DEV Community

Parth Sarthi Sharma profile picture

Parth Sarthi Sharma

Staff Software Engnr working on AI platforms, agentic systems, and cloud-native architectures. I write about: • Distributed systems & system design • LangChain, LangGraph, and real-world AI agents

Location Melbourne, Australia Joined Joined on  Personal website https://www.linkedin.com/in/parthsarthi-sharma/

Pronouns

He/Him

Work

Lead Software Engineer

I Compared 7 AI Observability Platforms So You Don’t Have To (2026 Edition)

I Compared 7 AI Observability Platforms So You Don’t Have To (2026 Edition)

2
Comments 2
4 min read

Want to connect with Parth Sarthi Sharma?

Create an account to connect with Parth Sarthi Sharma. You can also sign in below to proceed if you already have an account.

Already have an account? Sign in
How Senior Engineers Use AI Without Burning Through Token Limits - Reduce AI Token Usage by 60–90%

How Senior Engineers Use AI Without Burning Through Token Limits - Reduce AI Token Usage by 60–90%

1
Comments
4 min read
Reflection vs Reflexion Agents: The Next Leap in Agentic AI

Reflection vs Reflexion Agents: The Next Leap in Agentic AI

1
Comments 1
3 min read
Prompt Engineering Is Not Enough: Enter Flow Engineering for Production LLM Systems

Prompt Engineering Is Not Enough: Enter Flow Engineering for Production LLM Systems

3
Comments 5
4 min read
Secrets Management for LLM Tools: Don’t Let Your OpenAI Keys End Up on GitHub 🚨

Secrets Management for LLM Tools: Don’t Let Your OpenAI Keys End Up on GitHub 🚨

1
Comments
3 min read
Observability in AI Systems

Observability in AI Systems

Comments
3 min read
Self-RAG vs Adaptive RAG vs Corrective RAG

Self-RAG vs Adaptive RAG vs Corrective RAG

Comments
3 min read
LangChain vs LangGraph vs Semantic Kernel vs Google AI ADK vs CrewAI

LangChain vs LangGraph vs Semantic Kernel vs Google AI ADK vs CrewAI

1
Comments
3 min read
Local RAG vs Cloud RAG: What Changes When You Leave the Demo

Local RAG vs Cloud RAG: What Changes When You Leave the Demo

Comments
3 min read
Prompt Routing & Context Engineering: Letting the System Decide What It Needs

Prompt Routing & Context Engineering: Letting the System Decide What It Needs

Comments
3 min read
Simple RAG vs Agentic RAG: What Problem Are You Actually Solving?

Simple RAG vs Agentic RAG: What Problem Are You Actually Solving?

Comments
2 min read
Chunking, Batching & Indexing: The Hidden Costs of RAG Systems

Chunking, Batching & Indexing: The Hidden Costs of RAG Systems

Comments
2 min read
Why “Lost in the Middle” Breaks Most RAG Systems

Why “Lost in the Middle” Breaks Most RAG Systems

Comments
2 min read
Loaders, Splitters & Embeddings — How Bad Chunking Breaks Even Perfect RAG Systems

Loaders, Splitters & Embeddings — How Bad Chunking Breaks Even Perfect RAG Systems

Comments
3 min read
How LLMs Actually “See” Context (Tokens, Chunks, Windows)

How LLMs Actually “See” Context (Tokens, Chunks, Windows)

Comments
3 min read
Vector Dimensions, Cosine Similarity, Dot Product — and Why Your Distance Metric Silently Ruins Relevance

Vector Dimensions, Cosine Similarity, Dot Product — and Why Your Distance Metric Silently Ruins Relevance

Comments
2 min read
Dense vs Sparse Vector Stores: Which One Should You Use — and When?

Dense vs Sparse Vector Stores: Which One Should You Use — and When?

Comments
2 min read
ReAct vs Tool Calling: Why Your LLM Should Decide — But Never Execute

ReAct vs Tool Calling: Why Your LLM Should Decide — But Never Execute

Comments
2 min read
loading...