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

Melbourne, Australia Joined on Dec 24, 2025 https://www.linkedin.com/in/parthsarthi-sharma/

Pronouns

He/Him

Work

Lead Software Engineer

Parth Sarthi Sharma

Jun 11

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

#ai #observability #softwareengineering #sre

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.

Create Account

Already have an account? Sign in

Parth Sarthi Sharma

Jun 6

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

#ai #vibecoding #machinelearning #softwareengineering

4 min read

Parth Sarthi Sharma

Mar 22

Reflection vs Reflexion Agents: The Next Leap in Agentic AI

#ai #agentskills #llm #softwareengineering

3 min read

Parth Sarthi Sharma

Mar 7

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

#ai #llm #promptengineering #softwareengineering

4 min read

Parth Sarthi Sharma

Feb 14

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

#security #ai #llm #devops

3 min read

Parth Sarthi Sharma

Jan 27

Observability in AI Systems

#ai #rag #softwareengineering #llm

3 min read

Parth Sarthi Sharma

Jan 22

Self-RAG vs Adaptive RAG vs Corrective RAG

#ai #rag #vectordatabase #softwareengineering

3 min read

Parth Sarthi Sharma

Jan 20

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

#ai #rag #softwareengineering #llm

3 min read

Parth Sarthi Sharma

Jan 12

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

#ai #rag #vectordatabase #softwareengineering

3 min read

Parth Sarthi Sharma

Jan 9

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

#ai #promptengineering #vectordatabase #rag

3 min read

Parth Sarthi Sharma

Jan 8

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

#ai #rag #llm #softwareengineering

2 min read

Parth Sarthi Sharma

Jan 6

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

#ai #rag #llm #softwareengineering

2 min read

Parth Sarthi Sharma

Jan 4

Why “Lost in the Middle” Breaks Most RAG Systems

#ai #rag #vectordatabase #machinelearning

2 min read

Parth Sarthi Sharma

Jan 3

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

#ai #rag #vectordatabase #llm

3 min read

Parth Sarthi Sharma

Jan 2

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

#ai #rag #llm #genai

3 min read

Parth Sarthi Sharma

Dec 30 '25

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

#ai #vectordatabase #rag #generativeai

2 min read

Parth Sarthi Sharma

Dec 28 '25

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

#langchain #rag #ai #vectordatabase

2 min read

Parth Sarthi Sharma

Dec 24 '25

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

#ai #langchain #llm #systemdesign

2 min read

DEV Community

Parth Sarthi Sharma

Badges

Writing Debut

Skills/Languages

Currently hacking on

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

Want to connect with Parth Sarthi Sharma?

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

Reflection vs Reflexion Agents: The Next Leap in Agentic AI

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

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

Observability in AI Systems

Self-RAG vs Adaptive RAG vs Corrective RAG

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

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

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

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

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

Why “Lost in the Middle” Breaks Most RAG Systems

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

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

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

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

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