- The Discipline of Throwing Code AwayWhen Rebuilding AI-Generated Code Is Better Than Repairing a Bad FoundationLearn when to discard structurally flawed AI-generated code, preserve the lessons from failure, and turn rejected implementations into clearer specifications.AI Elixir Development Tools Code Quality Workflows
- Git Discipline for AI: Branches, Verification, and Pull RequestsHow Git Checkpoints Keep AI Agent Work Isolated, Verifiable, and ReviewableLearn how feature branches, binary verification, and pull requests create safe boundaries for AI coding agents while keeping humans in control of architecture decisions.AI Elixir Development Tools Workflows Code Quality
- project_eval: An IEx Swiss Army Knife You and Your AI ShareHow Tidewave's project_eval Turns Claude Output Into a Shared IEx WorkflowLearn how Tidewave's project_eval lets Claude Code inspect, test, and demonstrate behavior inside your running Elixir application through a shared IEx-style workflow.AI Elixir Development Tools Code Quality
- Managing the Conveyor Belt: Context Windows and Layered Elixir ArchitectureWhy Long AI Sessions Need Fresh Context and Clear Ownership BoundariesLearn how Bruce Tate manages Claude context windows with compacting, clearing, and priming while preserving layered Elixir architecture and one source of truth per layer.AI Elixir Development Tools Architecture Code Quality