Nachiketa Hebbar
LLM APIs, LangChain agents, and NLP models with a focus on practical implementation.
Nutrition Label
Nachiketa Hebbar specializes in hands-on coding tutorials that guide viewers through building AI applications using Python, LangChain, and LLM APIs. His content is highly practical, often featuring live coding sessions that show real-time execution, debugging, and functional prototypes rather than just theoretical slides.
Strengths
- +
- +
- +
Notes
- !Tutorials prioritize functional prototypes, so verify security best practices for production deployment.
- !Career advice is anecdotal and based on personal experience rather than broad industry data.
Rating Breakdown
Breakdown across the key dimensions we rate. Methodology →
Recent Videos
Fine-Tune BERT for ANY Text Classification Task| Explained With Code
Build A LLM-Based Text Classifier| Prompt Engineering
Life After Master’s in the U.S. (Career + Channel Update)
Build A Text-Image Search Engine in 10 Minutes| CLIP + Chroma DB Tutorial
K Fold Cross Validation| Complete Explanation in 10 minutes
Build Auto Code Completion ChatBot| LangChain + Python
LangChain Simplified #2| Agents Overview + Google Search API
Get Started With LangChain #1| LLM's + Prompt Templates|
Build a Chatbot in Python| ChatGPT API Complete Tutorial for Beginners
Life Update| MS in US| Things to Consider
Computer Vision App-A-Thon After Movie| IIT Delhi| @awirosweb
Convert Any AI Model into Video AI App and Earn| Early Access!
What I Do as a Computer Vision Engineer| Step by Step Guide|
Making a career in AI as a Fresher| IIT Kharagpur Guest Lecture|
Train Your First GAN in Tensorflow| Complete Tutorial in Python|
Why this rating
Evidence receipts showing why each dimension is rated the way it is.
“We'll be using the SerpAPI... and the LLM Math tool.”[03:10] →
The video delivers exactly what is promised: a simplified overview of Agents using the Google Search API (via SerpAPI) and a math tool.
“We get an accuracy of roughly 56 percent... which is not great.”[10:45] →
Creator demonstrates the actual execution of the code and honestly reports the poor baseline result (zero-shot) before attempting to improve it.
“landed a role as a Machine Learning Engineer 2 at TikTok”[Description] →
Creator explicitly discloses their new employer and specific job title, providing crucial context for future content bias or expertise.
“We need to give the agent some instructions on what it needs to do... This is where prompt templates come in.”[04:15] →
Explains the necessity of prompt engineering (prefix/suffix) for the agent, though does not address the security risks of giving an LLM access to a Python REPL.