← Back to Projects
AI AgentLLMPythonData AnalyticsMachine Learning

Multi-Agent Financial Research Assistant

An LLM-orchestrated multi-agent system that automates financial research pipelines: Data Collection Agent → Quantitative Analysis Agent → Report Generation Agent, with tool use and context memory — compressing research cycles from days to minutes.

10 min read
Interactive Demo
5 tech tags

Overview

This project builds a Supervisor-Worker multi-agent system for automated financial research. Users submit a research topic (e.g. 'Analyze Q3 earnings risk for [company]'), and the Supervisor Agent decomposes it into subtasks dispatched to specialist Workers: a Data Collection Agent fetches financials and news, a Quantitative Analysis Agent runs metric calculations and anomaly detection, and a Report Generation Agent assembles a structured research report.

Key Features

01

Supervisor-Worker architecture: Supervisor handles task decomposition, sub-agent scheduling, and result aggregation with dynamic routing

02

Tool calling (Function Calling): each agent has a dedicated toolset including financial data APIs, calculators, and chart generators

03

Context memory management: short-term state storage with history summarization to prevent token overflow

04

Parallel agent execution: data collection and initial analysis run concurrently, reducing total latency by ~60%

05

Human-in-the-loop: critical nodes (risk rating, conclusion sign-off) pause for human approval, ensuring output trustworthiness

Methodology

Built on LangGraph StateGraph. Each node is an agent; edges are conditional routing rules. The Supervisor uses ReAct (reason → act → observe) planning loops. Worker agents return structured JSON via Pydantic models. The Supervisor aggregates outputs and passes them to the Report Agent, which produces a Markdown report with sections: Executive Summary, Financial Analysis, Risk Assessment, and Investment Thesis.

Tech Stack

AI AgentAGENT
LLMLLM
PythonPY
Data AnalyticsDA
Machine LearningML

Project Info

Read time10 min
Live demoAvailable
FeaturedYes
Tags5
← Back to Projects
Interactive Demo

Multi-Agent Pipeline Demo

Select a research topic, launch the 4-layer agent pipeline, and watch tool call logs and final report generation in real time.

Multi-Agent · Pipeline Demo

Financial Research Multi-Agent System

4-layer agent pipeline with tool call logs and structured output.

0/4

11Supervisor22Data Collect33Quant Analyst44Report Gen