{ "cells": [ { "cell_type": "markdown", "metadata": {}, "source": [ "\n", " \n", " \n", " \n", " \n", "
\n", " \n", " \n", "

Are you ready for action??

\n", " Have you completed all the setup steps in the setup folder?
\n", " Have you read the README? Many common questions are answered here!
\n", " Have you checked out the guides in the guides folder?
\n", " Well in that case, you're ready!!\n", " \n", "
" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "\n", " \n", " \n", " \n", " \n", "
\n", " \n", " \n", "

This code is a live resource - keep an eye out for my updates

\n", " I push updates regularly. As people ask questions or have problems, I add more examples and improve explanations. As a result, the code below might not be identical to the videos, as I've added more steps and better comments. Consider this like an interactive book that accompanies the lectures.

\n", " I try to send emails regularly with important updates related to the course. You can find this in the 'Announcements' section of Udemy in the left sidebar. You can also choose to receive my emails via your Notification Settings in Udemy. I'm respectful of your inbox and always try to add value with my emails!\n", " \n", "
" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "### And please do remember to contact me if I can help\n", "\n", "And I love to connect: https://www.linkedin.com/in/eddonner/\n", "\n", "\n", "### New to Notebooks like this one? Head over to the guides folder!\n", "\n", "Just to check you've already added the Python and Jupyter extensions to Cursor, if not already installed:\n", "- Open extensions (View >> extensions)\n", "- Search for python, and when the results show, click on the ms-python one, and Install it if not already installed\n", "- Search for jupyter, and when the results show, click on the Microsoft one, and Install it if not already installed \n", "Then View >> Explorer to bring back the File Explorer.\n", "\n", "And then:\n", "1. Click where it says \"Select Kernel\" near the top right, and select the option called `.venv (Python 3.12.9)` or similar, which should be the first choice or the most prominent choice. You may need to choose \"Python Environments\" first.\n", "2. Click in each \"cell\" below, starting with the cell immediately below this text, and press Shift+Enter to run\n", "3. Enjoy!\n", "\n", "After you click \"Select Kernel\", if there is no option like `.venv (Python 3.12.9)` then please do the following: \n", "1. On Mac: From the Cursor menu, choose Settings >> VS Code Settings (NOTE: be sure to select `VSCode Settings` not `Cursor Settings`); \n", "On Windows PC: From the File menu, choose Preferences >> VS Code Settings(NOTE: be sure to select `VSCode Settings` not `Cursor Settings`) \n", "2. In the Settings search bar, type \"venv\" \n", "3. In the field \"Path to folder with a list of Virtual Environments\" put the path to the project root, like C:\\Users\\username\\projects\\agents (on a Windows PC) or /Users/username/projects/agents (on Mac or Linux). \n", "And then try again.\n", "\n", "Having problems with missing Python versions in that list? Have you ever used Anaconda before? It might be interferring. Quit Cursor, bring up a new command line, and make sure that your Anaconda environment is deactivated: \n", "`conda deactivate` \n", "And if you still have any problems with conda and python versions, it's possible that you will need to run this too: \n", "`conda config --set auto_activate_base false` \n", "and then from within the Agents directory, you should be able to run `uv python list` and see the Python 3.12 version." ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [ { "ename": "", "evalue": "", "output_type": "error", "traceback": [ "\u001b[1;31mThe kernel failed to start as the Python Environment 'agents (Python -1.-1.-1)' is no longer available. Consider selecting another kernel or refreshing the list of Python Environments." ] } ], "source": [ "# First let's do an import. If you get an Import Error, double check that your Kernel is correct..\n", "\n", "from dotenv import load_dotenv\n", "\n" ] }, { "cell_type": "code", "execution_count": 3, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "True" ] }, "execution_count": 3, "metadata": {}, "output_type": "execute_result" } ], "source": [ "# Next it's time to load the API keys into environment variables\n", "# If this returns false, see the next cell!\n", "\n", "load_dotenv(override=True)" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "### Wait, did that just output `False`??\n", "\n", "If so, the most common reason is that you didn't save your `.env` file after adding the key! Be sure to have saved.\n", "\n", "Also, make sure the `.env` file is named precisely `.env` and is in the project root directory (`agents`)\n", "\n", "By the way, your `.env` file should have a stop symbol next to it in Cursor on the left, and that's actually a good thing: that's Cursor saying to you, \"hey, I realize this is a file filled with secret information, and I'm not going to send it to an external AI to suggest changes, because your keys should not be shown to anyone else.\"" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "\n", " \n", " \n", " \n", " \n", "
\n", " \n", " \n", "

