Medium

Kenneth Leung

In

Level Up Coding

by

Kenneth Leung

·

Apr 22

Building Human-In-The-Loop Agentic Workflows

Understanding how to set up human-in-the-loop (HITL) agentic workflows in LangGraph

Building Human-In-The-Loop Agentic Workflows

In

Level Up Coding

by

Kenneth Leung

·

Mar 26

Scaling Feature Engineering Pipelines with Feast and Ray

Utilizing feature stores like Feast and distributed compute frameworks like Ray in production machine learning systems

Scaling Feature Engineering Pipelines with Feast and Ray

In

Level Up Coding

by

Kenneth Leung

·

Feb 27

How Cursor Actually Indexes Your Codebase

Exploring the RAG pipeline in Cursor that powers code indexing and retrieval for coding agents

How Cursor Actually Indexes Your Codebase

In

Level Up Coding

by

Kenneth Leung

·

Jan 25

How Agents Plan Tasks with To-Do Lists

Understanding the process behind agentic planning and task management in LangChain

How Agents Plan Tasks with To-Do Lists

In

Data Science Collective

by

Kenneth Leung

·

Jan 13

How Agents Hand Off Control in Multi-Agent Systems, Clearly Explained

Understanding how LLM-based agents transfer control to each other in a multi-agent system with LangGraph

How Agents Hand Off Control in Multi-Agent Systems, Clearly Explained

In

Level Up Coding

by

Kenneth Leung

·

Oct 1, 2025

Using Google’s LangExtract and Gemma for Structured Data Extraction

Extracting structured information effectively and accurately from long unstructured text with LangExtract and LLMs

Using Google’s LangExtract and Gemma for Structured Data Extraction

In

Level Up Coding

by

Kenneth Leung

·

May 13, 2025

How to Benchmark DeepSeek-R1 Distilled Models on GPQA Using Ollama and OpenAI’s simple-evals

Set up and run the GPQA-Diamond benchmark on DeepSeek-R1's distilled models locally to evaluate its reasoning capabilities.

How to Benchmark DeepSeek-R1 Distilled Models on GPQA Using Ollama and OpenAI’s simple-evals

In

DataDrivenInvestor

by

Kenneth Leung

·

Mar 10, 2025

How LLMs are Reshaping Financial Services: Real-World Examples

Exploring the practical use cases and specialized models that are driving innovation and efficiency across financial services

How LLMs are Reshaping Financial Services: Real-World Examples

In

TDS Archive

by

Kenneth Leung

·

Sep 25, 2024

Exposing Jailbreak Vulnerabilities in LLM Applications with ARTKIT

Automated prompt-based testing to extract hidden passwords in the popular Gandalf challenge

Exposing Jailbreak Vulnerabilities in LLM Applications with ARTKIT

In

Level Up Coding

by

Kenneth Leung

·

Apr 16, 2024

Inside the Leaked System Prompts of GPT-4, Gemini 1.5, Claude 3, and More

Unveiling the shared strategies and key distinctions in the prompts behind the best LLMs from OpenAI, Google, and Anthropic

Inside the Leaked System Prompts of GPT-4, Gemini 1.5, Claude 3, and More

Kenneth Leung

Kenneth Leung

AI Lead at Boston Consulting Group | Top Author | 2M+ reads on Medium | linkedin.com/in/kennethleungty | github.com/kennethleungty

Help

Status

About

Careers

Press

Blog

Store

Privacy

Rules

Terms

Text to speech