In the financial services industry, analysts need to switch between structured data (such as time-series pricing information), unstructured text (such as SEC filings and analyst reports), and audio/visual content (earnings calls and presentations). Each format requires different analytical approaches and specialized tools, creating workflow inefficiencies. Add on top of this the intense time pressure resulting from rapidly evolving industry conditions and narrow decision windows. Delayed analysis can mean missed opportunities or failure to identify emerging risks, with potentially significant financial consequences.
AI-assistants boost productivity by automating routine data collection and processing tasks, surfacing relevant insights, and allowing analysts to focus on higher-value activities. However, a single AI agent struggles with complex, multistep investment research workflows to effectively handle the full spectrum of multiple specialized tasks. This is where multi-agent collaboration provides an advancement. By creating specialized AI subagents that excel in specific tasks and functionalities and using them together under a coordinated framework using an AI supervisor agent, we can address the full complexity of investment research workflows. A supervisor agent can intelligently decompose complex queries, delegate specialized tasks to subagents, and synthesize their outputs into comprehensive answers—similar to how a research team functions in the real world. The benefits of this approach are substantial, stemming from distributed problem-solving and specialization, improved accuracy through specialized expertise, enhanced scalability by adding new agent capabilities without rebuilding the entire system, and greater transparency because the reasoning process of each specialized agent can be tracked and verified.
Amazon Bedrock Agents uses the reasoning of foundation models (FMs), APIs, and data to break down user requests, gather relevant information, and efficiently complete tasks. With the multi-agent collaboration capability of Amazon Bedrock, you can build, deploy, and manage multiple AI agents working together on complex multistep tasks that require specialized skills. Amazon Bedrock Data Automation (BDA) enables the generation of useful insights from unstructured multimodal content such as documents, images, audio, and video for your AI-powered applications, and it can be used as a parser when setting up a knowledge base for Retrieval Augmented Generation (RAG) workflows.
In this post, we walk through how to build a multi-agent investment research assistant using the multi-agent collaboration capability of Amazon Bedrock. Our solution demonstrates how a team of specialized AI agents can work together to analyze financial news, evaluate stock performance, optimize portfolio allocations, and deliver comprehensive investment insights—all orchestrated through a unified, natural language interface. We use BDA as a parser when setting up a knowledge base for RAG workflows with multi-modal data. Amazon Nova understanding models are used as the large language models (LLMs) associated with the supervisor agents and subagents.
Check the video that demonstrates the solution,
Results from these agents are demonstrative, not to be taken as financial advice.
Solution overview
The multi-agent investment research assistant is composed of a supervisor agent and three subagents (quantitative analysis agent, news agent, and smart summarizer agent) working together in a coordinated framework, as shown in the following diagram.
The supervisor agent uses the instructions you provide to understand the structure and role of each collaborator agent. The supervisor agent orchestrates the overall investment research process by breaking down user prompts, delegating subtasks to specialized subagents, and consolidating their outputs to generate the final response. Each subagent is configured to carry out specialized tasks as follows:
- Quantitative analysis agent
- Functions – Powered by stock-query and portfolio-optimization action groups. Responsibilities – Query and analyze historical stock data and build optimized portfolio allocations based on user inputs such as stock tickers or investment amount.
- Functions – Powered by the
web_search action group and the financial_analysis_KB knowledge base. Responsibilities – Search and retrieve relevant financial data such as earnings reports and filings from the knowledge base for context. If information isn’t present in the knowledge base, construct a web query. Handles queries related to analyzing company financials, performance drivers, and management commentary. - Functions – Uses LLM capabilities with specific prompt instructions, no custom action group. Responsibilities – Takes in output from other subagents, such as recent news and financial data, and synthesizes the information into structured investment insights. Summarizes long texts or documents such as earnings reports into concise insights.
