diff --git a/docs/index.md b/docs/index.md
index d31eb01..a6cfda5 100644
--- a/docs/index.md
+++ b/docs/index.md
@@ -15,6 +15,7 @@ We model the LLM workflow as a **Nested Flow**:
 - A Flow can be treated as a Node for **Nested Flows**.
 - Both Nodes and Flows can be **Batched** for data-intensive tasks.
 - Nodes and Flows can be **Async** for user inputs.
+- **Async** Nodes and Flows can be executed in **Parallel**.
 
 <div align="center">
   <img src="https://github.com/zachary62/miniLLMFlow/blob/main/assets/minillmflow.jpg?raw=true" width="400"/>
@@ -27,6 +28,7 @@ We model the LLM workflow as a **Nested Flow**:
 - [Communication](./communication.md)
 - [Batch](./batch.md)
 - [Async](./async.md)
+- [Parallel](./parallel.md)
 
 ## Preparation
 
diff --git a/docs/parallel.md b/docs/parallel.md
new file mode 100644
index 0000000..b1b8d3a
--- /dev/null
+++ b/docs/parallel.md
@@ -0,0 +1,57 @@
+---
+layout: default
+title: "Parallel"
+parent: "Core Abstraction"
+nav_order: 6
+---
+
+# Parallel
+
+**Parallel** Nodes and Flows let you run multiple tasks **concurrently**—for example, summarizing multiple texts at once. Unlike a regular **BatchNode**, which processes items sequentially, **AsyncParallelBatchNode** and **AsyncParallelBatchFlow** can fire off tasks in parallel. This can improve performance by overlapping I/O and compute. 
+
+## AsyncParallelBatchNode
+
+Like **AsyncBatchNode**, but uses `prep_async()`, `exec_async()`, and `post_async()` in **parallel**:
+
+```python
+class ParallelSummaries(AsyncParallelBatchNode):
+    async def prep_async(self, shared):
+        # e.g., multiple texts
+        return shared["texts"]
+
+    async def exec_async(self, text):
+        prompt = f"Summarize: {text}"
+        return await call_llm_async(prompt)
+
+    async def post_async(self, shared, prep_res, exec_res_list):
+        shared["summary"] = "\n\n".join(exec_res_list)
+        return "default"
+
+node = ParallelSummaries()
+flow = AsyncFlow(start=node)
+```
+
+## AsyncParallelBatchFlow
+
+Parallel version of **BatchFlow**. Each iteration of the sub-flow runs **concurrently** using different parameters:
+
+```python
+class SummarizeMultipleFiles(AsyncParallelBatchFlow):
+    async def prep_async(self, shared):
+        return [{"filename": f} for f in shared["files"]]
+
+sub_flow = AsyncFlow(start=LoadAndSummarizeFile())
+parallel_flow = SummarizeMultipleFiles(start=sub_flow)
+await parallel_flow.run_async(shared)
+```
+
+## Best Practices
+
+- **Ensure Tasks Are Independent**  
+  If each item depends on the output of a previous item, **don’t** parallelize. Parallelizing dependent tasks can lead to inconsistencies or race conditions.
+
+- **Beware Rate Limits**  
+  Parallel calls can **quickly** trigger rate limits on LLM services. You may need a **throttling** mechanism (e.g., semaphores or sleep intervals) to avoid hitting vendor limits.
+
+- **Consider Single-Node Batch APIs**  
+  Some LLMs offer a **batch inference** API where you can send multiple prompts in a single call. This is more complex to implement but can be more efficient than launching many parallel requests. Conceptually, it can look similar to an **AsyncBatchNode** or **BatchNode**, but the underlying call bundles multiple items into **one** request.
\ No newline at end of file