{ "cells": [ { "cell_type": "markdown", "metadata": {}, "source": [ "# Welcome to the start of your adventure in Agentic AI" ] }, { "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": 1, "metadata": {}, "outputs": [], "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" ] }, { "cell_type": "code", "execution_count": 2, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "True" ] }, "execution_count": 2, "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": 3, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "OpenAI API Key exists and begins gsk_sjqt\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('GROQ_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": 29, "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\n", "from agents import OpenAIChatCompletionsModel\n", "from openai import AsyncOpenAI\n", "import asyncio" ] }, { "cell_type": "code", "execution_count": 86, "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", "GEMINI_BASE_URL = \"https://generativelanguage.googleapis.com/v1beta/openai/\"\n", "google_api_key = os.getenv(\"GOOGLE_API_KEY\")\n", "gemini_client = OpenAI(base_url=GEMINI_BASE_URL, api_key='AIzaSyCBFpyTKTpU0s3X0FYycZ28GHS-6VGqjEg')\n", "gemini_model = OpenAIChatCompletionsModel(model=\"gemini-2.5-flash\", openai_client=gemini_client)\n" ] }, { "cell_type": "code", "execution_count": 62, "metadata": {}, "outputs": [], "source": [ "# Create a list of messages in the familiar OpenAI format\n", "\n", "messages = [{\"role\": \"user\", \"content\": \"What is 2+2?\"}]" ] }, { "cell_type": "code", "execution_count": 88, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "2 + 2 = 4\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 = gemini_client.chat.completions.create(model=\"gemini-2.5-flash-preview-05-20\", messages=[{\"role\":\"user\", \"content\": \"what is 2+2?\"}])\n", "print(response.choices[0].message.content)\n", " \n", "\n", "\n", " \n", "\n" ] }, { "cell_type": "code", "execution_count": 89, "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": 91, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Consider a sequence of number transformations where each output becomes the input for the next step. The rules applied follow a repeating cycle.\n", "\n", "Step 1: 10 becomes 21.\n", "Step 2: 21 becomes 9.\n", "Step 3: 9 becomes 1.\n", "Step 4: 1 becomes 3.\n", "Step 5: 3 becomes 0.\n", "Step 6: 0 becomes 0.\n", "\n", "What is the next number in the sequence of outputs?\n" ] } ], "source": [ "# ask it - this uses GPT 4.1 mini, still cheap but more powerful than nano\n", "\n", "\n", "response = gemini_client.chat.completions.create(\n", " model=\"gemini-2.5-flash-preview-05-20\",\n", " messages=messages)\n", " \n", " \n", "question = response.choices[0].message.content\n", "\n", "print(question)\n" ] }, { "cell_type": "code", "execution_count": 92, "metadata": {}, "outputs": [], "source": [ "# form a new messages list\n", "messages = [{\"role\": \"user\", \"content\": question}]\n" ] }, { "cell_type": "code", "execution_count": 95, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Let's break down the sequence of transformations and the rules:\n", "\n", "1. **Understand the rules:** We have a cycle of 6 rules. Each rule is defined by a specific input-output pair for that step.\n", " * Rule 1 (for Step 1, 7, 13, ...): If input is 10, output is 21.\n", " * Rule 2 (for Step 2, 8, 14, ...): If input is 21, output is 9.\n", " * Rule 3 (for Step 3, 9, 15, ...): If input is 9, output is 1.\n", " * Rule 4 (for Step 4, 10, 16, ...): If input is 1, output is 3.\n", " * Rule 5 (for Step 5, 11, 17, ...): If input is 3, output is 0.\n", " * Rule 6 (for Step 6, 12, 18, ...): If input is 0, output is 0.\n", "\n", "2. **Trace the sequence of outputs:**\n", " * Starting number: 10\n", " * **Step 1:** Input is 10. Rule 1 applies (\"10 becomes 21\"). Output: **21**\n", " * **Step 2:** Input is 21. Rule 2 applies (\"21 becomes 9\"). Output: **9**\n", " * **Step 3:** Input is 9. Rule 3 applies (\"9 becomes 1\"). Output: **1**\n", " * **Step 4:** Input is 1. Rule 4 applies (\"1 becomes 3\"). Output: **3**\n", " * **Step 5:** Input is 3. Rule 5 applies (\"3 becomes 0\"). Output: **0**\n", " * **Step 6:** Input is 0. Rule 6 applies (\"0 becomes 0\"). Output: **0**\n", "\n", "3. **Find the next number:**\n", " We have just completed Step 6, and the output was 0.\n", " The \"next number in the sequence of outputs\" means we need to perform Step 7.\n", " For Step 7, the rule cycle repeats, so we apply **Rule 1**.\n", " The input for Step 7 is the output of Step 6, which is **0**.\n", "\n", " Now, we apply Rule 1 (\"10 becomes 21\") to the number 0.