Lead Research — LangGraph

Build a respectful lead brief from public facts you paste — no scraping secrets, no spam scripts. (LangGraph stateful graph with a human checkpoint.)

Id: langgraph/lead-research · Slug: lead-research · 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. Build a respectful lead brief from public facts you paste — no scraping secrets, no spam scripts. (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: lead-research · What is an AI Team?

What it does

Build a respectful lead brief from public facts you paste — no scraping secrets, no spam scripts. (LangGraph stateful graph with a human checkpoint.)

Who for

Builders working on Sales 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_lead_research.py — LangGraph nodes + interrupt
README.md — Run notes

Full prompt / config / code

# graph_lead_research.py — Lead Research (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 respectful lead-research desk. Goal: brief from public facts the user pasted.

RULES:
- No scraping instructions that bypass auth or harvest personal emails at scale.
- No spam sequences. Suggest one human-sent outreach angle max.
- Separate public fact vs guess.
- Do not store or request secrets.

OUTPUT:
1) Company/person snapshot
2) Relevant public facts
3) Fit hypothesis (low confidence unless evidenced)
4) One human outreach angle
5) Do-not-do list"""

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)

Example in

Public paste:
- Acme Tools — indie SaaS for shop floors
- Blog post 2026-08: adopting local LLMs for SOP drafts
- Careers: 1 openings (generalist)
Goal: see if Build Library is relevant

Example out

Snapshot: small SaaS, local-LLM interest
Facts: blog theme matches Library; team size unclear
Fit: medium hypothesis — content-led, not hard sell
Outreach angle: share one Library recipe that matches SOP drafting
Do-not: scrape employee emails; no auto-DM sequences

Model / runtime notes

Graph includes an explicit human checkpoint. Stage-1 ends after gate (no infinite revise loop).

Canonical Team

Parent: lead-research · implementation_id: langgraph/lead-research

GitHub source

teams/lead-research/langgraph · 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.

Cite Omit Brief (marketplace Team page — separate entity)
Buyer QA Pass (marketplace Team page — separate entity)