🧠 Google ADK Stock Market Research Agent: Real-Time Investment Reports with Dappier

You can explore this project live on Replit here

This Replit app demonstrates how to build a powerful stock market research agent using Google ADK and Dappier. By combining multi-agent workflows and real-time financial data, this project showcases a novel approach to generating investment-grade markdown reports for any public company.

In this app, you’ll explore:

• Google ADK (Agent Development Kit): A flexible framework by Google to build intelligent, multi-step agents capable of reasoning, decision-making, and orchestration using Gemini models.
• Dappier: A real-time data platform that connects LLMs to live, rights-cleared information across domains like finance, news, and web search. It enriches agent workflows with structured, prompt-ready data.
• Gemini-Powered Agents: Modular LLM agents designed to resolve ticker symbols, extract stock metrics, analyze peer companies, and generate comprehensive investment summaries.
• Replit Deployment: Run the complete multi-agent research pipeline in the browser using Replit, with secure environment variable support and real-time agent execution.

This app not only delivers a practical solution for real-time stock research but also serves as a reusable foundation for any financial analytics tool powered by AI and live data.

🚀 Live Demo

You can explore and test the full stock market research pipeline directly in your browser.

• 🔗 Live Deployment: multi-agent-stock-market-research-or-google-adk-and-dap-dappier.replit.app Run the full multi-agent workflow and get real-time investment reports by entering a company name.

• 🛠️ Source Code: Replit Project Fork the code, explore agent definitions, customize tool integrations, or extend the pipeline for your own use cases.

💡 You don’t need to install anything locally. Just open the link, input a company name (e.g., "Apple"), and receive a full markdown-formatted investment report — powered by Gemini models and Dappier’s real-time financial data.

📦 Installation

This app is built using Replit, so you don’t need to set up any local environment. Just fork or run the app directly in your browser.

However, if you’re setting this up manually or adapting it outside Replit, install the required packages using pip:

pip install google-adk dappier

✅ Note: Replit automatically installs the packages listed in replit.nix or pyproject.toml (if used). You can also manually add packages from the Packages tab in the left sidebar.

Once dependencies are installed, you’re ready to configure your API keys and begin running the agent workflow.

🔑 Setting Up API Keys

To run the stock market research agent, you’ll need the following API keys:

• GOOGLE_API_KEY – For accessing Gemini models via Google ADK.
• GOOGLE_GENAI_USE_VERTEXAI – Set this to "false" to use Gemini on public API instead of Vertex AI.
• DAPPIER_API_KEY – To access real-time financial and web data from Dappier.

🔐 In Replit

1. Click the 🔒 Secrets tab (lock icon) in the left sidebar.
2. Add the following environment variables:

Key	Value
GOOGLE_API_KEY	(Your Google API Key)
GOOGLE_GENAI_USE_VERTEXAI	false
DAPPIER_API_KEY	(Your Dappier API Key)

You can get your API keys from the following sources:

• Google API Key: https://makersuite.google.com/app/apikey
• Dappier API Key: https://platform.dappier.com/profile/api-keys

⚠️ Important: Do not print your API keys or commit them to public repositories. Use environment variables or secret managers to handle credentials securely.

🔌 Real-Time Tools Powered by Dappier

Dappier provides real-time, rights-cleared data that powers different stages of the stock research workflow. In this app, we use two key tool functions:

1. Web Search Tool — For general queries like company overview, financial trends, and peer benchmarking.
2. Stock Market Tool — For structured stock market data such as price snapshots, ratios, volumes, and categorized news.

These are defined in the tools.py file and initialized using the Dappier Python SDK.

from dappier import Dappier

client = Dappier()

def real_time_web_search(query: str) -> str:
    """
    Perform a real-time web search. Use this for general queries that do not include a specific stock ticker.
    """
    try:
        return client.search_real_time_data_string(
            query=query,
            ai_model_id="am_01j06ytn18ejftedz6dyhz2b15"
        )
    except Exception as e:
        return f"Error: {str(e)}"

def stock_market_data_search(query: str) -> str:
    """
    Fetch real-time stock market data. Use this tool only when querying with a stock ticker symbol.
    """
    try:
        return client.search_real_time_data_string(
            query=query,
            ai_model_id="am_01j749h8pbf7ns8r1bq9s2evrh"
        )
    except Exception as e:
        return f"Error: {str(e)}"

🧠 These tools power the agents in different stages of the pipeline based on the query type — general vs. ticker-specific. All data comes from Dappier’s trusted and rights-cleared data sources, ensuring accuracy and compliance.

