OmniQuery User Guide

Intelligent Data Analysis Across All Your Sources

Powered by Google Agent Development Kit

How OmniQuery Works

1. Upload Your Data

PDFs, Word docs, Excel files, CSV data, or connect databases

2. Ask in Plain English

Natural language questions about your data and insights

3. Get Smart Insights

AI agents analyze and combine data from all sources automatically

Multi-Agent Intelligence

Document Agent

Analyzes PDFs, Word docs for insights and patterns

SQL Agent

Processes structured data from Excel, CSV, databases

Hybrid Agent

Combines insights from multiple data sources

Error Handler

Provides alternative analysis when needed

Upload Your Data Sources

Unstructured Data

PDF Reports & Documents
Word Documents (.doc, .docx)

Examples: Financial reports, meeting notes, policy documents, research papers, customer feedback

Structured Data

Excel Files (.xlsx)
CSV Data Files
Database Connections

Examples: Sales data, customer records, inventory, financial transactions, survey responses

Upload Steps

1

Select File Type

Choose "Documents" for PDFs/Word or "Structured Data" for Excel/CSV

2

Drag & Drop or Browse

Upload your files - multiple files supported

3

Add Metadata (Optional)

For structured data, add column descriptions for better analysis

4

Processing Complete

Files are automatically indexed and ready for queries

Ask Smart Questions

OmniQuery Interface

💬 Ask anything about your data:

Analytics Questions

• "What are the top 5 performing products this quarter?"

• "Show me revenue trends by region"

• "Identify outliers in our sales data"

• "What's our customer churn rate?"

Document Questions

• "What does the contract say about payment terms?"

• "Find key insights from customer feedback"

• "Summarize the Q4 financial report"

• "What are the main compliance requirements?"

Cross-Source Questions

• "Correlate sales data with customer satisfaction"

• "Compare budget vs actual spending from all sources"

• "How do market trends align with our performance?"

• "Find discrepancies between reports and data"

Insight Questions

• "What factors contribute to our best performance?"

• "Generate recommendations for improvement"

• "Predict next quarter's trends"

• "What should we focus on this month?"

Pro Tips for Better Results

  • • Be specific about time periods: "last quarter", "this year", "since January"
  • • Mention data sources when needed: "from Excel data", "according to reports"
  • • Ask follow-up questions to dive deeper into insights
  • • Use comparison words: "compare", "versus", "difference between"

Real Examples & Use Cases

Business Performance Analysis

Data Sources:

  • • Sales_Q4_2024.xlsx
  • • Financial_Report_Q4.pdf
  • • Customer_Feedback.docx
  • • CRM Database

Sample Queries:

  • • "Why did revenue drop in October?"
  • • "Which customers are most profitable?"
  • • "Compare Q4 goals vs actual results"
Expected Result:

Cross-source analysis showing revenue trends, customer sentiment correlation, and actionable recommendations

HR & Employee Analytics

Data Sources:

  • • Employee_Survey_2024.csv
  • • HR_Policies.pdf
  • • Performance_Reviews.xlsx
  • • Exit_Interviews.docx

Sample Queries:

  • • "What affects employee satisfaction most?"
  • • "Find patterns in employee turnover"
  • • "Compare policy changes with satisfaction scores"
Expected Result:

Insights on retention factors, policy effectiveness, and data-driven HR recommendations

Market Research & Strategy

Data Sources:

  • • Market_Research_2024.pdf
  • • Competitor_Analysis.xlsx
  • • Social_Media_Data.csv
  • • Industry_Report.docx

Sample Queries:

  • • "How do we compare to competitors?"
  • • "What market opportunities exist?"
  • • "Analyze social sentiment vs market position"
Expected Result:

Strategic insights combining market data, competitive analysis, and growth opportunities

Quick Start in 3 Steps

📁

Upload Files

Add your PDFs, Excel, Word docs

💬

Ask Questions

Type natural language queries

Get Insights

Receive intelligent analysis