Your first graph: LangGraph lesson 1 - AI Tester Blueprint

01Real-world example

Illustration: A CI step receives a test-run record and adds one field, such as a build ID, before passing it on. — A CI step receives a test-run record and adds one field, such as a build ID, before passing it on.

02The graph

Your first graph as a graph — greet is a node. It reads the state and hands back one new key: greeting.

03How the code does it

class State(TypedDict) declares the keys every node can read: tester and greeting.
greet() returns only {"greeting": ...}. LangGraph merges that into the state; it never replaces the whole dict.
add_edge(START, "greet") and add_edge("greet", END) make the only path. compile() validates it and returns a runnable app.
app.get_graph().draw_mermaid() prints the graph you built, so you can check the wiring before you add logic.

Key points

State is a plain dict shared by every node
A node returns only what it changed
Build it, compile() it, invoke() it

04Run it

terminal

cd chapter_18_LangGraph/src/chapters
python 001_Hello_Graph.py

output

Hello Pramod, your first graph ran.

DDrills for lesson 1

Work in chapter_18_LangGraph/src/chapters. Change one thing, run it, and compare with the expected result.

Print the graph and read it
Run the script and paste the Mermaid text it prints into mermaid.live.

Expected result
Three nodes in a line: __start__ to greet to __end__.
Add a key to the state
Add role: str to State, pass {"tester": "Pramod", "role": "SDET"} to invoke, and use it in the greeting.

Hint
Only State, the invoke input and the f-string in greet change.

Expected result
Hello Pramod (SDET), your first graph ran. (or however you format it).
Return the whole state
Make greet return every key, not just greeting. Does the result change?

Expected result
No. Returning unchanged keys is allowed, but it hides what the node actually changed. Return only what changed.

SThe full script

The exact file from the course repo, plus the output it printed when this page was written.

001_Hello_Graph.py

"""001 - The smallest possible graph: one node between START and END.

State is the backpack. A node is a plain function: it receives the backpack
and returns only the keys it wants to change. LangGraph merges them in.
"""
from typing import TypedDict

from langgraph.graph import END, START, StateGraph


class State(TypedDict):
    tester: str
    greeting: str


def greet(state: State) -> dict:
    return {"greeting": f"Hello {state['tester']}, your first graph ran."}


builder = StateGraph(State)
builder.add_node("greet", greet)
builder.add_edge(START, "greet")
builder.add_edge("greet", END)

app = builder.compile()

if __name__ == "__main__":
    result = app.invoke({"tester": "Pramod"})
    print(result["greeting"])
    print("\nFinal state:", result)
    print("\nThe graph as Mermaid (paste into mermaid.live):")
    print(app.get_graph().draw_mermaid())

Expected output

output

Hello Pramod, your first graph ran.