How do I check for politically exposed persons (PEPs) in an AI agent?

Steps

1. Install langchain-strale and a chat-model package.
2. Create the toolkit with your Strale API key.
3. Bind pep-check to your model.
4. Ask it to check a name and country, then run the tool call the model returns.

The solution

# pip install langchain-strale langchain-openai
from langchain_strale import StraleToolkit
from langchain_openai import ChatOpenAI

toolkit = StraleToolkit(api_key="sk_live_YOUR_KEY")
tools = [t for t in toolkit.get_tools() if t.name == "pep-check"]

llm = ChatOpenAI(model="gpt-4o").bind_tools(tools)
result = llm.invoke("Check if 'John Smith' from the United Kingdom is a PEP")

# The model picks the tool and its arguments; your code runs the call.
for call in result.tool_calls:
    tool = next(t for t in tools if t.name == call["name"])
    print(tool.invoke(call["args"]))

How it works

A politically exposed person is someone who holds or has held a prominent public position, such as a politician, senior official, judge or military leader. The database also lists their relatives and close associates.

The answer has is_pep, match_count and a matches list with each person's name, positions held and the countries involved, plus lists_queried, which names the source.

There is no numeric confidence field, so narrowing the query is your main lever for precision: pass country and birth_date where you have them. Coverage per country is not verified on each call.

A match means a name appears on a list that was searched. It is not a decision about the person or company: a person should review it.

bind_tools only lets the model propose a call. To have the model read the result and answer in words, put the same tools in one of LangChain's agent loops.

Tools in this guide