Aegis-BI-Engine

<div align="center">

            ___       _______   _______  __   _______.
           /   \     |   ____| /  _____||  | /       |
          /  ^  \    |  |__   |  |  __  |  ||   (----`
     /  /_\  \   |   __|  |  | |_ | |  | \   \
        /  _____  \  |  |____ |  |__| | |  | .----)  |
       /__/     \__\ |_______| \______| |__| |_______/

        ██████╗ ██╗    ███████╗███╗   ██╗ ██████╗ ██╗███╗   ██╗███████╗
        ██╔══██╗██║    ██╔════╝████╗  ██║██╔════╝ ██║████╗  ██║██╔════╝
      ██████╔╝██║    █████╗  ██╔██╗ ██║██║  ███╗██║██╔██╗ ██║█████╗
      ██╔══██╗██║    ██╔══╝  ██║╚██╗██║██║   ██║██║██║╚██╗██║██╔══╝
        ██████╔╝██║    ███████╗██║ ╚████║╚██████╔╝██║██║ ╚████║███████╗
        ╚═════╝ ╚═╝    ╚══════╝╚═╝  ╚═══╝ ╚═════╝ ╚═╝╚═╝  ╚═══╝╚══════╝

AEGIS BI ENGINE

Autonomous Multi-Agent Intelligence Pipeline

From Raw Market Signal to Power BI-Ready Structured Data - Zero Human Latency

---

---

"Strategic question in. Production-grade structured intelligence out. Fully orchestrated by autonomous AI agents - zero manual intervention, zero latency."

</div>

---

<br/>

The Intelligence Preparation Crisis

Enterprise business intelligence is structurally broken at the preparation layer. Organizations hemorrhage 70-80% of their total analytics bandwidth on data gathering, source validation, unstructured-to-structured conversion, and schema normalization - before a single visualization ever renders. This preparation overhead transforms BI from a proactive competitive weapon into a perpetually lagging, reactive output.

The dysfunction compounds across three structural failure modes:

Research Fragmentation - Analysts manually aggregate intelligence from heterogeneous, disconnected sources: market reports, competitor filings, industry databases, regulatory repositories. Each analyst operates with idiosyncratic sourcing methodology, producing non-reproducible, inconsistency-riddled outputs where data quality is analyst-dependent and structurally unpredictable.

Unstructured-to-Structured Conversion Tax - Raw research artifacts (PDFs, articles, briefs) demand exhaustive manual transformation into tabular formats suitable for BI ingestion. This labor-intensive restructuring introduces transcription errors, format drift, and multi-day delays. Skilled analyst cognition is consumed by mechanical data manipulation rather than strategic interpretation.

Dashboard Integration Friction - Post-structuring, data still requires iterative cleansing, schema normalization, and type alignment before Power BI accepts it cleanly. Encoding anomalies and version mismatches generate compounding iteration cycles that further extend time-to-insight latency.

AEGIS eliminates this entire preparation overhead. Strategic question to dashboard-ready structured data in minutes. Zero manual research. Zero data wrangling. Zero format conversion. Pure autonomous intelligence at machine velocity.

<br/>

---

<br/>

What AEGIS Delivers

  ┌─────────────────────────────────────────────────────────────────────────┐
  │                                                                         │
  │   YOU PROVIDE            AEGIS EXECUTES              YOU RECEIVE        │
  │   ──────────             ──────────────              ───────────        │
  │                          Autonomous multi-                              │
  │   One natural   ──────►  agent intelligence  ──────► Structured CSV     │
  │   language               pipeline                    Power BI loads     │
  │   topic                  (zero human                 instantly          │
  │                          involvement)                                   │
  │                                                                         │
  └─────────────────────────────────────────────────────────────────────────┘

  Input  :  Any natural language market or research topic - no structure required
  Output :  Clean, normalized, schema-optimized CSV - directly importable into Power BI
  Human touches required  :  One  (initial topic input)
  Execution time          :  Minutes
  Manual data wrangling   :  None

