Sales Pipeline Forecaster
Read a deals spreadsheet, calculate weighted pipeline by stage, and forecast revenue.
"""
Sales Pipeline Forecaster
=========================
Read a deals spreadsheet, calculate weighted pipeline by stage, and forecast revenue.
Setup:
1. Create a Google Sheet with columns: Deal Name, Company, Amount, Stage, Close Date, Probability
2. Set SALES_PIPELINE_SHEET_ID env var to your spreadsheet ID
3. Set Google OAuth credentials (GOOGLE_CLIENT_ID, GOOGLE_CLIENT_SECRET)
Example Sheet Format:
| Deal Name | Company | Amount | Stage | Close Date | Probability |
|--------------|-----------|---------|--------------|------------|-------------|
| Enterprise | Acme Corp | 50000 | Negotiation | 2026-07-15 | 70% |
| Starter Plan | Beta Inc | 5000 | Discovery | 2026-08-01 | 20% |
Run:
.venvs/demo/bin/python cookbook/91_tools/google/sheets/sales_pipeline.py
"""
from os import getenv
from agno.agent import Agent
from agno.models.openai import OpenAIResponses
from agno.tools.google.sheets import GoogleSheetsTools
from pydantic import BaseModel, Field
class PipelineForecast(BaseModel):
total_pipeline: float = Field(..., description="Sum of all deal amounts")
weighted_pipeline: float = Field(
..., description="Sum of amount * probability for each deal"
)
deals_by_stage: dict[str, int] = Field(..., description="Count of deals per stage")
top_deals: list[str] = Field(..., description="Top 3 deals by weighted value")
forecast_summary: str = Field(..., description="Brief forecast narrative")
agent = Agent(
name="Pipeline Forecaster",
model=OpenAIResponses(id="gpt-5.5"),
tools=[GoogleSheetsTools(read_sheet=True)],
instructions=[
"You analyze sales pipeline data and provide revenue forecasts.",
"Calculate weighted pipeline as: sum of (deal amount * probability) for each deal.",
"Group deals by stage and identify the highest-value opportunities.",
"Provide actionable insights about pipeline health.",
],
output_schema=PipelineForecast,
markdown=True,
)
if __name__ == "__main__":
sheet_id = getenv("SALES_PIPELINE_SHEET_ID")
if not sheet_id:
print("Set SALES_PIPELINE_SHEET_ID to your spreadsheet ID")
print(
"Example: export SALES_PIPELINE_SHEET_ID=1BxiMVs0XRA5nFMdKvBdBZjgmUUqptlbs74OgvE2upms"
)
exit(1)
agent.print_response(
f"Analyze the sales pipeline in spreadsheet {sheet_id} and provide a revenue forecast. "
"Calculate the weighted pipeline value and identify our top opportunities.",
stream=True,
)Add the actual tab and range to the prompt, for example Read 'Deals'!A1:F100 from the spreadsheet before calculating the forecast. read_sheet requires both the spreadsheet ID and a range, and the toolkit has no tab-discovery method. The output schema structures the model's calculations; it does not independently validate arithmetic.
Run the Example
Set up your virtual environment
uv venv --python 3.12
source .venv/bin/activateInstall dependencies
uv pip install -U agno google-api-python-client google-auth google-auth-httplib2 google-auth-oauthlib openaiConfigure Google OAuth
Enable the Google API used by this example, configure the consent screen, and create a Desktop OAuth client in your Cloud project. Export its GOOGLE_CLIENT_ID, GOOGLE_CLIENT_SECRET, and GOOGLE_PROJECT_ID, or place the downloaded client JSON at credentials.json in the directory where you run Python. Google's Python quickstart shows the Desktop client setup.
The first tool call opens a browser for consent and caches credentials in token.json. Use a separate token_path when switching accounts. Passing an Agno user_id does not switch the authenticated Google account.
Export environment variables
export OPENAI_API_KEY="your_openai_api_key_here"
export SALES_PIPELINE_SHEET_ID="your_sales_pipeline_sheet_id_here"Run the example
Save the code above as sales_pipeline.py, then run:
python sales_pipeline.pyFull source: cookbook/91_tools/google/sheets/sales_pipeline.py