Reasoning Finance Agent

ReasoningTools and WebSearch for step-by-step financial analysis on Slack

Part of the Slack interface examples. Follow the setup guide.

The source example below uses claude-sonnet-4-20250514, which Anthropic retired. Before running it, replace that model ID with claude-sonnet-4-6 (or another available compatible Claude model).

Code

reasoning_agent.py
from agno.agent import Agent
from agno.db.sqlite import SqliteDb
from agno.models.anthropic import Claude
from agno.os.app import AgentOS
from agno.os.interfaces.slack import Slack
from agno.tools.reasoning import ReasoningTools
from agno.tools.websearch import WebSearchTools

agent_db = SqliteDb(session_table="agent_sessions", db_file="tmp/persistent_memory.db")

reasoning_finance_agent = Agent(
    name="Reasoning Finance Agent",
    model=Claude(id="claude-sonnet-4-20250514"),
    db=agent_db,
    tools=[
        ReasoningTools(add_instructions=True),
        WebSearchTools(),
    ],
    instructions="Use tables to display data. When you use thinking tools, keep the thinking brief.",
    add_history_to_context=True,
    num_history_runs=3,
    add_datetime_to_context=True,
    markdown=True,
)

# Setup our AgentOS app
agent_os = AgentOS(
    agents=[reasoning_finance_agent],
    interfaces=[Slack(agent=reasoning_finance_agent)],
)
app = agent_os.get_app()


if __name__ == "__main__":
    agent_os.serve(app="reasoning_agent:app", reload=True)

Usage

Set up your virtual environment

uv venv --python 3.12
source .venv/bin/activate

Set Environment Variables

export SLACK_TOKEN=***
export SLACK_SIGNING_SECRET=***
export ANTHROPIC_API_KEY=***

Install Dependencies

uv pip install 'agno[os,slack]' anthropic ddgs

Run Example

python reasoning_agent.py

Key Features

  • Chain-of-Thought Reasoning: ReasoningTools enables structured step-by-step analysis
  • Web Search: Searches the web for current information via WebSearchTools
  • Persistent Sessions: SQLite database for conversation history across restarts