<br/>

---

<br/>

System Architecture

  ╔═══════════════════════════════════════════════════════════════════════╗
  ║                        AEGIS BI ENGINE                                ║
  ╠═══════════════════════════════════════════════════════════════════════╣
  ║                                                                       ║
  ║   ┌───────────────────────────────────────────────────────────────┐   ║
  ║   │                   ORCHESTRATION LAYER                         │   ║
  ║   │                   CrewAI Framework                            │   ║
  ║   │  Task Delegation · Execution Sequencing · Error Recovery      │   ║
  ║   └────────────────────────┬──────────────────────────────────────┘   ║
  ║                            │                                          ║
  ║           ┌────────────────┴────────────────┐                         ║
  ║           │                                 │                         ║
  ║   ┌───────┴────────────┐         ┌──────────┴─────────────┐           ║
  ║   │  RESEARCHER AGENT  │         │    ANALYST AGENT       │           ║
  ║   │                    │         │                        │           ║
  ║   │ Autonomous invest. │ ──────► │ Schema architecture    │           ║
  ║   │ Multi-src synthesis│         │ Pattern extraction     │           ║
  ║   │ Credibility valid. │         │ Data normalization     │           ║
  ║   │ Strategic insights │         │ CSV engineering        │           ║
  ║   │ Self-correct logic │         │ Quality validation     │           ║
  ║   └───────┬────────────┘         └──────────┬─────────────┘           ║
  ║           │                                 │                         ║
  ║           └────────────────┬────────────────┘                         ║
  ║                            │                                          ║
  ║              LLM: Groq LLaMA 3.3-70B-Versatile                        ║
  ║              Sub-second inference · 500-800 tokens/sec                ║
  ║                            │                                          ║
  ║   ┌────────────────────────┴──────────────────────────────────────┐   ║
  ║   │                      OUTPUT LAYER                             │   ║
  ║   │                                                               │   ║
  ║   │  intelligence.csv ──────────────────► Power BI Direct Load    │   ║
  ║   │  insights report  ──────────────────► Decision Support        │   ║
  ║   └───────────────────────────────────────────────────────────────┘   ║
  ║                                                                       ║
  ╚═══════════════════════════════════════════════════════════════════════╝

<br/>

Autonomous Pipeline Execution Flow

  Topic Input
  (natural language)
        │
        ▼
  ┌─────────────────────────────────────┐
  │         CrewAI Orchestrator         │
  │  Task delegation                    │
  │  Sequential execution control       │
  │  Error recovery and retry logic     │
  └─────────────────┬───────────────────┘
                    │
                    ▼
  ┌─────────────────────────────────────┐   ┌─────────────────────────┐
  │    PHASE 1 — RESEARCHER AGENT       │   │   Groq LPU Backend      │
  │                                     │◄──│                         │
  │  1  Topic dimension analysis        │   │  LLaMA 3.3-70B          │
  │  2  Investigation strategy design   │   │  Versatile              │
  │  3  Multi-source intelligence scan  │   │  500-800 tokens/sec     │
  │  4  Cross-source validation         │   │  Sub-second inference   │
  │  5  Strategic synthesis             │   └─────────────────────────┘
  └─────────────────┬───────────────────┘
                    │
                    │  Structured research brief
                    ▼
  ┌─────────────────────────────────────┐   ┌─────────────────────────┐
  │    PHASE 2 — ANALYST AGENT          │   │   Groq LPU Backend      │
  │                                     │◄──│                         │
  │  1  Research brief ingestion        │   │  LLaMA 3.3-70B          │
  │  2  Optimal schema architecture     │   │  Versatile              │
  │  3  Tabular data engineering        │   │  500-800 tokens/sec     │
  │  4  Normalization and encoding      │   │  Sub-second inference   │
  │  5  Integrity validation            │   └─────────────────────────┘
  └─────────────────┬───────────────────┘
                    │
                    ▼
  ┌─────────────────────────────────────┐
  │        OUTPUT GENERATION            │
  │                                     │
  │  market_intelligence.csv            │
  │  Insights summary report            │
  │  Power BI import-ready              │
  └─────────────────────────────────────┘

<br/>

Why Groq Accelerates This Architecture

AEGIS leverages Groq's LPU (Language Processing Unit) inference infrastructure running LLaMA 3.3-70B-Versatile - delivering sub-second token generation that makes the multi-agent pipeline feel instantaneous. Where standard cloud LLM backends stall on inference latency and disrupt agentic flow, AEGIS executes research and analysis phases at machine velocity while maintaining enterprise-grade reasoning depth.