\n", " Since the input (0) does not match the specific condition of Rule 1 (which only transforms 10), the number remains unchanged by this rule.\n", "\n", "Therefore, the next number in the sequence of outputs is **0**.\n" ] } ], "source": [ "# Ask it again\n", "\n", "response = gemini_client.chat.completions.create(\n", " model=\"gemini-2.5-flash-preview-05-20\",\n", " messages=messages\n", ")\n", "\n", "answer = response.choices[0].message.content\n", "print(answer)\n" ] }, { "cell_type": "code", "execution_count": 96, "metadata": {}, "outputs": [ { "data": { "text/markdown": [ "Let's break down the sequence of transformations and the rules:\n", "\n", "1. **Understand the rules:** We have a cycle of 6 rules. Each rule is defined by a specific input-output pair for that step.\n", " * Rule 1 (for Step 1, 7, 13, ...): If input is 10, output is 21.\n", " * Rule 2 (for Step 2, 8, 14, ...): If input is 21, output is 9.\n", " * Rule 3 (for Step 3, 9, 15, ...): If input is 9, output is 1.\n", " * Rule 4 (for Step 4, 10, 16, ...): If input is 1, output is 3.\n", " * Rule 5 (for Step 5, 11, 17, ...): If input is 3, output is 0.\n", " * Rule 6 (for Step 6, 12, 18, ...): If input is 0, output is 0.\n", "\n", "2. **Trace the sequence of outputs:**\n", " * Starting number: 10\n", " * **Step 1:** Input is 10. Rule 1 applies (\"10 becomes 21\"). Output: **21**\n", " * **Step 2:** Input is 21. Rule 2 applies (\"21 becomes 9\"). Output: **9**\n", " * **Step 3:** Input is 9. Rule 3 applies (\"9 becomes 1\"). Output: **1**\n", " * **Step 4:** Input is 1. Rule 4 applies (\"1 becomes 3\"). Output: **3**\n", " * **Step 5:** Input is 3. Rule 5 applies (\"3 becomes 0\"). Output: **0**\n", " * **Step 6:** Input is 0. Rule 6 applies (\"0 becomes 0\"). Output: **0**\n", "\n", "3. **Find the next number:**\n", " We have just completed Step 6, and the output was 0.\n", " The \"next number in the sequence of outputs\" means we need to perform Step 7.\n", " For Step 7, the rule cycle repeats, so we apply **Rule 1**.\n", " The input for Step 7 is the output of Step 6, which is **0**.\n", "\n", " Now, we apply Rule 1 (\"10 becomes 21\") to the number 0.\n", " Since the input (0) does not match the specific condition of Rule 1 (which only transforms 10), the number remains unchanged by this rule.\n", "\n", "Therefore, the next number in the sequence of outputs is **0**." ], "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": 98, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Okay, let's pick a business area ripe for Agentic AI:\n", "\n", "---\n", "\n", "**Business Area: Financial Crime & Compliance (Specifically, Anti-Money Laundering - AML)**\n", "\n", "**Why this is Ripe for an Agentic AI Opportunity:**\n", "\n", "1. **Massive Data Volume & Complexity:** Banks and financial institutions process billions of transactions daily, across countless customers, geographies, and financial products. The data is often unstructured, diverse, and comes from numerous internal and external sources.\n", "2. **Evolving Threat Landscape:** Money laundering schemes, terrorist financing, and other financial crimes are constantly evolving, becoming more sophisticated, and leveraging new technologies. Static rules-based systems are easily outsmarted.\n", "3. **High Stakes & Regulatory Pressure:** Regulatory fines for AML failures are astronomical (often billions of dollars), and reputational damage can be severe. Regulators are increasingly demanding more proactive, data-driven, and effective compliance measures.\n", "4. **Labor Intensive & Inefficient:** Current AML processes rely heavily on human analysts reviewing alerts, conducting investigations, and filing Suspicious Activity Reports (SARs). This is incredibly resource-intensive, prone to human error and fatigue, and often leads to high false positive rates (alert fatigue).\n", "5. **Need for Proactive Intelligence:** The goal isn't just to *react* to suspicious transactions, but to *proactively identify* emerging threats, connect disparate pieces of information, and anticipate illicit activities before they fully materialize.\n", "\n", "**How an Agentic AI Would Operate (The Opportunity):**\n", "\n", "Imagine an \"AML Intelligence Agent\" designed to be proactive, autonomous (within defined guardrails), and adaptive:\n", "\n", "* **Intelligent Data Ingestion & Synthesis:**\n", " * Continuously ingest and analyze transaction data, customer KYC (Know Your Customer) information, communication records, news feeds, social media data (where permissible), public records, and global sanctions lists.\n", " * Intelligently normalize and connect disparate data points, forming a comprehensive, real-time risk profile for entities and transactions.