Building intelligent systems that think, reason, and act
class PriteshDhandhukia:
def __init__(self):
self.name = "Pritesh Dhandhukia"
self.role = "AI Engineer & Solutions Architect"
self.location = "🌍 Building AI systems worldwide"
self.expertise = {
"agentic_ai": ["LangGraph", "CrewAI", "Multi-Agent Systems", "MCP"],
"aws_cloud": ["Bedrock", "SageMaker", "Textract", "Rekognition", "EMR"],
"ml_engineering": ["RAG", "Fine-tuning", "LLM Evaluation", "Knowledge Bases"],
"data_stack": ["ETL Pipelines", "Data Visualization", "Storage Solutions"]
}
self.currently_working_on = [
"🤖 Building production-ready agentic AI systems",
"🔗 Implementing Model Context Protocol (MCP) servers",
"📊 Evaluating LLMs with RAGAS framework",
"☁️ Architecting scalable AI solutions on AWS"
]
self.daily_drivers = ["Python", "TypeScript", "AWS CDK", "Docker"]
def say_hi(self):
print("Thanks for dropping by! Let's build something amazing together! 🚀")
me = PriteshDhandhukia()
me.say_hi()
Compare LangGraph, CrewAI & Custom Orchestration
A comprehensive side-by-side comparison of agentic AI frameworks using Model Context Protocol (MCP). Features working implementations of all three approaches with shared tools for fair comparison.
Tech: Python, TypeScript, LangGraph, CrewAI, MCP, Anthropic Claude
Highlights:
- 🏗️ Complete MCP server with 4 contract analysis tools
- 🟢 LangGraph state-based workflow implementation
- 🟣 CrewAI role-based multi-agent system
- 🟠 Custom orchestration from scratch
- 📊 Production-ready patterns and architecture diagrams
focus_areas = {
"learning": [
"Advanced agentic AI patterns",
"Distributed agent systems",
"Production LLM deployment",
"AWS AI/ML services"
],
"building": [
"MCP servers for various domains",
"Multi-agent orchestration frameworks",
"RAG evaluation tooling",
"AWS serverless AI solutions"
],
"contributing": [
"Open-source AI frameworks",
"MCP server examples",
"Documentation improvements",
"Community knowledge sharing"
]
}- 🔧 MCP Protocol - Building production MCP servers
- 🤖 Agentic AI - Comparing orchestration frameworks
- 📊 LLM Evaluation - RAGAS-based testing pipelines
- ☁️ AWS AI Stack - Bedrock, Textract, Rekognition integrations
- 🎓 Fine-tuning - Custom model training and evaluation
- 📈 Data Pipelines - Raw data to insights workflows
achievements = {
"open_source": "Built comprehensive MCP framework comparison",
"aws": "Architected multiple production AI solutions",
"ai_agents": "Implemented 3+ agent orchestration patterns",
"community": "Sharing knowledge through code and documentation",
"learning": "Continuously exploring cutting-edge AI technologies"
}"The future of AI is not just about smarter models—it's about systems that can reason, collaborate, and act with purpose."
I'm passionate about:
- 🤝 Building AI agents that work together, not just alone
- 🏗️ Creating reusable patterns and frameworks
- 📚 Sharing knowledge and helping others learn
- ⚡ Making AI systems production-ready, not just proof-of-concepts
- 🌍 Open-source collaboration and community building
Have an interesting project? Want to collaborate?
Let's build something amazing together!
fun_facts = [
"🤖 I build AI agents that actually work in production",
"☕ Coffee-driven code is my specialty",
"📊 I create architecture diagrams for fun (seriously!)",
"🎯 Currently mastering: Production-grade agentic AI systems",
"💭 Philosophy: 'Build it, ship it, iterate'"
]⭐ From prit-ctl - Building the future, one commit at a time