  Inference Velocity Comparison
  ──────────────────────────────────────────────────────────────────

  Groq LPU       ████████████████████████████████  500-800 tokens/sec
  Standard Cloud ██████                             50-100 tokens/sec
  Local Models   ██                                 15-40  tokens/sec

  AEGIS runs on Groq for maximum autonomous pipeline throughput

<br/>

---

<br/>

Agent Specification

Researcher Agent - Autonomous Intelligence Acquisition

The Researcher Agent operates as a fully autonomous investigative intelligence unit. It receives only a topic specification and independently determines every dimension of research strategy and execution - no step-by-step prompting, no guided paths, no human supervision between initiation and output.

  RESEARCHER AGENT — CAPABILITY ARCHITECTURE
  ────────────────────────────────────────────────────────────────────────

  INPUT            INTERNAL EXECUTION                        OUTPUT
  ─────            ──────────────────                        ──────

  Topic     ────►  Topic dimension mapping           ────►   Structured
  (natural         Source category identification            research
   language)       Parallel data acquisition                 intelligence
                   Credibility weighting                     brief
                   Cross-source validation
                   Contradiction resolution
                   Strategic implication synthesis

Distinguishing characteristics that separate this agent from naive retrieval systems:

• Independently identifies optimal source categories per topic domain
• Self-corrects when initial sources prove insufficient or contradictory
• Generates strategic implications and insights - not mere information aggregation
• Applies dynamic credibility weighting across academic, industry, and market sources
• Operates at full autonomy - zero intermediate intervention required

<br/>

Analyst Agent - Structured Data Engineering

The Analyst Agent transforms unstructured research intelligence into production-grade tabular datasets precision-engineered for business intelligence tooling - autonomously architecting schemas that require zero post-processing before Power BI ingestion.

  ANALYST AGENT — DATA ENGINEERING PIPELINE
  ────────────────────────────────────────────────────────────────────────

  Research Brief    Schema Engineering                     CSV Output
  ──────────────    ─────────────────                      ──────────

  Unstructured ──►  Dimension identification        ────►  Analyst-friendly
  intelligence      Column type architecture                naming conventions
                    Naming convention design                Clean encoding
                    Normalization protocols                 BI-optimized schema
                    Completeness verification               Dashboard-ready data

Schema engineering principles the Analyst Agent enforces autonomously:

• Descriptive column naming: Revenue_USD_Millions not Rev_M
• Data type precision aligned with Power BI visualization requirements
• ISO 8601 date formatting throughout every temporal column
• Standardized categorical taxonomy with consistent capitalization
• Calculated derived metrics included alongside source values

<br/>

---

<br/>

Technology Stack

  ┌──────────────────────────────────────────────────────────────────────┐
  │                         TECHNOLOGY STACK                             │
  │                                                                      │
  │  ┌─────────────────┐  ┌─────────────────┐  ┌─────────────────────┐   │
  │  │    CrewAI       │  │   Groq LPU      │  │  LLaMA 3.3-70B      │   │
  │  │                 │  │   Cloud         │  │  Versatile          │   │
  │  │  Multi-agent    │  │                 │  │                     │   │
  │  │  orchestration  │  │  Sub-second     │  │  70B parameter      │   │
  │  │  Task routing   │  │  inference      │  │  reasoning model    │   │
  │  │  Error recovery │  │  500-800 t/s    │  │  Domain-agnostic    │   │
  │  └─────────────────┘  └─────────────────┘  └─────────────────────┘   │
  │                                                                      │
  │  ┌─────────────────┐  ┌─────────────────┐  ┌─────────────────────┐   │
  │  │    FastAPI      │  │    Pandas       │  │     Power BI        │   │
  │  │                 │  │                 │  │                     │   │
  │  │  REST endpoint  │  │  DataFrame      │  │  Direct CSV load    │   │
  │  │  Async support  │  │  engineering    │  │  Zero transform.    │   │
  │  │  API interface  │  │  Validation     │  │  Instant dashboards │   │
  │  └─────────────────┘  └─────────────────┘  └─────────────────────┘   │
  └──────────────────────────────────────────────────────────────────────┘

| Component | Technology | Function | |----------------------|--------------------------|------------------------------------------------------------| | Agent Orchestration | CrewAI | Multi-agent coordination and autonomous task delegation | | Language Model | LLaMA 3.3-70B-Versatile | Agent cognition, reasoning, and autonomous decision-making | | Inference Engine | Groq LPU Cloud | Sub-second token generation for pipeline velocity | | API Layer | FastAPI | REST interface for external workflow integration | | Data Engineering | Pandas | DataFrame manipulation, validation, and CSV generation | | Configuration | python-dotenv | Secure API key and environment variable management |

