AI Engineering

Introduction Large language models (LLMs) have transformed how we interact with text, code, and even visual data. Their ability to generate coherent prose, answer questions, and synthesize information is impressive—yet they remain fundamentally stateless, batch‑oriented, and latency‑heavy. When you need a system that reasons in the moment, responds to sensor streams, or controls safety‑critical hardware, the classic LLM pipeline quickly becomes a bottleneck. Enter Liquid Neural Networks (LNNs), a class of continuous‑time recurrent networks that can adapt their internal dynamics on the fly. Coupled with Rust, a systems language that offers zero‑cost abstractions, memory safety, and deterministic performance, we have a compelling foundation for building real‑time reasoning engines that go beyond what static LLM inference can provide. ...

Introduction The landscape of software engineering is undergoing a seismic shift. For decades, the relationship between a developer and their computer was mediated by manual input: typing commands, clicking buttons, and switching between windows. With the release of Claude Code and the Computer Use capability, Anthropic has introduced a paradigm shift where the AI is no longer just a chatbot, but an active participant in the operating system. Claude Code is a command-line interface (CLI) tool that allows Claude to interact directly with your local development environment. When paired with the broader “Computer Use” API—which enables Claude to perceive a screen, move a cursor, and execute keyboard events—we are witnessing the birth of the “AI Agent” era. ...

The explosion of Large Language Models (LLMs) like GPT-4 and Claude has revolutionized how we build software. However, these models suffer from two major limitations: knowledge cut-offs and “hallucinations.” To build production-ready AI applications, we need a way to provide these models with specific, private, or up-to-date information. This is where Retrieval Augmented Generation (RAG) comes in, and the heart of any RAG system is the Vector Database. In this guide, we will go from zero to hero, exploring the architecture, mathematics, and implementation strategies of vector databases. ...

Introduction Tool calling (also called function calling or plugins) is the capability that turns large language models from text predictors into general-purpose controllers for software. Instead of only generating natural language, an LLM can: Decide when to call a tool (e.g., “get_weather”, “run_sql_query”) Decide which tool to call Construct arguments for that tool Use the result of the tool to continue its reasoning or response This post is a deep dive into the anatomy of tool calling: the moving parts, how they interact, what can go wrong, and how to design reliable systems on top of them. ...

Introduction As language models are woven into more complex systems—multi-tool agents, retrieval-augmented generation, multi-model stacks—“what should handle this request?” becomes a first-class problem. That’s what a semantic router solves. Instead of routing based on keywords or simple rules, a semantic router uses meaning (embeddings, similarity, sometimes LLMs themselves) to decide: Which tool, model, or chain to call Which knowledge base to query Which specialized agent or microservice should own the request This post is a detailed, practical guide to semantic routers: ...