In the chat completions API format used by OpenAI, Anthropic, Google, and others, messages come in three roles: system, user, and assistant. The system message is the system prompt, it's processed first, with higher conceptual priority than user turns, and persists across the entire conversation.
What Goes in a System Prompt
Prompt engineering is the discipline of communicating effectively with large language models. Because LLMs are trained to predict plausible continuations of text, how you frame a request has an enormous impact on what you get back, the same underlying model can behave like an expert assistant or produce generic noise depending on prompt quality.
Foundational Techniques
Zero-Shot…
LangChain is an open-source framework that provides building blocks for LLM applications. Rather than calling OpenAI's API directly and wiring everything by hand, LangChain gives you composable abstractions: chains (sequences of LLM calls), agents (LLMs that choose which tools to call), memory (state across turns), and retrievers (fetch relevant documents).
Core Abstractions
OpenHands (formerly OpenDevin) is an open-source platform for AI software engineering agents. Unlike Cursor or Windsurf which are IDEs with AI assistance, OpenHands is a platform where AI agents operate autonomously, writing code, executing shell commands, browsing the web, and iterating until a task is complete.
How OpenHands Works
OpenHands runs agents inside isolated Docker containers. The…
Windsurf (by Codeium) is an AI IDE that competes directly with Cursor. Its key differentiator is Cascade, an agentic system designed around "flows", coherent multi-step coding sessions where the agent understands and remembers what it has done across many tool calls, rather than treating each interaction as isolated.
Cascade: The Core Agent
Cascade has simultaneous awareness of:
Cursor is a fork of VS Code that reimagines the editor as an AI-native environment. While GitHub Copilot adds AI as a plugin to existing editors, Cursor was built from the ground up with AI as a first-class participant, not an afterthought.
Core Features
Ollama makes running open-source LLMs as straightforward as running a Docker container. You pull a model, and it starts serving a local REST API that your code can call, no cloud, no API key, no per-token billing.
How It Works
Ollama bundles model weights, a Go-based runtime, and a simple model definition format (Modelfiles) into a single binary. When you run ollama run llama3.2, it downloads…