<br/>

---

<br/>

Quick Start

Prerequisites

• Python 3.11 or higher
• Groq API key (free tier available at console.groq.com)
• Power BI Desktop for dashboard visualization

<br/>

Installation

Step 1 - Clone the repository

git clone https://github.com/Adhithyan006/Aegis-BI-Engine.git
cd Aegis-BI-Engine

Step 2 - Create and activate virtual environment

# Windows PowerShell
python -m venv venv
venv\Scripts\Activate.ps1

# Windows Command Prompt
python -m venv venv
venv\Scripts\activate.bat

# macOS and Linux
python -m venv venv
source venv/bin/activate

Step 3 - Install dependencies

pip install -r requirements.txt

Step 4 - Configure environment

Create a .env file in the project root:

GROQ_API_KEY=your_groq_api_key_here

Step 5 - Execute the engine

python main.py

<br/>

---

<br/>

Usage

Direct Pipeline Execution

# main.py - configure your research topic
topic = "Global generative AI infrastructure market competitive dynamics 2025"

crew.kickoff(inputs={"topic": topic})

python main.py

The engine autonomously executes all pipeline stages and delivers structured CSV to the project directory. No intermediate configuration or supervision required.

<br/>

Topic Specification Examples

  Focused market     :  "Electric vehicle battery market in Southeast Asia"
  Competitive intel  :  "Enterprise cloud infrastructure AWS Azure GCP dynamics"
  Technology scan    :  "Large language model deployment frameworks - adoption and maturity"
  Strategic entry    :  "Renewable energy storage technologies - cost trajectory and scale"
  Sector analysis    :  "B2B SaaS vertical expansion strategies in emerging markets"

No schema specification, source guidance, or format instruction required. The agent system autonomously determines all execution parameters from natural language input alone.

<br/>

Live Console Output During Execution

  [AEGIS] Initializing CrewAI orchestration...
  [AEGIS] Deploying Researcher Agent on topic: [your topic]

  [Researcher] Analyzing topic dimensions...
  [Researcher] Formulating investigation strategy...
  [Researcher] Executing multi-source intelligence acquisition...
  [Researcher] Cross-validating findings across 6 sources...
  [Researcher] Synthesizing strategic intelligence...
  [Researcher] Research phase complete

  [Analyst]    Ingesting research intelligence...
  [Analyst]    Architecting optimal data schema...
  [Analyst]    Engineering tabular structure: 18 columns x 47 rows...
  [Analyst]    Executing normalization and encoding protocols...
  [Analyst]    Validating data integrity and completeness...
  [Analyst]    CSV generation complete

  [AEGIS] Output : market_intelligence.csv
  [AEGIS] Total execution time : 4 minutes 23 seconds

<br/>

---

<br/>

Output Specification

CSV Schema Design

AEGIS outputs clean, normalized CSV with analyst-precision schema architecture:

  Market_Segment   Region           Year   Market_Size_USD_B   YoY_Growth_Pct   Key_Players            Maturity_Stage
  ─────────────────────────────────────────────────────────────────────────────────────────────────────────────────────
  Battery_EV       Southeast_Asia   2024   12.4                31.5             BYD, Tesla, VinFast    Growth
  Hybrid_EV        Southeast_Asia   2024    6.8                18.2             Toyota, Honda          Mature
  Hydrogen_FC      Southeast_Asia   2024    1.2                47.3             Hyundai, Toyota        Emerging

Schema characteristics the Analyst Agent enforces autonomously:

• Descriptive column names requiring no external data dictionary
• Float precision appropriate per metric type
• ISO 8601 date and period formatting throughout
• Standardized categorical capitalization and consistent taxonomy
• No missing values in critical analytical columns
• Derived metrics included alongside absolute values

<br/>

Power BI Import Workflow

  Power BI Desktop
        │
        ▼
  Home  ──►  Get Data  ──►  Text/CSV
        │
        ▼
  Navigate to Aegis-BI-Engine project directory
  Select the generated .csv output file
        │
        ▼
  Power Query preview renders instantly
  Data is clean - zero transformation steps required
        │
        ▼
  Click Load
        │
        ▼
  Full structured dataset available for visualization

Total manual intervention: file selection only. No schema modification, type casting, or data cleansing required before visualization begins.

