This course equips you with the skills to design and implement AI agents tailored to the financial sector. Beginning with an introduction to AI agents, you will explore extending agents with tools, structured outputs, and state management. The course emphasizes practical programming in Python, covering agent memory, API integrations, and database interactions. Key concepts include short-term and long-term memory management, Agentic Retrieval Augmented Generation (RAG), and agent evaluation techniques. At the end of this course, you will apply your knowledge in a project, creating a comprehensive FinTool Analyst AI agent that synthesizes course principles.
Overview
Syllabus
- Introduction to Building AI Agents for Financial Services
- Learn to build AI agents for financial services that retrieve, analyze, and synthesize data, mimicking expert analyst reasoning using Python, APIs, and agentic workflows.
- Extending Agents with Tools
- Extend AI agents beyond text with tool integrations, enabling reliable real-time actions and data access.
- Building Agents with Tools in Python for Financial Services
- Learn to build AI financial agents in Python by defining functions as tools, using JSON schemas, and orchestrating multi-step conversations for accurate, explainable analysis.
- Structured Outputs
- Discover structured outputs in AI: transform responses into actionable JSON for integration. Utilize schemas, parsers, and function calls to enhance reliability and automation in workflows.
- Implementing Structured Outputs with Pydantic for Financial Services
- Learn to enforce strict, validated JSON schemas on AI outputs for finance using Pydantic, ensuring reliable, type-safe, and fail-safe structured data ready for real applications.
- Agent State Management
- Explore agent state management with state machines. Learn how agents track user input, instructions, and tool use for complex workflows, ensuring adaptability and reliability.
- Implementing Agent State Management with Python for Financial Services
- Learn to build reliable, auditable AI agents for financial workflows in Python using state machines, dataclasses, and processor classes to manage multi-step processes with data integrity.
- Short-Term Agent Memory
- Explore short-term memory in AI agents, enhancing coherence via state, ephemeral, and ephemeral memory strategies for efficient context retention in active sessions.
- Adding Agent Memory with Python for Financial Services
- Learn to build AI assistants for financial services with Python by implementing short-term memory: sliding window, running summary, and structured data extraction for better context retention.
- External Tools and APIs
- Explore using external APIs for real-time data, dynamic actions, and authenticating agents. Discover MCP, a protocol standardizing AI’s tool interoperability and safety.
- Integrating External Tools and APIs with OpenAI & Python for Financial Services
- Learn to build AI agents in Python that fetch live financial data using APIs, extract info with LLMs, calculate costs, and interactively handle incomplete user queries.
- Web Search Agents
- Equip agents to search web for real-time, unstructured info. Ground responses in evidence using APIs, handle noise, and avoid hallucination for credible answers.
- Creating Web Search Agents with Python for Financial Services
- Learn to build Python AI agents for real-time financial research by integrating web search APIs, filtering credible sources, using LLMs for data extraction, and delivering concise summaries.
- Interacting with Databases
- Equip agents to access and modify structured data by using SQL for interaction and vector databases for semantic tasks, ensuring seamless integration with private systems.
- Building Database Agents in Python for Financial Services
- Learn to build AI agents in Python that convert plain English into safe SQL for finance, with validation, safety guardrails, retry logic, and clear natural language summaries.
- Agentic Retrieval Augmented Generation
- Discover Agentic RAG: Enhance RAG by enabling reflection, query reformulation, and intelligent adaption for nuanced answers. Master retrieval, reasoning, and retry loops.
- Agentic RAG with Python and ChromaDB for Financial Services
- Learn to build an autonomous RAG agent with Python and ChromaDB for finance, featuring self-evaluation, improved search queries, reliable answers, and confidence assessment.
- Long-Term Agent Memory
- Explore long-term agent memory: understand semantic, episodic, and procedural memories. Learn storage strategies and best practices for personalized, coherent interactions.
- Maintaining Long-Term Agent Memory in Python for Financial Services
- Learn to implement persistent, intelligent long-term memory for AI agents in Python using PostgreSQL, SQLAlchemy, and LLMs for consistent, context-aware financial advice.
- Agent Evaluation
- Agent Evaluation guides assessing an agent’s task completion, quality, tool use, and system metrics using response, step, or trajectory strategies to ensure reliable and efficient operations.
- Evaluating Agents with Python for Financial Services
- Discover how to evaluate agentic RAG systems in financial services with Python, using accuracy, citation, and retrieval metrics for objective, actionable AI performance insights.
- Project: FinTool Analyst
- In this hands-on project, you'll build a sophisticated multi-tool agentic system that serves as an intelligent financial analyst assistant.
Taught by
Sohbet Dovranov and Henrique Santana
Related Courses
Related Articles
-
6 Best AI Agent Courses for Beginners and Non-Coders in 2026
-
Harvard’s Intro to Python: Earn a Free Certificate
-
15 Best Python Courses for 2026: Learn the Most Popular Language
-
12 Best Retrieval-Augmented Generation (RAG) Courses in 2026
-
12 Best Data Analysis Courses for 2026: From Data to Insights
-
13 Best Data Science Courses for 2026
