Merge pull request #2708 from langchain-ai/eugene/wait_for_user_input…

…_improve

wait for user input improvements

docs/docs/how-tos/human_in_the_loop/wait-user-input.ipynb

@@ -6,7 +6,7 @@
    "id": "51466c8d-8ce4-4b3d-be4e-18fdbeda5f53",
    "metadata": {},
    "source": [
-    "# How to wait for user input\n",
+    "# How to wait for user input using `interrupt`\n",
     "\n",
     "!!! tip \"Prerequisites\"\n",
     "\n",
@@ -17,7 +17,7 @@
     "    * [LangGraph Glossary](../../../concepts/low_level)\n",
     "    \n",
     "\n",
-    "Human-in-the-loop (HIL) interactions are crucial for [agentic systems](https://langchain-ai.github.io/langgraph/concepts/agentic_concepts/#human-in-the-loop). Waiting for human input is a common HIL interaction pattern, allowing the agent to ask the user clarifying questions and await input before proceeding. \n",
+    "**Human-in-the-loop (HIL)** interactions are crucial for [agentic systems](https://langchain-ai.github.io/langgraph/concepts/agentic_concepts/#human-in-the-loop). Waiting for human input is a common HIL interaction pattern, allowing the agent to ask the user clarifying questions and await input before proceeding. \n",
     "\n",
     "We can implement this in LangGraph using [`interrupt()`][langgraph.types.interrupt]: `interrupt` allows us to stop graph execution to collect input from a user and continue execution with collected input."
    ]
@@ -98,13 +98,13 @@
    "source": [
     "## Simple Usage\n",
     "\n",
-    "Let's look at very basic usage of this. One intuitive approach is simply to create a node, `human_feedback`, that will get user feedback. This allows us to place our feedback gathering at a specific, chosen point in our graph.\n",
-    " \n",
-    "1) We call `interrupt()` inside our `human_feedback` node.\n",
+    "Let's explore a basic example of using human feedback. A straightforward approach is to create a node, **`human_feedback`**, designed specifically to collect user input. This allows us to gather feedback at a specific, chosen point in our graph.\n",
     "\n",
-    "2) We set up a [checkpointer](https://langchain-ai.github.io/langgraph/concepts/low_level/#checkpointer) to save the state of the graph up until this node.\n",
+    "Steps:\n",
     "\n",
-    "3) We use `Command(resume=...)` to provide the requested value to the human feedback node and resume execution."
+    "1. **Call `interrupt()`** inside the **`human_feedback`** node.  \n",
+    "2. **Set up a [checkpointer](https://langchain-ai.github.io/langgraph/concepts/low_level/#checkpointer)** to save the graph's state up to this node.  \n",
+    "3. **Use `Command(resume=...)`** to provide the requested value to the **`human_feedback`** node and resume execution."
    ]
   },
   {
@@ -281,21 +281,19 @@
   },
   {
    "cell_type": "markdown",
-   "id": "e36f89e5",
+   "id": "b22b9598-7ce4-4d16-b932-bba2bc2803ec",
    "metadata": {},
    "source": [
     "## Agent\n",
     "\n",
-    "In the context of agents, waiting for user feedback is useful to ask clarifying questions.\n",
-    " \n",
-    "To show this, we will build a relatively simple ReAct-style agent that does tool calling. \n",
+    "In the context of [agents](../../../concepts/agentic_concepts), waiting for user feedback is especially useful for asking clarifying questions. To illustrate this, we’ll create a simple [ReAct-style agent](../../../concepts/agentic_concepts#react-implementation) capable of [tool calling](https://python.langchain.com/docs/concepts/tool_calling/). \n",
     "\n",
-    "We will use Anthropic's models and a fake tool (just for demo purposes)."
+    "For this example, we’ll use Anthropic's chat model along with a **mock tool** (purely for demonstration purposes)."
    ]
   },
   {
    "cell_type": "markdown",
-   "id": "b3b8b7e5",
+   "id": "01789855-b769-426d-a329-3cdb29684df8",
    "metadata": {},
    "source": [
     "<div class=\"admonition note\">\n",

docs/docs/how-tos/index.md

@@ -49,7 +49,7 @@ LangGraph makes it easy to manage conversation [memory](../concepts/memory.md) i
 you to involve humans in the decision-making process of your graph. These how-to guides show how to implement human-in-the-loop workflows in your graph.
 
 - [How to edit graph state](human_in_the_loop/edit-graph-state.ipynb)
-- [How to wait for user input](human_in_the_loop/wait-user-input.ipynb)
+- [How to wait for user input using `interrupt`](human_in_the_loop/wait-user-input.ipynb)
 - [How to view and update past graph state](human_in_the_loop/time-travel.ipynb)
 - [How to review tool calls](human_in_the_loop/review-tool-calls.ipynb)
 - [How to add static breakpoints](human_in_the_loop/breakpoints.ipynb): Use for debugging purposes. For [**human-in-the-loop**](../concepts/human_in_the_loop.md) workflows, we recommend the [`interrupt()`](../../../reference/types/#langgraph.types.interrupt) function instead.