🏷️ Ticker Resolution Agent

The first step in the stock research pipeline is to resolve the stock ticker symbol from a user-provided company name. This ensures downstream agents receive a valid ticker for accurate data retrieval.

We define a lightweight LLM agent using Google ADK’s LlmAgent, powered by Gemini, and backed by Dappier’s real-time web search tool.

from google.adk.agents import LlmAgent
from datetime import datetime
from .tools import real_time_web_search

GEMINI_MODEL = "gemini-2.0-flash"
timestamp = datetime.now().strftime("%Y-%m-%d %H:%M:%S")

# --- Initial Agent to Resolve Ticker ---
ticker_resolution_agent = LlmAgent(
    name="TickerResolutionAgent",
    model=GEMINI_MODEL,
    instruction=f"""
As of {timestamp}, take a user-provided company name and use real-time web search to resolve its stock ticker symbol.
Return only the stock ticker symbol in uppercase.
""",
    description="Resolves stock ticker symbol from company name.",
    tools=[real_time_web_search],
    output_key="ticker_symbol"
)

🎯 This agent ensures the entire pipeline starts with an accurate stock symbol, derived from the latest web data. Dappier is used here to ensure up-to-date resolution, especially for lesser-known or recently listed companies.

Perfect — we’ll now begin documenting the individual agents, one at a time, starting with the Ticker Resolution Agent.

🏷️ Ticker Resolution Agent

The first step in the stock research pipeline is to resolve the stock ticker symbol from a user-provided company name. This ensures downstream agents receive a valid ticker for accurate data retrieval.

We define a lightweight LLM agent using Google ADK’s LlmAgent, powered by Gemini, and backed by Dappier’s real-time web search tool.

from google.adk.agents import LlmAgent
from datetime import datetime
from .tools import real_time_web_search

GEMINI_MODEL = "gemini-2.0-flash"
timestamp = datetime.now().strftime("%Y-%m-%d %H:%M:%S")

# --- Initial Agent to Resolve Ticker ---
ticker_resolution_agent = LlmAgent(
    name="TickerResolutionAgent",
    model=GEMINI_MODEL,
    instruction=f"""
As of {timestamp}, take a user-provided company name and use real-time web search to resolve its stock ticker symbol.
Return only the stock ticker symbol in uppercase.
""",
    description="Resolves stock ticker symbol from company name.",
    tools=[real_time_web_search],
    output_key="ticker_symbol"
)

🎯 This agent ensures the entire pipeline starts with an accurate stock symbol, derived from the latest web data. Dappier is used here to ensure up-to-date resolution, especially for lesser-known or recently listed companies.

💰 Financial Performance Agent

After gathering company basics, this agent dives into the company’s recent financial performance using real-time search.

It retrieves financial indicators such as:

• Revenue (TTM)
• Net Income (TTM)
• YoY growth
• Gross margin
• Key financial trends or earnings commentary

financials_agent = LlmAgent(
    name="FinancialsPerformanceAgent",
    model=GEMINI_MODEL,
    instruction=f"""
As of "{timestamp}", use real-time web search with the timestamp to extract financial performance data for {{ticker_symbol}},
including Revenue (TTM), Net Income (TTM), YoY revenue growth, gross margin, and recent quarterly trends.
Include any earnings trends or management commentary.
""",
    description="Extracts financial metrics using real-time web search.",
    tools=[real_time_web_search],
    output_key="financials_summary"
)

🧮 Competitive Benchmarking Agent

To evaluate a company’s standing in its industry, this agent identifies and compares 3–5 peer companies using real-time web search.

