Blog

AI engineering insights, practical advice, and things I'm learning.

Latest AI news, updated daily. Go to News →

Ai Engineering

How Cursor Built Composer 2 on Top of Kimi K2.5

Cursor's Composer 2 is built on Kimi K2.5. What continued pretraining, reinforcement learning, and self-summarization mean, and how they work.

Cursor · Kimi K2 5 · Reinforcement Learning

Ai Engineering

What Is Mixture-of-Experts (MoE) in AI?

MoE models have a trillion parameters but only activate a fraction per token. How expert routing works, why it matters for cost, and which major models use it.

Mixture Of Experts · Moe · Llm Architecture

Ai Engineering

What Is Continued Pretraining in AI?

Continued pretraining adapts a general LLM to a specific domain using large unlabeled data. How it works, how it differs from fine-tuning, and real examples.

Continued Pretraining · Llm Training · Domain Adaptation

Ai Engineering

Continued Pretraining vs RAG: Two Ways to Add Knowledge

Continued pretraining bakes knowledge into model weights. RAG injects it at query time. When to use each, where each breaks down, and why you often need both.

Continued Pretraining · Rag · Retrieval Augmented Generation

Ai Engineering

How to Build Enterprise AI with Mistral Forge on Your Own Data

Learn how Mistral Forge helps enterprises build custom AI models with private data, synthetic data, evals, and flexible deployment.

Mistral Forge · Enterprise Ai · Custom Models

Ai Engineering

How to Deploy NVIDIA Dynamo 1.0 for Production AI Inference Across GPU Clusters

Learn how to use NVIDIA Dynamo 1.0 to orchestrate scalable AI inference with KV routing, multimodal support, and Kubernetes scheduling.

Nvidia Dynamo · Inference Optimization · Gpu Clusters

Ai Engineering

How to Run NVIDIA Nemotron 3 Nano 4B Locally on Jetson and RTX

Learn to deploy NVIDIA's Nemotron 3 Nano 4B locally with BF16, FP8, or GGUF on Jetson, RTX, vLLM, TensorRT-LLM, and llama.cpp.

Local Llms · Edge Ai · Nvidia

Career

AI Engineer Career Path: Skills, Salary, and How to Get Started

AI engineering is a distinct role from ML engineering or data science. Here's what AI engineers do, what skills you need, what the pay looks like, and how to break in from other software roles.

Career · Ai Engineer · Skills

Ai Agents

How to Choose Between GPT-5.4 Mini and Nano for Coding Agents and High-Volume API Tasks

Learn when to use GPT-5.4 mini vs nano for coding, tool use, subagents, and cost-sensitive API workflows.

Openai · Gpt 5 4 Mini · Gpt 5 4 Nano

Ai Engineering

How to Deploy Mistral Small 4 for Multimodal Reasoning and Coding

Learn how to deploy Mistral Small 4 with reasoning controls, multimodal input, and optimized serving on API, Hugging Face, or NVIDIA.

Mistral Small 4 · Mistral Ai · Multimodal Models

Ai Engineering

How to Get Started with Open-H, GR00T-H, and Cosmos-H for Healthcare Robotics Research

Learn how to use NVIDIA's new Open-H dataset and GR00T-H and Cosmos-H models to build and evaluate healthcare robotics systems.

Healthcare Robotics · Physical Ai · Robotics Datasets

Prompt Engineering

System Prompts: How to Write Effective LLM Instructions

System prompts define how your LLM behaves. Here's how to structure them, what mistakes to avoid, and how provider-specific behavior affects your prompt strategy.

System Prompts · Prompt Engineering · Llms

Prompt Engineering

Chain of Thought Prompting: A Developer Guide

Chain of thought prompting makes LLMs reason through problems step by step. Here's when it works, when it doesn't, and how to implement it with practical patterns.

Chain Of Thought · Prompt Engineering · Reasoning

Prompt Engineering

Few-Shot Prompting: How to Guide LLMs with Examples

Few-shot prompting teaches LLMs by example instead of instruction. Here's how to choose examples, format them, and know when few-shot is the right approach vs. fine-tuning.

Few Shot Prompting · Prompt Engineering · Llms

Ai Engineering

How to Use Claude Across Excel and PowerPoint with Shared Context and Skills

Learn how to use Claude's shared Excel and PowerPoint context, Skills, and enterprise gateways for faster analyst workflows.

Anthropic · Claude · Excel

Ai Coding

Agent Skills vs Cursor Rules: When to Use Each

Cursor has both rules and skills for customizing the AI agent. They overlap, but they're not the same. Here's when to use each and how they interact.

Agent Skills · Cursor Rules · Cursor

Ai Agents

How to Add Memory to AI Agents

AI agents without memory forget everything between turns. Here's how to implement conversation buffers, sliding windows, summary memory, and vector-backed long-term recall.

Ai Agents · Memory · Conversation History

Ai Coding

How to Create Your First Agent Skill

A step-by-step guide to writing an agent skill from scratch: directory structure, SKILL.md format, effective descriptions, common patterns, and a complete working example.

Agent Skills · Cursor · Claude Code

Ai Agents

How to Evaluate and Test AI Agents

Evaluating AI agents requires different metrics than evaluating LLMs. Here's how to measure task completion, trajectory quality, tool-use accuracy, and regression across agent systems.

Ai Agents · Evaluation · Testing

Ai Coding

What Are Agent Skills and Why They Matter

Agent skills are portable packages of instructions that extend AI coding agents. Here's what they are, how they work, and why the open standard changes how developers work with AI tools.

Agent Skills · Cursor · Ai Coding