Code Offline with Context Engineering I ride BART every day, and I've turned those underground stretches into productive coding time using Continue's agent mode with Ollama. No internet required. The reality of offline development We've all been there. No access to LLMs goes down for 30-40mins because your coffee
Building a Semantic Code History Search with LanceDB Ever wished you could ask "who wrote all the authentication logic?" instead of manually running git blame on every auth-related file? What if your AI coding assistant could understand not just who changed code, but why and what it relates to across your entire codebase? Let's
The New Rules CLI The evolution of rules from constraints to amplifiers The concept of "rules" in software development has undergone a fundamental transformation. What once meant rigid linting configurations now represents a sophisticated approach to customizing AI coding assistants. With 82% of developers using AI assistants daily or weekly, the ability
Continue Newsletter - May & June 📜 Leverage rules as a context provider in Continue Use the @ symbol to leverage specific rules that provide context and instructions to the assistant. This ensures more accurate and consistent code generation based on your project's unique guidelines. These rules help you define project-specific instructions for the AI, customizing
The Anatomy of Rules: Writing Effective Boundaries for AI Agents in Ruby When working with AI agents to write code, the difference between good and great results often comes down to the quality of your rules. In my recent video, I demonstrated how rules serve as guardrails that amplify your intentions and ensure the agent codes like a senior developer would. My