It focuses on benchmarking key metrics:

• P/E ratio
• Revenue
• Stock Price
• Market Cap

It also highlights whether the target company outperforms or underperforms against its peers.

benchmarking_agent = LlmAgent(
    name="CompetitiveBenchmarkingAgent",
    model=GEMINI_MODEL,
    instruction=f"""
As of {timestamp}, identify 3-5 peer companies in the same sector as {{ticker_symbol}} using real-time web search.
Extract and compare metrics: P/E ratio, revenue, stock price, market cap.
Highlight where {{ticker_symbol}} outperforms or underperforms.
""",
    description="Performs competitive benchmarking using real-time web search.",
    tools=[real_time_web_search],
    output_key="competitive_benchmarking"
)

📰 Stock News & Sentiment Agent

Fetches categorized real-time financial news for the given ticker.

news_agent = LlmAgent(
    name="StockNewsAndSentimentAgent",
    model=GEMINI_MODEL,
    instruction=f"""
As of {timestamp}, fetch real-time financial news
for "{{ticker_symbol}}". Categorize by: Earnings, Analyst Ratings, Market Moves, Partnerships, Legal/Regulatory.
""",
    description="Fetches categorized stock news using stock_market_data_search.",
    tools=[stock_market_data_search],
    output_key="categorized_news"
)

🤖 Parallel Research Agents

Run multiple agents concurrently to improve performance and modularity.

Web Research Agent Group

parallel_web_research_agent = ParallelAgent(
    name="WebResearchAgentGroup",
    sub_agents=[company_overview_agent, financials_agent, benchmarking_agent],
    description="Gathers structured company data in parallel."
)

Stock Insights Agent Group

parallel_stock_insights_agent = ParallelAgent(
    name="StockInsightsAgentGroup",
    sub_agents=[stock_snapshot_agent, news_agent],
    description="Gathers real-time stock insights in parallel."
)

📝 Investment Report Generator Agent

Synthesizes all outputs into a single markdown-formatted investment report.

report_generator_agent = LlmAgent(
    name="InvestmentReportGenerator",
    model=GEMINI_MODEL,
    instruction=f"""
As of {timestamp}, compile a comprehensive investment report for **{{stock_ticker}}**, formatted as markdown. Synthesize the outputs of all tasks: company overview, financial performance, competitive benchmarking, real-time stock snapshot, and categorized financial news.

The report must include the following structured sections:

1. **Quick Summary**  
2. **Company Profile Table**  
3. **Financial Performance Table**  
4. **Competitive Benchmarking Table**  
5. **Real-Time Stock Snapshot**  
6. **Categorized Financial News**  
7. **Insight Section**  

All the related information is below:

{{company_overview}}

{{financials_summary}}

{{competitive_benchmarking}}

{{stock_snapshot}}

{{categorized_news}}

Output only the final markdown report.
""",
    description="Generates a full investment report from aggregated data.",
    output_key="final_markdown_report"
)

🔁 Sequential Agent Pipeline

Defines the full multi-agent flow: resolves ticker → fetches data → generates report.

sequential_pipeline_agent = SequentialAgent(
    name="StockMarketResearchPipeline",
    sub_agents=[
        ticker_resolution_agent,
        parallel_web_research_agent,
        parallel_stock_insights_agent,
        report_generator_agent
    ],
    description="Orchestrates multi-agent flow: resolves ticker, gathers data, and generates report."
)

# Entry point
root_agent = sequential_pipeline_agent

💻 Running the Agent

This app is fully interactive — you don’t need to write any code to run it.

Just open the Replit app and use the built-in chat interface to enter a company name (e.g., "Apple" or "Tesla"). The agent pipeline will:

1. Resolve the stock ticker.
2. Fetch real-time data and financial insights.
3. Generate a full investment report in markdown format.

💬 The chat interface will display the markdown report directly in the console or browser output pane.

🌟 Highlights

This app has guided you through building and running a stock market research agent using Google ADK and Dappier. By combining real-time financial data, multi-agent workflows, and markdown generation, you’ve created a complete pipeline that transforms natural language input into a structured investment report.

Key tools utilized in this app include:

• Google ADK: A flexible framework that enables sequential and parallel agent orchestration, built around modular LLM-based agents for complex task automation.
• Dappier: A platform connecting LLMs to real-time, rights-cleared data across domains like finance, news, and web search. It delivers enriched, prompt-ready insights, empowering agents with verified and up-to-date information.
• Gemini Models: LLMs used to reason over financial data, extract metrics, benchmark competitors, and synthesize final markdown content.
• Replit: An interactive development and execution environment that makes it easy to deploy, test, and interact with the pipeline via chat interface.

This app can be adapted and expanded to support various other financial workflows such as:

• Portfolio monitoring
• Real-time earnings tracking
• Sector-specific investment dashboards
• Automated newsletter generation

It serves as a practical template for integrating LLMs and live data APIs into real-world financial research tools.