Multi-agent collaboration works as follows:
- User prompts the multi-agent investment research assistant with a high-level research query. Supervisor agent breaks the query into subtasks and orchestrates and invokes the relevant subagents in parallel or sequentially as needed:
- News agent to retrieve financial reports or data Quantitative analysis agent for stock data analysis Smart summarizer agent to summarize lengthy texts
This architecture uses the strengths of the different specialized agents to comprehensively address the various aspects of investment research, and the supervisor agent provides the intelligent orchestration.
Technical architecture
The following diagram is the technical architecture.
Some of the key components and the associated codes of the technical architecture are:
- Amazon Bedrock Data Automation (BDA) for processing data – The following invokes a BDA job asynchronously using the
invoke_data_automation_async() method from the bda-runtime client in boto3: Defining and building subagents with tools – The following creates a subagent using Agent.create. It defines two Lambda tools—one for fetching historical stock data and another for running portfolio optimization—then registers them with the subagent along with its role, goal, instructions, and the underlying FM. - Defining and building the supervisor agent (multi-agent investment research assistant) – The following creates a supervisor agent using
SupervisorAgent.create. It defines the collaborator agents (subagents), and registers them with the supervisor agent along with its role, goal, instructions, and the underlying FM. Invoking the supervisor agent (multi-agent investment research assistant) – The following uses the invoke method to pass in the defined request as a prompt and get response from the supervisor agent, using the multi-agent collaboration architecture. Prerequisites
To deploy this solution, attach the appropriate permissions for Amazon Bedrock, AWS Lambda, Amazon OpenSearch Serverless, Amazon Simple Storage Service (Amazon S3), and AWS Identity and Access Management (IAM) to your execution role. You also need to deploy two AWS CloudFormation stacks: web_search and stock_data.
For more information on the permission policy, CloudFormation stacks, and setting up the environment, refer to the README.md in the investment_research_agent repository on GitHub.
Dive deeper into the solution
To dive deeper into the solution and the code shown in this post, refer to the investment research assistant agent GitHub repo. The repo contains instructions for the end-to-end solution, including setting up the supervisor agent and subagents, associated action groups, unstructured data (earnings reports PDF files and earnings call audio files), and structured data (stocks time series).
In the appendix at the end of this post, we share different questions asked by a financial analyst to the supervisor agent, the subagent invoked, and the answers from the supervisor agent.
Cleanup
To clean up this solution, make sure to delete all agents, knowledge bases, and associated Amazon OpenSearch Serverless instances. Delete both the web_search and stock_data stacks. This will make sure that no charges are incurred after you’re finished testing this solution. Read the associated notebook in the GitHub repository for more instructions on cleaning up the agents.
Conclusion
The multi-agent investment research assistant built using Amazon Bedrock Agents with its multi-agent collaboration feature represents how financial professionals can use AI to enhance their analytical capabilities. By using specialized agents—each focusing on distinct aspects of financial analysis—orchestrated by a supervisor agent, we’ve created a system that can process diverse data types, apply appropriate analytical techniques, and synthesize comprehensive insights in response to complex investment queries. The result is an AI assistant that can handle multistep financial analysis workflows that would otherwise overwhelm a single-agent system.
The application of multi-agent collaboration extends broadly across the financial sector, from equity research and portfolio management to risk assessment and compliance monitoring. A complex financial workflow that requires multiple specialized skills and data sources can benefit from this architectural approach.
The implementation uses key AWS services, including Amazon Bedrock for foundation models, the multi-agent collaboration capability of Amazon Bedrock Agents, Amazon S3 for document storage, Amazon OpenSearch Serverless for vector search capabilities, and Lambda functions for specialized actions. This serverless architecture provides scalability, and the knowledge base integration provides context from financial documents to ground the AI’s responses in factual data.
For more information:
- Get started building your own multi-agent investment research assistant by accessing our complete solution code and implementation guide in the GitHub repo. Explore how to customize the solution for your specific investment research needs by modifying the subagents’ specialized tools and action groups and by bringing your data securely to Amazon Bedrock Knowledge Bases. You can also explore and run Amazon Bedrock multi-agent collaboration workshop with AWS specialists or on your own.
