Issues

MCP sounds like a brilliant idea that can be implemented in an afternoon. But once you start building it, especially in an enterprise app setting, rather than a consumer-level application, all kinds of difficulties crop up.

• AI Systems
• Systems Design
• LLM Engineering

RAG is usually the easiest use case for software engineers to get their feet wet. The core idea is not to rely on the LLM's internal knowledge, which can be outdated. However, most engineers fixate too much on vector and/or keyword search, missing out on deeper agentic patterns. That's what we'll cover in this issue.

• AI Systems
• Systems Design
• LLM Engineering

AI started as a threat to software engineers' jobs. The models of yesteryears still required humans in the loop. But right now, they're able to build complex software rapidly, albeit still requiring an engineer to oversee things. So, we won't need software engineers eventually, right? **Wrong!**

• AI Systems
• Systems Design
• LLM Engineering

Why AI won't take your engineering job. Here are a few less-discussed facts.

• AI Systems
• Systems Design
• LLM Engineering

Most believe that the choice of model, the available tools, or even the sophistication of the prompts are the most important factors in building an agentic system. They're wrong.

• AI Systems
• Systems Design
• LLM Engineering

There’s an important rule of writing that is not widely known outside certain circles but is tremendously valuable for writing LLM prompts.

• AI Systems
• Systems Design
• LLM Engineering

The secret to building with AI is in realizing that LLMs are like mirrors. Being a better engineer has never been more important. And here's why.

• AI Systems
• Systems Design
• LLM Engineering

Before you build an agent, pick the architecture that fits the job. Systems design for AI. Not whatever pattern you copied from a blog.

• AI Systems
• Agent Engineering
• Systems Design
• LLM Engineering

LLMs made raw intelligence cheap. Judgment and plain system design still decide if your product earns money. Including how DSLs tighten agent-style loops.

• AI Systems
• Agent Engineering
• DSL Design
• LLM Engineering

Why shipping production AI takes clear use cases and real system design. Not prompt tricks. Not a framed degree on the wall.

• Product Strategy
• AI Systems
• LLM Engineering
• ROI