Library · Team · LangGraph · support-triage
Support Triage — LangGraph
Classify an inbound message, propose a first reply hold, and flag escalation — human sends. (LangGraph stateful graph with a human checkpoint.)
Id: langgraph/support-triage · Slug: support-triage · Status: Untested · Untested on this machine — recipe reviewed for safety (no secrets, no destructive commands, no auto-spend). Mark tested after you run it locally.
What is this
Code for LangGraph. Classify an inbound message, propose a first reply hold, and flag escalation — human sends. (LangGraph stateful graph with a human checkpoint.)
How this runtime fits
This LangGraph implementation is a graph-style runtime for the parent AI Team. Agent orchestration and multi-agent workflow language fit when nodes split work and gates; it is not automatically identical to every multi-agent system.
Parent AI Team: support-triage · What is an AI Team?
What it does
Classify an inbound message, propose a first reply hold, and flag escalation — human sends. (LangGraph stateful graph with a human checkpoint.)
Who for
Builders working on Support jobs who can run LangGraph themselves.
Need to run
- You will run this locally or on infra you control.
- No production credentials in prompts or committed files.
- Python 3.10+
- LangGraph in a venv
- Local model binder
How to use
- Install LangGraph in a venv (pin versions).
- Wire produce() to your local model client.
- Run the file once with Example in.
- Keep human_gate approval defaulting to False; enable revise only intentionally.
Limitations
- Not a substitute for professional legal, medical, or investment advice.
- Outputs can be wrong; human review required before publish or spend.
- Stage-1 Library items are free recipes — marketplace ready-to-use teams remain separate.
- Do not attach billing cloud LLM nodes without a human budget check.
- No harvesting of personal data beyond what the operator pasted.
Test status
Status: Untested · Untested on this machine — recipe reviewed for safety (no secrets, no destructive commands, no auto-spend). Mark tested after you run it locally.
Files
graph_support_triage.py— LangGraph nodes + interruptREADME.md— Run notes
Full prompt / config / code
Free. No sign-up. The full text is right here. Copy it, or take the file with you.
無料・登録不要。全文はこの下にあります。コピーするか、ファイルで持ち帰れます。
Download .md.md で持ち帰る How to run it動かし方 Fork itフォークする Results & questions結果・質問を書く
# graph_support_triage.py — Support Triage (LangGraph sketch)
# pip install langgraph langchain-core (pin yourself)
# Use a local chat model binder; do not embed secrets.
from typing import TypedDict, Literal
from langgraph.graph import StateGraph, END
SYSTEM = """You are a support triage assistant. Goal: classify and draft a hold reply.
RULES:
- Always emit ALL four OUTPUT sections.
- Human sends the message. You do not send email/chat.
- Never ask for passwords, seed phrases, or full card numbers.
- Never ask for API keys, passwords, tokens, or secrets. Ask only for local-run evidence paths, logs, or redacted screenshots.
- Escalate billing disputes and safety issues.
- Do not invent policy beyond operator notes in the paste.
- Do not claim the desk already tested/ran the seller's team on our machines unless the paste says so.
- Badge/Verified flip requests: Escalate? NO — Verified not flipped from request alone. Urgency Low or Med (not safety).
- Hold-reply: greet seller; explain Untested vs Verified in one sentence; say desk does not flip Verified from a request alone; ask what local-run evidence they can share; do NOT echo their ticket body.
- Label SAMPLE tickets as sample.
- Keep the hold reply short and kind.
OUTPUT:
1) Category + urgency
2) What we know / need
3) Hold-reply draft
4) Escalate? yes/no + why"""
class State(TypedDict):
user_input: str
draft: str
approved: bool
notes: str
def produce(state: State) -> State:
# Pseudo: call your local model with SYSTEM + state["user_input"]
draft = "[MODEL OUTPUT PLACEHOLDER — wire your local LLM here]\n" + state["user_input"][:500]
return {**state, "draft": draft, "notes": "awaiting human"}
def human_gate(state: State) -> State:
# In real use: interrupt / input() / UI approval.
# Default False so nothing auto-publishes.
return {**state, "approved": False}
def route_after_gate(state: State) -> Literal["done", "revise"]:
return "done" if state.get("approved") else "done" # stage-1: always end after gate
g = StateGraph(State)
g.add_node("produce", produce)
g.add_node("human_gate", human_gate)
g.set_entry_point("produce")
g.add_edge("produce", "human_gate")
g.add_conditional_edges("human_gate", route_after_gate, {"done": END, "revise": "produce"})
app = g.compile()
if __name__ == "__main__":
out = app.invoke({"user_input": "PASTE_EXAMPLE_IN", "draft": "", "approved": False, "notes": ""})
print(out)
License as listed in the registry: free-use-at-own-risk. Use is at your own risk. BSV does not run it for you. What is open here
ライセンス(レジストリの記載どおり):free-use-at-own-risk。 利用は自己責任です。BSVが代わりに実行することはありません。何が開いているか
This job is also written for 14 other tools. See all 15 versions side by side.
この仕事は、ほかに 14 のツール向けの版があります。15 版を並べて見る。
Example in
From: user@example.com Subject: charged twice? Body: I see two USDT sends. Order #1842. Need help.
Example out
Category: billing / duplicate payment | urgency: high Know: order #1842, two USDT sends claimed Need: txids, amounts, times Hold-reply: Thanks — please reply with both txids… Escalate: yes — payment mismatch
Model / runtime notes
Graph includes an explicit human checkpoint. Stage-1 ends after gate (no infinite revise loop).
Canonical Team
Parent: support-triage
· implementation_id: langgraph/support-triage
GitHub source
teams/support-triage/langgraph (path in the BSV team registry repository) · commit eb87e8e049fdf9908e438305ff827c7b617505b5
· license: free-use-at-own-risk
Structural check: PASS · env: structural (structural only — does not set Verified)
Related Library items
Related marketplace Team pages
Soft thematic links only — not identity merges. Marketplace Teams ≠ Library AI Team records.
- First Reply Hold (marketplace Team page — separate entity)
- Hold Reply Inbox (marketplace Team page — separate entity)
Run this task locally · LangGraph team runner
The BSV team runner runs this task on a local model (LM Studio or Ollama), checks the required sections and saves only after your approval. Paste the team prompt from the full-text page into prompts/support-triage.txt.
BSVのチームランナーで、この仕事をローカルモデル(LM StudioまたはOllama)で動かせます。必要な項目を確認し、あなたが承認したときだけ保存します。全文ページのプロンプトを prompts/support-triage.txt に貼り付けて使います。
python runner.py --task support-triage --input notes.md
Not runtime tested by BSV.
BSVでは実行検証をしていません。