On dashboard automation: AEGIS owns the entire intelligence pipeline through structured data delivery. Dashboard construction in Power BI Desktop remains a manual creative process - visual selection, layout architecture, and interactive filter design require human analytical judgment. Full end-to-end automation from data to published dashboard requires Power BI Premium licensing and the Power BI REST API, which Microsoft restricts to enterprise licensing tiers and does not expose on standard individual accounts.

<br/>

---

<br/>

Performance Profile

Time-to-Intelligence Comparison

  TRADITIONAL ANALYST WORKFLOW
  ──────────────────────────────────────────────────────────────────────

  Source identification      ████████░░░░░░░░░░░░░   2-4  hours
  Data acquisition           ████████████░░░░░░░░░   3-5  hours
  Unstructured-to-structured ████████████████░░░░░   4-6  hours
  Quality validation         ████████░░░░░░░░░░░░░   2-4  hours
  Schema formatting          ██████░░░░░░░░░░░░░░░   1-3  hours
  ──────────────────────────────────────────────────────────────────────
  TOTAL                                              12-22 hours


  AEGIS AUTONOMOUS PIPELINE
  ──────────────────────────────────────────────────────────────────────

  Agent initialization       █░░░░░░░░░░░░░░░░░░░░   10  seconds
  Research phase             ████░░░░░░░░░░░░░░░░░   3-8 minutes
  Analysis and CSV output    ██░░░░░░░░░░░░░░░░░░░   1-3 minutes
  ──────────────────────────────────────────────────────────────────────
  TOTAL                                              5-12 minutes

  TIME REDUCTION : 95-98%

Typical Output Characteristics

  Output volume       :  15-30 columns,  30-100 rows per execution
  Schema suitability  :  80% require zero modification before Power BI import
  Data completeness   :  95%+ minimum across critical analytical columns
  Research depth      :  Multi-source synthesis, 5-10 sources per execution

<br/>

---

<br/>

Demo

<div align="center">

AEGIS BI Engine - Live Execution

Watch autonomous agents execute the complete research-to-structured-data pipeline in real time

</div>

Demonstration scope:

• Natural language topic submission and autonomous agent initialization
• Researcher Agent live execution with real-time multi-source intelligence acquisition
• Agent deliberation and autonomous strategy decision-making visible in console output
• Analyst Agent schema architecture and structured data engineering in action
• CSV output generation and Power BI direct import workflow walkthrough
• End-to-end timeline from strategic question to dashboard-ready intelligence

Watch the full execution walkthrough:

Copy link and open in browser: https://drive.google.com/file/d/1OFE-7rCSHXr7AXO6XoiQJDa2WvEPygXg/view

<br/>

---

<br/>

Repository Structure

  Aegis-BI-Engine/
  │
  ├── app.py                      Core agent orchestration engine
  │   ├── Agent definitions       Researcher and Analyst specializations
  │   ├── Task specifications     Research and Analysis task configurations
  │   ├── Crew initialization     CrewAI pipeline assembly and launch
  │   ├── Output management       CSV export and report formatting
  │   └── Error handling          Recovery and structured logging
  │
  ├── main.py                     Execution entry point and CLI
  │   ├── Topic input handling    Natural language query intake
  │   ├── Crew execution          Pipeline trigger and coordination
  │   └── Result delivery         Output display and export management
  │
  ├── requirements.txt            Python dependency manifest
  │   ├── crewai                  Multi-agent orchestration framework
  │   ├── groq                    Groq LPU inference client
  │   ├── pandas                  Data engineering and CSV generation
  │   └── python-dotenv           Environment configuration management
  │
  ├── .env                        Environment configuration (gitignored)
  │   ├── GROQ_API_KEY            Groq inference API credential
  │   └── [Optional params]       Logging levels and model overrides
  │
  ├── .gitignore                  Version control exclusions
  │   ├── .env                    API key protection
  │   ├── venv/                   Virtual environment directory
  │   └── *.csv                   Generated intelligence outputs
  │
  ├── README.md                   This documentation
  │
  └── [Generated CSV Outputs]     Agent-produced intelligence datasets
      ├── Timestamped filenames
      ├── Normalized schemas
      └── Power BI-ready format

<br/>

---

<br/>

Use Cases

Competitive Intelligence Operations

Periodic execution on competitor topics generates longitudinal intelligence datasets for trend analysis. Track competitor capability trajectories, pricing evolution, and market positioning drift over time. Build dashboards that surface competitive threats without dedicating analyst hours to research preparation per cycle.

