AI Outreach Agent

This project demonstrates how to use Composio to create an 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

1. Installation

   install the required dependencies

   pip install composio-core
   
2. Connecting to tools and models

   connect to required tools

   composio add gmail
   composio add hubspot
   
   export OPENAI_API_KEY="<your-openai-api-key>"
   
3. Importing the required libraries

   import required libraries

   from composio_llamaindex import ComposioToolSet, App, Action
   from llama_index.core.agent import FunctionCallingAgentWorker
   from llama_index.core.llms import ChatMessage
   from llama_index.llms.openai import OpenAI
   from dotenv import load_dotenv
   
   load_dotenv()
   
4. Initializing the Tools and the LLM

   initialize toolset and llm

   toolset = ComposioToolSet(api_key="YOUR-API-KEY")
   tools = toolset.get_tools(actions=[Action.HUBSPOT_LIST_CONTACTS_PAGE, Action.GMAIL_CREATE_EMAIL_DRAFT])
   
   llm = OpenAI(model="gpt-4o")
   
5. Setting up Function Calling Worker

   setup function calling worker

   prefix_messages = [
       ChatMessage(
           role="system",
           content=(
               f"""
               "You are a Lead Outreach Agent that is has access to the CRM through HubSpot."
               "and is an expert writer. Your job is to first research some info about the lead "
               "given to you and then draft a perfect ideal email for whatever input task is given to you. "
               """
           ),
       )
   ]
   
   agent = FunctionCallingAgentWorker(
       tools=tools,
       llm=llm,
       prefix_messages=prefix_messages,
       max_function_calls=10,
       allow_parallel_tool_calls=False,
       verbose=True,
   ).as_agent()
   
6. Executing the Agent

   execute the agent

   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."
   response = agent.chat(user_input)
   
7. Final Code

   final code

   from composio_llamaindex import ComposioToolSet, App, Action
   from llama_index.core.agent import FunctionCallingAgentWorker
   from llama_index.core.llms import ChatMessage
   from llama_index.llms.openai import OpenAI
   from dotenv import load_dotenv
   
   load_dotenv()
   toolset = ComposioToolSet(api_key="")
   tools = toolset.get_tools(actions=[Action.HUBSPOT_LIST_CONTACTS_PAGE, Action.GMAIL_CREATE_EMAIL_DRAFT])
   
   llm = OpenAI(model="gpt-4o")
   
   prefix_messages = [
       ChatMessage(
           role="system",
           content=(
               f"""
               "You are a Lead Outreach Agent that is has access to the CRM through HubSpot."
               "and is an expert writer. Your job is to first research some info about the lead "
               "given to you and then draft a perfect ideal email for whatever input task is given to you. "
               """
           ),
       )
   ]
   
   agent = FunctionCallingAgentWorker(
       tools=tools,
       llm=llm,
       prefix_messages=prefix_messages,
       max_function_calls=10,
       allow_parallel_tool_calls=False,
       verbose=True,
   ).as_agent()
   
   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."
   response = agent.chat(user_input)
   

Javascript

1. Installation

   install the required dependencies

   npm install composio-core langchain @langchain/openai
   
2. Connecting to tools and models

   connect to tools

   composio add gmail
   composio add hubspot
   
   export OPENAI_API_KEY="<your-openai-api-key>"
   export COMPOSIO_API_KEY="<your-composio-api-key>"
   
3. Importing the required libraries

   import the required libraries

   import { ChatOpenAI } from "@langchain/openai";
   import { createOpenAIFunctionsAgent, AgentExecutor } from "langchain/agents";
   import { pull } from "langchain/hub";
   import dotenv from 'dotenv';
   import { LangchainToolSet } from "composio-core";
   
   dotenv.config();
   
4. Initializing the Tools and the LLM

   initialize toolset and llm

   const toolset = new LangchainToolSet({
     apiKey: process.env.COMPOSIO_API_KEY,
   });
   
   const tools = await toolset.getTools({actions: ["HUBSPOT_LIST_CONTACTS_PAGE", "GMAIL_CREATE_EMAIL_DRAFT"]});
   
   const llm = new ChatOpenAI({
       model: "gpt-4-turbo",
       apiKey: process.env.OPENAI_API_KEY,
   });
   
5. Setting up Agent

   setup agent

   const prompt = await pull("hwchase17/openai-functions-agent");
   
   const additional = `
       "You are a Lead Outreach Agent that is has access to the CRM through HubSpot."
       "and is an expert writer. Your job is to first research some info about the lead "
       "given to you and then draft a perfect ideal email template for whatever input task is given to you. "
       `;
   const agent = await createOpenAIFunctionsAgent({
       llm,
       tools,
       prompt,
   });
   
   const agentExecutor = new AgentExecutor({
       agent,
       tools,
       verbose: false, 
   });
   
   
6. Executing the Agent

   execute the agent

   const result = await agentExecutor.invoke({
       input: `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.`
   });
   console.log('🎉Output from agent: ', result.output);
   
7. Final Code

   final code

   import { ChatOpenAI } from "@langchain/openai";
   import { createOpenAIFunctionsAgent, AgentExecutor } from "langchain/agents";
   import { pull } from "langchain/hub";
   import dotenv from 'dotenv';
   import { LangchainToolSet } from "composio-core";
   
   dotenv.config();
   
   const llm = new ChatOpenAI({
       model: "gpt-4-turbo",
       apiKey: process.env.OPENAI_API_KEY,
   });
   
   const toolset = new LangchainToolSet({
       apiKey: process.env.COMPOSIO_API_KEY,
   });
   
   const tools = await toolset.getTools({actions: ["HUBSPOT_LIST_CONTACTS_PAGE", "GMAIL_CREATE_EMAIL_DRAFT"]});
   
   const prompt = await pull("hwchase17/openai-functions-agent");
   
   const additional = `
       "You are a Lead Outreach Agent that is has access to the CRM through HubSpot."
       "and is an expert writer. Your job is to first research some info about the lead "
       "given to you and then draft a perfect ideal email template for whatever input task is given to you. "
       `;
   
   
   const agent = await createOpenAIFunctionsAgent({
       llm,
       tools,
       prompt,
   });
   
   const agentExecutor = new AgentExecutor({
       agent,
       tools,
       verbose: false, 
   });
   const result = await agentExecutor.invoke({
       input: `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.`
   });
   console.log('🎉Output from agent: ', result.output);