Final reminders

\n", " 1. If you're not confident about Environment Variables or Web Endpoints / APIs, please read Topics 3 and 5 in this technical foundations guide.
\n", " 2. If you want to use AIs other than OpenAI, like Gemini, DeepSeek or Ollama (free), please see the first section in this AI APIs guide.
\n", " 3. If you ever get a Name Error in Python, you can always fix it immediately; see the last section of this Python Foundations guide and follow both tutorials and exercises.
\n", " \n", "
" ] }, { "cell_type": "code", "execution_count": 4, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "OpenAI API Key exists and begins sk-proj-\n" ] } ], "source": [ "# Check the key - if you're not using OpenAI, check whichever key you're using! Ollama doesn't need a key.\n", "\n", "import os\n", "openai_api_key = os.getenv('OPENAI_API_KEY')\n", "\n", "if openai_api_key:\n", " print(f\"OpenAI API Key exists and begins {openai_api_key[:8]}\")\n", "else:\n", " print(\"OpenAI API Key not set - please head to the troubleshooting guide in the setup folder\")\n", " \n" ] }, { "cell_type": "code", "execution_count": 5, "metadata": {}, "outputs": [], "source": [ "# And now - the all important import statement\n", "# If you get an import error - head over to troubleshooting in the Setup folder\n", "# Even for other LLM providers like Gemini, you still use this OpenAI import - see Guide 9 for why\n", "\n", "from openai import OpenAI" ] }, { "cell_type": "code", "execution_count": 6, "metadata": {}, "outputs": [], "source": [ "# And now we'll create an instance of the OpenAI class\n", "# If you're not sure what it means to create an instance of a class - head over to the guides folder (guide 6)!\n", "# If you get a NameError - head over to the guides folder (guide 6)to learn about NameErrors - always instantly fixable\n", "# If you're not using OpenAI, you just need to slightly modify this - precise instructions are in the AI APIs guide (guide 9)\n", "\n", "openai = OpenAI()" ] }, { "cell_type": "code", "execution_count": 7, "metadata": {}, "outputs": [], "source": [ "# Create a list of messages in the familiar OpenAI format\n", "\n", "messages = [{\"role\": \"user\", \"content\": \"What is 2+2?\"}]\n", "message = [{\"role\": \"user\", \"content\": \"What is 1+2?\"}]" ] }, { "cell_type": "code", "execution_count": 9, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "1 + 2 equals 3.\n" ] } ], "source": [ "# And now call it! Any problems, head to the troubleshooting guide\n", "# This uses GPT 4.1 nano, the incredibly cheap model\n", "# The APIs guide (guide 9) has exact instructions for using even cheaper or free alternatives to OpenAI\n", "# If you get a NameError, head to the guides folder (guide 6) to learn about NameErrors - always instantly fixable\n", "\n", "response = openai.chat.completions.create(\n", " model=\"gpt-4.1-nano\",\n", " messages=message\n", " \n", ")\n", "\n", "print(response.choices[0].message.content)\n" ] }, { "cell_type": "code", "execution_count": 10, "metadata": {}, "outputs": [], "source": [ "# And now - let's ask for a question:\n", "\n", "question = \"Please propose a hard, challenging question to assess someone's IQ. Respond only with the question.