Read more about single agent solutions for investment research with multi-modal data:
- Part 1 – Generative AI and multi-modal agents in AWS: The key to unlocking new value in financial markets, which demonstrates how multi-modal agents use AWS services to efficiently gather financial insights from an organization’s text, speech, and tabular data sources for a financial analyst’s query using open source LangChain agents as alternative implementation. Part 2 – AI-powered assistants for investment research with multi-modal data: An application of Amazon Bedrock Agents, which introduces a solution using Amazon Bedrock Agents and Amazon Bedrock Knowledge Bases that can help financial analysts use various multi-modal financial data to gather financial insights.
Read the blog post on Unlocking complex problem-solving with multi-agent collaboration on Amazon Bedrock for more details on benefits, design, and evaluation of multi-agent collaboration for enterprise applications.
About the Authors
Sovik Kumar Nath is an AI/ML and Generative AI senior solution architect with AWS. He has extensive experience designing end-to-end machine learning and business analytics solutions in finance, operations, marketing, healthcare, supply chain management, and IoT. He has double masters degrees from the University of South Florida, University of Fribourg, Switzerland, and a bachelors degree from the Indian Institute of Technology, Kharagpur. Outside of work, Sovik enjoys traveling, taking ferry rides, and watching movies.
Lucas Banerji is an AI/ML and GenAI specialist Solutions Architect at AWS. He is passionate about building agentic AI systems and exploring the frontier of what’s possible with intelligent automation. Lucas holds a degree in Computer Science from the University of Virginia. Outside of work, he enjoys running, practicing Muay Thai, and traveling the world.
Mohan Musti is a Principal Technical Account Manger based out of Dallas. Mohan helps customers architect and optimize applications on AWS. Mohan has Computer Science and Engineering from JNT University, India. In his spare time, he enjoys spending time with his family and camping.
Appendix
The following table contains example questions asked and responses from the AI-powered assistant for investment research based on structured and unstructured data.
| Question Purpose | Question asked by financial analyst to AI-powered assistant | Subagent, action group and/or knowledge base invoked | Intermediate steps from Supervisor agent chain-of-thought reasoning | Multi-agent Investment Research Assistant – Responses |
| Prompt the agent to analyze the company’s financial health and performance. | Analyze Amazon’s financial health based on the 2024 10k report. Calculate important financial ratios. Limit to 5 sentences. | news_agent (financial_analysis_kb), smart_summarizer_agent | 1) I need to specifically request the 2024 10-K report information from the knowledge base. Let me ask the news agent for this specific report. 2) Since the knowledge base contains recent financial information and forward-looking guidance, I’ll provide a comprehensive summary of Amazon’s financial metrics and projections. 3) Now I’ll ask the analyst agent to analyze this information and calculate key financial ratios. | Based on Amazon’s recent financial data, the company demonstrates strong financial health with total assets of $624.9B and a robust cash position of $78.8B, while generating $143.3B in net sales and $59.2B in net income. Key profitability metrics show improvement with a 46% gross margin, 4.4% operating margin, and 14.8% return on equity, while efficiency ratios remain healthy with inventory turnover at 13.2x and asset turnover at 1.4x. Liquidity ratios (current ratio: 1.06, quick ratio: 0.88) are adequate though tight, but are supported by strong operating cash flow of $54.3B, representing a 38% year-over-year increase. The company maintains a balanced leverage profile with a debt-to-equity ratio of 0.98 and solid interest coverage ratio of 8.5x, indicating good debt management. Despite ongoing high capital expenditures, Amazon’s improving margins, strong cash generation, and efficient operations suggest a healthy financial position with sustainable growth potential. |