Strategic Market Entry Assessment

Research competitive landscapes, regulatory environments, customer segmentation dynamics, and technology requirements for new market evaluation. Generate structured comparison matrices across geographies and product categories. Enable rapid scenario analysis through dashboard-based exploration.

Technology Investment Evaluation

Assess emerging technology maturity curves, vendor ecosystem health, adoption trajectories, and cost-benefit projections. Structure findings into comparison matrices for investment committee or technical review board consumption.

Regulatory Intelligence Mapping

Research compliance requirements across jurisdictions, map policy evolution timelines, and track regulatory environment shifts. Generate structured datasets of obligations and impact dimensions for strategy and compliance teams.

Executive Intelligence Briefings

Convert standing market monitoring topics into recurring autonomous intelligence runs. Deliver structured, dashboard-ready briefing data on demand - without allocating analyst bandwidth to preparation overhead.

<br/>

---

<br/>

Advanced Configuration

Model Parameters

AEGIS is production-configured on Groq LLaMA 3.3-70B-Versatile - the optimal configuration for deep multi-agent research workflows at machine inference velocity:

# app.py — production configuration
llm = LLM(
    model="groq/llama-3.3-70b-versatile",
    api_key=os.getenv("GROQ_API_KEY"),
)

Agent Behavior Customization

Research posture and output characteristics are tunable through agent configuration in app.py:

# Deepen quantitative rigor
researcher.backstory += " Prioritize statistical evidence and numerical data above qualitative claims."

# Narrow temporal scope
researcher.goal += " Focus exclusively on developments from the past 6 months."

# Optimize schema orientation
analyst.goal += " Design schemas optimized for time-series trend analysis."

Execution Verbosity Control

VERBOSE=True     # Full agent deliberation visible in console
VERBOSE=False    # Minimal output - final results only

<br/>

---

<br/>

Roadmap

Near-Term

• Domain-specialized agent configurations for Financial Intelligence, Healthcare, and Deep Technology verticals
• Scheduled autonomous execution for recurring intelligence monitoring cadences
• Multi-topic parallel processing with concurrent agent crew deployment

Medium-Term

• Power BI REST API integration for organizations operating on Premium licensing
• Incremental dataset update capability for longitudinal topic tracking
• Dedicated data quality validation agent as a discrete pipeline stage

Long-Term

• End-to-end autonomous BI delivery from natural language query to published interactive dashboard
• Conversational analytics interface for natural language dataset interrogation
• Persistent knowledge graph accumulation and cross-execution intelligence continuity

<br/>

---

<br/>

Contributing

Contributions advancing autonomous intelligence infrastructure are welcomed.

Highest-leverage contribution domains:

• Domain-expert agent specializations for vertical industry contexts
• Schema standardization protocols enabling cross-execution alignment
• Power BI Premium REST API integration layer
• Output quality metrics and automated validation frameworks
• Use case documentation and domain-specific deployment guides

git clone https://github.com/your-handle/Aegis-BI-Engine.git
git checkout -b feature/your-capability-name
git commit -m "feat: descriptive capability summary"
git push origin feature/your-capability-name

Open a Pull Request with a complete end-to-end execution output sample attached.

<br/>

---

<br/>

License

MIT License - Full terms in repository LICENSE file.

Open source to accelerate enterprise adoption of autonomous intelligence pipelines. Free for commercial and academic use with attribution.

<br/>

---

<br/> <div align="center">

  ╔══════════════════════════════════════════════════════════════════╗
  ║                                                                  ║
  ║   Autonomous Intelligence.  Structured Precision.                ║
  ║   Zero Preparation Overhead.                                     ║
  ║                                                                  ║
  ║   From strategic question to Power BI-ready data                 ║
  ║   in minutes, not days.                                          ║
  ║                                                                  ║
  ╚══════════════════════════════════════════════════════════════════╝

Built by Adhithyan - GitHub: @Adhithyan006

Star this repository to help engineers worldwide discover autonomous BI infrastructure

</div>