\"\n", "messages = [{\"role\": \"user\", \"content\": question}]\n" ] }, { "cell_type": "code", "execution_count": 11, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "If five machines take five minutes to make five widgets, how long would 100 machines take to make 100 widgets?\n" ] } ], "source": [ "# ask it - this uses GPT 4.1 mini, still cheap but more powerful than nano\n", "\n", "response = openai.chat.completions.create(\n", " model=\"gpt-4.1-mini\",\n", " messages=messages\n", ")\n", "\n", "question = response.choices[0].message.content\n", "\n", "print(question)\n" ] }, { "cell_type": "code", "execution_count": 12, "metadata": {}, "outputs": [], "source": [ "# form a new messages list\n", "messages = [{\"role\": \"user\", \"content\": question}]\n" ] }, { "cell_type": "code", "execution_count": 13, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Let's analyze the problem step-by-step:\n", "\n", "**Given:**\n", "- 5 machines take 5 minutes to make 5 widgets.\n", "\n", "**Step 1: Find the rate per machine**\n", "\n", "If 5 machines make 5 widgets in 5 minutes, then:\n", "\n", "- Each machine makes 1 widget in 5 minutes (because 5 widgets / 5 machines = 1 widget per machine in 5 minutes).\n", "\n", "**Step 2: Determine time for 1 machine to make 1 widget**\n", "\n", "- 1 machine takes 5 minutes to make 1 widget.\n", "\n", "**Step 3: Calculate how long 100 machines take to make 100 widgets**\n", "\n", "- Since each machine makes 1 widget in 5 minutes,\n", "- 100 machines working simultaneously can make 100 widgets in 5 minutes.\n", "\n", "**Answer:**\n", "\n", "\\[\n", "\\boxed{5 \\text{ minutes}}\n", "\\]\n", "\n", "So, 100 machines will take 5 minutes to make 100 widgets.\n" ] } ], "source": [ "# Ask it again\n", "\n", "response = openai.chat.completions.create(\n", " model=\"gpt-4.1-mini\",\n", " messages=messages\n", ")\n", "\n", "answer = response.choices[0].message.content\n", "print(answer)\n" ] }, { "cell_type": "code", "execution_count": 14, "metadata": {}, "outputs": [ { "data": { "text/markdown": [ "Let's analyze the problem step-by-step:\n", "\n", "**Given:**\n", "- 5 machines take 5 minutes to make 5 widgets.\n", "\n", "**Step 1: Find the rate per machine**\n", "\n", "If 5 machines make 5 widgets in 5 minutes, then:\n", "\n", "- Each machine makes 1 widget in 5 minutes (because 5 widgets / 5 machines = 1 widget per machine in 5 minutes).\n", "\n", "**Step 2: Determine time for 1 machine to make 1 widget**\n", "\n", "- 1 machine takes 5 minutes to make 1 widget.\n", "\n", "**Step 3: Calculate how long 100 machines take to make 100 widgets**\n", "\n", "- Since each machine makes 1 widget in 5 minutes,\n", "- 100 machines working simultaneously can make 100 widgets in 5 minutes.\n", "\n", "**Answer:**\n", "\n", "\\[\n", "\\boxed{5 \\text{ minutes}}\n", "\\]\n", "\n", "So, 100 machines will take 5 minutes to make 100 widgets." ], "text/plain": [ "" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "from IPython.display import Markdown, display\n", "\n", "display(Markdown(answer))\n", "\n" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "# Congratulations!\n", "\n", "That was a small, simple step in the direction of Agentic AI, with your new environment!\n", "\n", "Next time things get more interesting..." ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "\n", " \n", " \n", " \n", " \n", "
\n", " \n", " \n", "

