AI Outreach Agent

Overview

This agent automates lead outreach by crafting personalized emails tailored to each lead and sending them instantly. Designed to optimize engagement and streamline your sales process, the AI Outreach Agent helps businesses save time and improve the effectiveness of their email campaigns.

Getting Started

Python

Javascript

Installation

install the required dependencies

$ pip install composio-core

Connecting to tools and models

connect to required tools

$ composio add gmail
> composio add hubspot
> 
> export OPENAI_API_KEY="<your-openai-api-key>"

Importing the required libraries

import required libraries

1 from composio_llamaindex import ComposioToolSet, App, Action
2 from llama_index.core.agent import FunctionCallingAgentWorker
3 from llama_index.core.llms import ChatMessage
4 from llama_index.llms.openai import OpenAI
5 from dotenv import load_dotenv
6 
7 load_dotenv()

Initializing the Tools and the LLM

initialize toolset and llm

1 toolset = ComposioToolSet(api_key="")
2 tools = toolset.get_tools(apps=[App.HUBSPOT, App.GMAIL])
3 
4 llm = OpenAI(model="gpt-4o")

Setting up Function Calling Worker

setup function calling worker

1 prefix_messages = [
2     ChatMessage(
3         role="system",
4         content=(
5             f"""
6             "You are a Lead Outreach Agent that is has access to the CRM through HubSpot."
7             "and is an expert writer. Your job is to first research some info about the lead "
8             "given to you and then draft a perfect ideal email for whatever input task is given to you. "
9             """
10         ),
11     )
12 ]
13 
14 agent = FunctionCallingAgentWorker(
15     tools=tools,
16     llm=llm,
17     prefix_messages=prefix_messages,
18     max_function_calls=10,
19     allow_parallel_tool_calls=False,
20     verbose=True,
21 ).as_agent()

Executing the Agent

execute the agent

1 user_input = f"Draft an email for each lead in my Hubspot contacts page introducing yourself and asking them if they're interested in integrating AI Agents in their workflow."
2 response = agent.chat(user_input)

Final Code

final code

1 from composio_llamaindex import ComposioToolSet, App, Action
2 from llama_index.core.agent import FunctionCallingAgentWorker
3 from llama_index.core.llms import ChatMessage
4 from llama_index.llms.openai import OpenAI
5 from dotenv import load_dotenv
6 
7 load_dotenv()
8 toolset = ComposioToolSet(api_key="")
9 tools = toolset.get_tools(apps=[App.PEOPLEDATALABS, App.GOOGLESHEETS])
10 
11 llm = OpenAI(model="gpt-4o")
12 
13 prefix_messages = [
14     ChatMessage(
15         role="system",
16         content=(
17             f"""
18             "You are a Lead Outreach Agent that is has access to the CRM through HubSpot."
19             "and is an expert writer. Your job is to first research some info about the lead "
20             "given to you and then draft a perfect ideal email for whatever input task is given to you. "
21             """
22         ),
23     )
24 ]
25 
26 agent = FunctionCallingAgentWorker(
27     tools=tools,
28     llm=llm,
29     prefix_messages=prefix_messages,
30     max_function_calls=10,
31     allow_parallel_tool_calls=False,
32     verbose=True,
33 ).as_agent()
34 
35 user_input = f"Draft an email for each lead in my Hubspot contacts page introducing yourself and asking them if they're interested in integrating AI Agents in their workflow."
36 response = agent.chat(user_input)