| Prompt the agent to analyze the company’s financial performance from company’s earnings reports | What were the main drivers of AWS’s revenue growth in the Q1 2023 quarter? Please limit your answers to 5 sentences. | news_agent (financial_analysis_kb), smart_summarizer_agent | 1.) I need to get information about AWS’s Q1 2023 earnings report. I’ll ask the news agent to check the knowledge base for this specific information. 2.) Based on the search results, I can provide a comprehensive answer about AWS’s Q1 2023 performance and growth drivers. The information comes directly from their earnings reports. 3.) I’ll synthesize this information into a concise response focusing on the main drivers and send it to the user. | AWS’s Q1 2023 revenue growth was primarily driven by continued cloud adoption, achieving net sales of $21.4 billion and a 16% year-over-year growth rate. However, the growth was tempered by customers across all segments optimizing their cloud spending in response to economic uncertainty. The business maintained strong fundamentals with an annualized sales run rate exceeding $85 billion, though momentum showed signs of slowing with April growth rates declining by approximately 500 basis points compared to Q1. |
| Prompt the agent to analyze the company’s management team and their plans for the future from company’s earnings reports | What are Amazon’s top priorities for 2024? What are the biggest risks facing the company? Please limit your answers to 5 sentences. | news_agent (financial_analysis_kb & web_search), smart_summarizer_agent | 1.) I’ll ask the news agent to check the knowledge base for recent information about Amazon’s strategic priorities and risk factors for 2024. 2.) Let me get additional recent news and risk factors by asking the news agent to search for supplementary information. 3.) Based on the recent news searches, I can now provide a comprehensive overview of the significant risks currently facing Amazon | Amazon’s top priorities for 2024 include expanding international stores, growing grocery and B2B retail segments, scaling the “Buy with Prime” program, advancing healthcare initiatives, and developing low Earth orbit satellite capabilities for improved connectivity. The company faces several significant risks, including substantial AI-related capital expenditure pressures (expected $75 billion in 2024), increasing regulatory scrutiny from the FTC and competition authorities, potential impacts from new Chinese import tariffs, and intensifying competition in both cloud computing and retail sectors. Amazon is balancing these ambitious growth initiatives with cost optimization efforts, while viewing their strategic investments as potentially transformative for their long-term future. |
| Prompt the agent to build an optimal portfolio using the collected data | Optimize my portfolio with AAA, BBB, and CCC [anonymized tickers] | quantitative_analysis_agent (stock_data_lookup & portfolio tool) | 1.) I need to get historical stock data for these three stocks before running portfolio optimization. I’ll ask the stock data agent for this information. 2.) Now that I have retrieved the historical price data for all three stocks, I’ll perform portfolio optimization using this data. 3.) I’ll synthesize this information into a clear, comprehensive response for the user. | Based on portfolio optimization analysis, here is the recommended allocation: Company A (AAA): 61.04% Company B (BBB): 32.54% Company C (CCC): 6.42% This allocation optimizes risk-adjusted returns based on recent market data. Please note that these allocations are based on mathematical optimization and historical data. Consider your personal investment goals, risk tolerance, and market conditions when making investment decisions. |
| Prompt the agent to look up news and relate it to stock data | What was happening to AMZN stock in November 2024, relate that to news in the same timeframe | news_agent (web_search), quantitative_analysis_agent (stock_data_lookup), & smart_summarizer_agent | 1.) I’ll need to get both recent stock price data and news, then synthesize them together. I’ll request both simultaneously to be efficient. 2.) I’ll now synthesize the stock price movement with the recent news developments to provide a comprehensive analysis. | November 2024: Stock Price Movement: – Trading Range: $161.43 (low) to $206.21 (high) – Overall Trend: Significant upward momentum with notable volatility – Key Technical Levels: Resistance at $206, Support at $190. Key News Impact: 1. Q4 2024 Guidance (Released Oct 31): – Projected net sales: $181.5-188.5 billion – Expected growth: 7-11% year-over-year – This guidance served as a major catalyst for the stock’s movement Price-News Correlation: – The strong upward movement (~27% range) appears to be primarily driven by positive Q4 guidance – Investor confidence was bolstered by the projected sales growth – The wide guidance range reflected optimism around the holiday shopping season – Higher trading volumes were observed during price movements, indicating strong market participation The stock’s performance suggests that investors responded positively to Amazon’s forward-looking guidance, particularly regarding holiday season expectations. The volatility in price movements indicates active trading around these news events, with the market generally maintaining an optimistic outlook on Amazon’s near-term prospects. |