\n", "\n", "* **Dynamic Risk Scoring & Pattern Detection:**\n", " * Move beyond static rules to leverage advanced AI/ML models that detect subtle, evolving patterns indicative of money laundering, even those not previously seen. This includes behavioral anomalies, network analysis (identifying suspicious connections between entities), and predictive analytics.\n", " * Dynamically adjust risk scores for customers and transactions based on ongoing behavior and external factors.\n", "\n", "* **Proactive Investigation & Orchestration:**\n", " * Instead of just flagging an alert, the agent proactively *initiates an investigation workflow*.\n", " * It automatically gathers all relevant information (account history, communications, counterparty details, public records) needed for a human analyst to review.\n", " * It might even *draft initial narratives* for SARs, highlighting key findings and the logical chain of evidence.\n", " * It could proactively suggest further lines of inquiry, additional data sources to consult, or even recommend freezing an account (for human review/approval).\n", "\n", "* **Adaptive Learning & Threat Intelligence:**\n", " * Continuously learn from human feedback on investigations (e.g., which alerts led to true positives, which were false).\n", " * Automatically adapt its detection models to new money laundering typologies and regulatory changes.\n", " * Generate real-time threat intelligence for the compliance team, highlighting emerging risks or patterns observed across the institution's activity.\n", "\n", "* **Explainable Insights (XAI):**\n", " * Crucially, the agent would need strong XAI capabilities to explain *why* it flagged something as suspicious or why it recommended a particular action. This is vital for regulatory scrutiny and human trust.\n", "\n", "**Benefits of an Agentic AI in AML:**\n", "\n", "1. **Reduced False Positives:** By understanding context and evolving patterns, the AI can significantly reduce the number of irrelevant alerts, freeing up human analysts for true risks.\n", "2. **Enhanced Detection of Sophisticated Schemes:** Identifies complex, layered money laundering schemes that static rules or human review might miss.\n", "3. **Faster Response Times:** Real-time analysis and automated information gathering drastically reduce the time from detection to investigation.\n", "4. **Cost Efficiency:** Significant reduction in operational costs associated with manual review and investigation.\n", "5. **Improved Regulatory Compliance:** Proactive intelligence and more accurate reporting lead to a stronger compliance posture and reduced risk of fines.\n", "6. **Empowered Human Analysts:** Humans transition from data-entry and initial review to higher-value tasks: strategic analysis, complex decision-making, direct engagement with authorities, and training/overseeing the AI.\n", "\n", "This area offers immense potential for an Agentic AI to not just assist, but to fundamentally transform how financial institutions combat illicit finance, making the global financial system safer and more efficient.\n" ] } ], "source": [ "# First create the messages:\n", "\n", "messages = [{\"role\": \"user\", \"content\": \"pick a business area that might be worth exploring for an Agentic AI opportunity\"}]\n", "\n", "# Then make the first call:\n", "\n", "response = gemini_client.chat.completions.create(\n", " model=\"gemini-2.5-flash-preview-05-20\",\n", " messages=messages\n", ")\n", "\n", "# Then read the business idea:\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", "\n", "\n", "# And repeat! In the next message, include the business idea within the message" ] }, { "cell_type": "code", "execution_count": 99, "metadata": {}, "outputs": [ { "data": { "text/markdown": [ "Okay, let's pick a business area ripe for Agentic AI:\n", "\n", "---\n", "\n", "**Business Area: Financial Crime & Compliance (Specifically, Anti-Money Laundering - AML)**\n", "\n", "**Why this is Ripe for an Agentic AI Opportunity:**\n", "\n", "1. **Massive Data Volume & Complexity:** Banks and financial institutions process billions of transactions daily, across countless customers, geographies, and financial products. The data is often unstructured, diverse, and comes from numerous internal and external sources.\n", "2. **Evolving Threat Landscape:** Money laundering schemes, terrorist financing, and other financial crimes are constantly evolving, becoming more sophisticated, and leveraging new technologies. Static rules-based systems are easily outsmarted.\n", "3. **High Stakes & Regulatory Pressure:** Regulatory fines for AML failures are astronomical (often billions of dollars), and reputational damage can be severe. Regulators are increasingly demanding more proactive, data-driven, and effective compliance measures.