How to add browser capabilities to a LangChain agent (screenshots, PDFs, page inspection)

How to Add Browser Capabilities to a LangChain Agent LangChain agents can reason, plan, and call tools. What they can't do out of the box is see a web page, take a screenshot, or verify that a UI action actually worked. Here's how to add browser tools to a LangChain agent using the PageBolt API — no Selenium, no Playwright, no browser to manage. Python: adding tools to a LangChain agent import os import requests import base64 from langchain.agents import AgentExecutor , create_openai_tools_agent from langchain_openai import ChatOpenAI from langchain.tools import tool from langchain_core.prompts import ChatPromptTemplate , MessagesPlaceholder PAGEBOLT_API_KEY = os . environ [ " PAGEBOLT_API_KEY " ] BASE_URL = " https://pagebolt.dev/api/v1 " @tool def take_screenshot ( url : str ) -> str : """ Take a screenshot of a web page. Returns a description of what was captured. Use this to visually verify a page, check layouts, or inspect rendered content. Input: a full URL (e.g. https://example.