallbackHa
 pip install -U deepeval langgraph langchain-openai
 ```
 
-LangGraph uses LangChain's callback system, so the `deepeval` integration is manual. You decide which graph runs are traced by passing `CallbackHandler(...)` into the graph config.
+LangGraph uses LangChain's callback system, so the `deepeval` integration is per-call. You decide which graph runs are traced by passing `CallbackHandler(...)` into the graph config.
 
 </Step>
 
@@ -219,7 +219,7 @@ For deterministic tool calls, use tool spans for traceability, inputs, outputs,
 
 ## Customizing trace and span data
 
-LangGraph is manually instrumented through LangChain callbacks, so customization happens at the callback or component config boundary.
+LangGraph is instrumented per-call through LangChain callbacks, so customization happens at the callback or component config boundary.
 
 - Use `CallbackHandler(...)` kwargs for trace-level defaults like `name`, `tags`, `metadata`, `thread_id`, and `user_id`.
 - Use LangChain metadata for component-level fields on LLM and retriever spans.

docs/content/integrations/frameworks/llamaindex.mdx

@@ -4,7 +4,7 @@ title: LlamaIndex
 sidebar_label: LlamaIndex
 ---
 
-<IntegrationTagsDisplayer manual={true} cicdEvals={true} traceability={true} />
+<IntegrationTagsDisplayer native={true} cicdEvals={true} traceability={true} />
 
 [LlamaIndex](https://www.llamaindex.ai/) is an orchestration framework for data ingestion, indexing, and retrieval-augmented generation, with first-class agent and workflow primitives.
 

docs/content/integrations/frameworks/openai-agents.mdx

@@ -4,7 +4,7 @@ title: OpenAI Agents
 sidebar_label: OpenAI Agents
 ---
 
-<IntegrationTagsDisplayer manual={true} cicdEvals={true} traceability={true} />
+<IntegrationTagsDisplayer native={true} cicdEvals={true} traceability={true} />
 
 [OpenAI Agents](https://openai.github.io/openai-agents-python/) is OpenAI's Python SDK for building agents that reason, call tools, and hand off to other agents.
 

docs/content/integrations/frameworks/openai.mdx

@@ -4,7 +4,7 @@ title: OpenAI
 sidebar_label: OpenAI
 ---
 
-<IntegrationTagsDisplayer manual={true} cicdEvals={true} traceability={true} />
+<IntegrationTagsDisplayer native={true} cicdEvals={true} traceability={true} />
 
 [OpenAI](https://platform.openai.com/docs/) provides chat completions and responses APIs for building LLM applications.
 

docs/src/components/IntegrationTagsDisplayer/IntegrationTagsDisplayer.module.scss

@@ -27,7 +27,7 @@
     &.otel {
       --pill-hue: oklch(0.6 0.14 220);
     }
-    &.manual {
+    &.native {
       --pill-hue: oklch(0.58 0.15 155);
     }
 

docs/src/components/IntegrationTagsDisplayer/index.tsx

@@ -3,14 +3,14 @@ import styles from "./IntegrationTagsDisplayer.module.scss";
 
 interface IntegrationTagsDisplayerProps {
   otel?: boolean;
-  manual?: boolean;
+  native?: boolean;
   cicdEvals?: boolean;
   traceability?: boolean;
 }
 
 const IntegrationTagsDisplayer = ({
   otel = false,
-  manual = false,
+  native = false,
   cicdEvals = false,
   traceability = false,
 }: IntegrationTagsDisplayerProps) => {
@@ -21,9 +21,9 @@ const IntegrationTagsDisplayer = ({
           OTel Instrumentation
         </div>
       )}
-      {manual && (
-        <div className={`${styles.pill} ${styles.manual}`}>
-          Manual instrumentation
+      {native && (
+        <div className={`${styles.pill} ${styles.native}`}>
+          Native Instrumentation
         </div>
       )}
       {cicdEvals && (