Jonathan Pedoeem

Learnings from the Google Prompt Engineering Paper and others

The gap between basic and expert prompt engineering is smaller than you think. While many teams plateau after mastering basics like “be specific” and “provide examples,” the real breakthroughs come from understanding how different model families interpret instructions, context, tools, and examples. After extensive research into official documentation from OpenAI,

LLM Idioms

An LLM idiom is a pattern or format that models tend to recognize implicitly — conventions their training has reinforced and their internal representations can use without extra explanation. These are the native languages of AI systems. To me, this is one of the most important concepts in prompt engineering. I

Grok 4 vs Claude Opus 4: I Compared Them and Here's What I Found Out

Grok 4 (from xAI) and Claude Opus 4 (from Anthropic) are two of the most advanced language models available today. Both launched in 2025 and serve research, enterprise, and creative needs—but they take very different approaches. Here's how to choose the right AI model for academic research,

Claude Code vs. Cursor

AI coding assistants have reshaped how developers write, review, and maintain code. Two standout tools take different approaches: Claude Code operates as an autonomous terminal agent for complex, multi-step engineering tasks, while Cursor brings real-time AI assistance into the familiar VS Code-style editing workflow. Understanding their core

How I Automated Our Monthly Product Updates with Claude Code

From tedious manual work to comprehensive automated analysis in one afternoon 0:00 /2:41 1× If you're like me, you probably dread writing those monthly product update emails. You know the ones – where you have to comb through dozens (or hundreds) of commits across multiple repositories, trying

HumanLoop Shutdown: Guide to Migrating Your Prompts and Evals to PromptLayer

HumanLoop shut down on September 8, 2025. If your team relied on HumanLoop for prompt management, evaluations, and observability, you may still be looking for a stable replacement. PromptLayer offers everything HumanLoop did—and more. What is PromptLayer? PromptLayer is a comprehensive prompt engineering platform that serves as the “Git

Why LLMs Get Distracted and How to Write Shorter Prompts

Context Rot: How modern LLMs quietly degrade with longer prompts — and what you can do about it Context Rot: What Every Developer Needs to Know About LLM Long-Context Performance How modern LLMs quietly degrade with longer prompts — and what you can do about it If you've been

The Agentic System Design Interview: How to evaluate AI Engineers

So you need a team to build an LLM multi-agent system... how do you interview candidates? I'll try to provide some ideas and strategies in this article. Firstly... What is an AI Engineer? AI engineers build the future. They create scalable AI systems and agents. They test,

What is Context Engineering?

The term "prompt engineering" surged after ChatGPT launched in late 2022. It began as a practical toolkit for getting better responses from AI: be explicit, add examples, write role-playing instructions, and experiment with the prompt optimization patterns many teams reached for first. As I've written

Learnings from the Google Prompt Engineering Paper and others

LLM Idioms

Grok 4 vs Claude Opus 4: I Compared Them and Here's What I Found Out

Claude Code vs. Cursor

How I Automated Our Monthly Product Updates with Claude Code

HumanLoop Shutdown: Guide to Migrating Your Prompts and Evals to PromptLayer

Why LLMs Get Distracted and How to Write Shorter Prompts

The Agentic System Design Interview: How to evaluate AI Engineers

What is Context Engineering?

The first platform built for prompt engineering

Usage

Company

Follow Us