---
title: "Harshavardhanan (@harshavardhan) | Hashnode"
description: "Architect In Role. Developer by Heart. Read the latest articles by Harshavardhanan on Hashnode."
url: "https://hashnode.com/@harshavardhan"
---

@harshavardhan

# Harshavardhanan

@harshavardhan · Joined August 2018

Architect In Role. Developer by Heart

### [Anatomy of a Prompt — System, User, and Assistant Explained](https://blog.pragmaticbyharsh.com/anatomy-of-a-prompt-system-user-assistant-explained?utm_source=hashnode&utm_medium=feed)

Understand how system, user and assistant messages shape LLM behavior.

8 min read · [blog.pragmaticbyharsh.com](https://blog.pragmaticbyharsh.com/anatomy-of-a-prompt-system-user-assistant-explained?utm_source=hashnode&utm_medium=feed)

[Feb 15](https://hashnode.com/posts/anatomy-of-a-prompt-system-user-assistant-explained/699166eace356a7cdac6d504)

### [Choosing Embedding Models and Dimensions: Why 1536 Isn't Always Better Than 384](https://blog.pragmaticbyharsh.com/choosing-embedding-models-dimensions-production-tradeoffs?utm_source=hashnode&utm_medium=feed)

Learn how to choose embedding models and dimensions for production RAG systems. Compare OpenAI, Voyage AI, and Google's free options for embedding

11 min read · [blog.pragmaticbyharsh.com](https://blog.pragmaticbyharsh.com/choosing-embedding-models-dimensions-production-tradeoffs?utm_source=hashnode&utm_medium=feed)

[Feb 10](https://hashnode.com/posts/choosing-embedding-models-dimensions-production-tradeoffs/698b7959ce66e4a1190732b1)

### [What Are Embeddings and How Vector Similarity Actually Works](https://blog.pragmaticbyharsh.com/what-are-embeddings-vector-similarity-explained?utm_source=hashnode&utm_medium=feed)

Learn what embeddings are, how vector similarity works, and why understanding magnitude vs direction matters for semantic search and RAG systems.

14 min read · [blog.pragmaticbyharsh.com](https://blog.pragmaticbyharsh.com/what-are-embeddings-vector-similarity-explained?utm_source=hashnode&utm_medium=feed)

[Feb 8](https://hashnode.com/posts/what-are-embeddings-vector-similarity-explained/698841be760aad3a2be0868d)

### [How Tokenization Works: BPE and the Algorithm Behind Your LLM](https://blog.pragmaticbyharsh.com/how-bpe-tokenization-works-llm-algorithm?utm_source=hashnode&utm_medium=feed)

Learn how Byte Pair Encoding (BPE) actually works — the algorithm that powers GPT, Claude, and LLaMA tokenizers. Step-by-step with examples.

9 min read · [blog.pragmaticbyharsh.com](https://blog.pragmaticbyharsh.com/how-bpe-tokenization-works-llm-algorithm?utm_source=hashnode&utm_medium=feed)

[Feb 3](https://hashnode.com/posts/how-bpe-tokenization-works-llm-algorithm/69823ebfd9f0256419abf8a6)

### [What Are Tokens and Why Your LLM Bill Depends on Them](https://blog.pragmaticbyharsh.com/what-are-tokens-llm-tokenization-explained?utm_source=hashnode&utm_medium=feed)

Learn what tokens really are, why they're not words, and how understanding tokenization saves you money on LLM API costs.

9 min read · [blog.pragmaticbyharsh.com](https://blog.pragmaticbyharsh.com/what-are-tokens-llm-tokenization-explained?utm_source=hashnode&utm_medium=feed)

[Feb 1](https://hashnode.com/posts/what-are-tokens-llm-tokenization-explained/697f71b1d7b52bad1de6145f)