Exercise

\n", " Now try this commercial application:
\n", " First ask the LLM to pick a business area that might be worth exploring for an Agentic AI opportunity.
\n", " Then ask the LLM to present a pain-point in that industry - something challenging that might be ripe for an Agentic solution.
\n", " Finally have 3 third LLM call propose the Agentic AI solution.
\n", " We will cover this at up-coming labs, so don't worry if you're unsure.. just give it a try!\n", " \n", "
" ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "This is an excellent and timely business idea! Agentic AI personal productivity assistants harnessing autonomous decision-making can really transform how knowledge workers manage complexity and cognitive load.\n", "\n", "I’d be glad to help you take this forward. Here are some thoughts on specific tech, go-to-market, and challenges you might consider next:\n", "\n", "---\n", "\n", "### Technology Approaches \n", "\n", "**1. Modular AI Architecture** \n", "- Use a modular design separating perception (data ingestion), reasoning (task prioritization and planning), and action (scheduling, communication). \n", "- Leverage transformers and few-shot learning for understanding documents, emails, etc., combined with reinforcement learning or planning algorithms for autonomous task execution. \n", "\n", "**2. Data Integration & Privacy** \n", "- Connectors/APIs for common productivity stacks (Outlook, Gmail, Teams, Slack, Jira, Trello). \n", "- On-device or federated learning to respect privacy while tailoring AI to users. \n", "- Fine-tune or prompt large language models (LLMs) with user context to synthesize info and support decision-making autonomously. \n", "\n", "**3. Autonomous Decision-Making Framework** \n", "- Implement bounded autonomy with user-configurable guardrails to prevent undesired actions (e.g., confirm meeting cancellations). \n", "- Combine symbolic reasoning with neural nets to ensure explainability and controllability. \n", "\n", "**4. Continuous Learning & Adaptation** \n", "- Use user feedback loops and passive monitoring for improving task prioritization and workflow adaptations. \n", "- Incorporate goal-tracking modules that dynamically update plans based on progress and context changes. \n", "\n", "---\n", "\n", "### Market Entry & Validation \n", "\n", "**1. Start with Early Adopters** \n", "- Target high-pressure knowledge workers dealing with information overload (e.g., legal professionals, consultants, academics). \n", "- Build a minimal viable product (MVP) focused on one key pain point like autonomous email triage or meeting management. \n", "\n", "**2. User Research & Iteration** \n", "- Conduct contextual inquiries and use diary studies to deeply understand workflows. \n", "- Iterate on AI autonomy levels—some users want suggestions, others may want full autonomy in scheduling and task delegation. \n", "\n", "**3. Strategic Partnerships** \n", "- Partner with SaaS productivity vendors to build integrations and co-market. \n", "- Enterprise pilot programs with companies looking to boost team productivity on hybrid work models. \n", "\n", "---\n", "\n", "### Challenges to Anticipate \n", "\n", "**1. Trust & Reliability** \n", "- Autonomous agents need to be highly reliable—mistakes in scheduling or delegation can have outsized consequences. \n", "- Transparent explanation mechanisms will be critical to build user trust. \n", "\n", "**2. Privacy & Security** \n", "- Handling sensitive emails, calendar, and documents requires rigorous compliance (GDPR, HIPAA, etc.) and user consent workflows. \n", "\n", "**3. User Control vs. Autonomy Balance** \n", "- Finding the right balance between agentic autonomy and user control/customization is a user experience challenge. \n", "- Allow users to tune autonomy levels per task or context. \n", "\n", "**4. Integration Complexity** \n", "- Enterprise ecosystems are fragmented; building robust connectors and handling evolving APIs will require ongoing effort. \n", "\n", "---\n", "\n", "If you want, I can help you create a more detailed product roadmap, identify AI frameworks and APIs to leverage (OpenAI, LangChain, LangSmith, etc.), or devise pilot testing protocols. Just say the word!\n" ] } ], "source": [ "# First create the messages:\n", "\n", "messages = [{\"role\": \"user\", \"content\": \"Can you generate a business idea for me to workth exploring for an Agentic AI?\"}]\n", "\n", "# Then make the first call:\n", "\n", "response = openai.chat.completions.create(\n", " model=\"gpt-4.1-mini\",\n", " messages=messages\n", ")\n", "\n", "# Then read the business idea:\n", "\n", "business_idea = response.choices[0].message.content\n", "print(business_idea)\n", "\n", "# And repeat! In the next message, include the business idea within the message\n", "\n", "messages = [{\"role\": \"user\", \"content\": business_idea}]\n", "\n", "response = openai.chat.completions.create(\n", " model=\"gpt-4.1-mini\",\n", " messages=messages\n", ")\n", "print(response.choices[0].message.content)" ] } ], "metadata": { "kernelspec": { "display_name": "agents", "language": "python", "name": "python3" }, "language_info": { "codemirror_mode": { "name": "ipython", "version": 3 }, "file_extension": ".py", "mimetype": "text/x-python", "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", "version": "-1.-1.-1" } }, "nbformat": 4, "nbformat_minor": 2 }