A new direction for AI developer tooling (Friends)

What It Covers

Jose Valim discusses Tidewave, a local coding agent for full-stack web applications that runs in the browser alongside your development environment, integrating tightly with Phoenix, Rails, and other frameworks for real-time verification and testing.

Key Questions Answered

• •Local-First Architecture: Tidewave runs on localhost rather than remote servers, accessing your actual browser session and development environment. This allows the agent to use existing authentication, database connections, and framework configurations without separate MCP setup or credential management.
• •Browser-Based Verification: The agent executes JavaScript directly on the page to test implementations, automatically scrolling to validate autoplay features and running database queries to confirm data persistence. This creates a verification loop where agents test their own work before declaring completion.
• •Context Pruning Strategy: When context windows fill, Tidewave prunes tool outputs from early conversation stages rather than summarizing everything. This preserves recent context accuracy while extending conversation length, allowing developers to have meta-conversations with the agent about available tools and capabilities.
• •Framework Integration Over MCPs: Instead of installing multiple MCP servers for database access, GitHub integration, or documentation, Tidewave leverages existing framework capabilities. The agent uses code execution within the web application context, accessing documentation bundled with exact dependency versions rather than potentially outdated remote sources.
• •Productivity Through Specialization: Developers gain measurable productivity by identifying specific use cases where agents excel versus fail. Valim avoids using agents for Elixir type system work but successfully uses them to translate features between frameworks, skipping redundant tests and mocks while maintaining quality through proper verification loops.