\n", "4. **Labor Intensive & Inefficient:** Current AML processes rely heavily on human analysts reviewing alerts, conducting investigations, and filing Suspicious Activity Reports (SARs). This is incredibly resource-intensive, prone to human error and fatigue, and often leads to high false positive rates (alert fatigue).\n", "5. **Need for Proactive Intelligence:** The goal isn't just to *react* to suspicious transactions, but to *proactively identify* emerging threats, connect disparate pieces of information, and anticipate illicit activities before they fully materialize.\n", "\n", "**How an Agentic AI Would Operate (The Opportunity):**\n", "\n", "Imagine an \"AML Intelligence Agent\" designed to be proactive, autonomous (within defined guardrails), and adaptive:\n", "\n", "* **Intelligent Data Ingestion & Synthesis:**\n", " * Continuously ingest and analyze transaction data, customer KYC (Know Your Customer) information, communication records, news feeds, social media data (where permissible), public records, and global sanctions lists.\n", " * Intelligently normalize and connect disparate data points, forming a comprehensive, real-time risk profile for entities and transactions.\n", "\n", "* **Dynamic Risk Scoring & Pattern Detection:**\n", " * Move beyond static rules to leverage advanced AI/ML models that detect subtle, evolving patterns indicative of money laundering, even those not previously seen. This includes behavioral anomalies, network analysis (identifying suspicious connections between entities), and predictive analytics.\n", " * Dynamically adjust risk scores for customers and transactions based on ongoing behavior and external factors.\n", "\n", "* **Proactive Investigation & Orchestration:**\n", " * Instead of just flagging an alert, the agent proactively *initiates an investigation workflow*.\n", " * It automatically gathers all relevant information (account history, communications, counterparty details, public records) needed for a human analyst to review.\n", " * It might even *draft initial narratives* for SARs, highlighting key findings and the logical chain of evidence.\n", " * It could proactively suggest further lines of inquiry, additional data sources to consult, or even recommend freezing an account (for human review/approval).\n", "\n", "* **Adaptive Learning & Threat Intelligence:**\n", " * Continuously learn from human feedback on investigations (e.g., which alerts led to true positives, which were false).\n", " * Automatically adapt its detection models to new money laundering typologies and regulatory changes.\n", " * Generate real-time threat intelligence for the compliance team, highlighting emerging risks or patterns observed across the institution's activity.\n", "\n", "* **Explainable Insights (XAI):**\n", " * Crucially, the agent would need strong XAI capabilities to explain *why* it flagged something as suspicious or why it recommended a particular action. This is vital for regulatory scrutiny and human trust.\n", "\n", "**Benefits of an Agentic AI in AML:**\n", "\n", "1. **Reduced False Positives:** By understanding context and evolving patterns, the AI can significantly reduce the number of irrelevant alerts, freeing up human analysts for true risks.\n", "2. **Enhanced Detection of Sophisticated Schemes:** Identifies complex, layered money laundering schemes that static rules or human review might miss.\n", "3. **Faster Response Times:** Real-time analysis and automated information gathering drastically reduce the time from detection to investigation.\n", "4. **Cost Efficiency:** Significant reduction in operational costs associated with manual review and investigation.\n", "5. **Improved Regulatory Compliance:** Proactive intelligence and more accurate reporting lead to a stronger compliance posture and reduced risk of fines.\n", "6. **Empowered Human Analysts:** Humans transition from data-entry and initial review to higher-value tasks: strategic analysis, complex decision-making, direct engagement with authorities, and training/overseeing the AI.\n", "\n", "This area offers immense potential for an Agentic AI to not just assist, but to fundamentally transform how financial institutions combat illicit finance, making the global financial system safer and more efficient." ], "text/plain": [ "" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "from IPython.display import Markdown, display\n", "\n", "display(Markdown(business_idea))" ] }, { "cell_type": "markdown", "metadata": {}, "source": [] } ], "metadata": { "kernelspec": { "display_name": ".venv", "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": "3.12.11" } }, "nbformat": 4, "nbformat_minor": 2 }