- 1How I Work With AI Coding Agents in Elixir (And Why "Vibing" Is a Trap)A Practical Framework for AI-Augmented Elixir DevelopmentExplore the five modes of collaborating with AI coding agents in Elixir — and why 'vibing' creates fragile systems.AI Elixir Development Tools Best Practices
- 2Why AI "Forgets" (and How to Work With It Instead of Fighting It)A Mental Model for Predictable AI Collaboration in ElixirWhy AI agents lose context, how the conveyor belt model explains it, and a practical habit Elixir developers can use immediately to get better results.AI Elixir Development Tools Best Practices
- 3Which AI Agent Should You Actually Use?A Simple Framework for Choosing the Right Tool for the JobStop comparing features and benchmarks. Learn to match AI agents to your workflow with a practical decide-vs-execute rule you can use today.AI Elixir Development Tools Best Practices
- 4Stop Prompting. Start Anchoring.Why Decisions Should Live in Code, Not ConversationsThe model didn't forget your architecture—it just never lived anywhere durable. Learn how to anchor decisions in structure instead of prompts.AI Elixir Development Tools Best Practices
- 5The Editor Is the AgentWhy Checkpoint-Based AI Workflows Create ControlLearn the Ask → Plan → Agent workflow, a two-level safety net, and context discipline for checkpoint-based AI coding in Elixir.AI Elixir Development Tools Best Practices Workflows
- 6The Illusion of Speed: When AI Builds a Phoenix App in 30 MinutesWhy Vibe Coding Feels Fast and Becomes a Maintenance TrapA 30‑minute Phoenix LiveView demo looks magical – until you see how the yes loop creates hidden scope and long‑term maintenance cost.AI Elixir Development Tools Best Practices
- 7The Morning After: What That 30-Minute Phoenix App Actually CostsWhy Working Code and Maintainable Architecture Are Not the Same ThingA fast Phoenix LiveView build can look impressive, but hidden structural debt appears when you inspect what AI generated under speed pressure.AI Elixir Development Tools Best Practices
- 8Stop Repeating Yourself: How to Architect AI Workflows Like CodeApply DRY Thinking to AI Instructions with Axioms, Roles, and TasksIf you keep retyping the same AI instructions, you do not have a workflow. Learn a practical three-layer structure to keep coding agents consistent.AI Elixir Development Tools Best Practices Workflows
- 9Building Your AI Toolchain: Rules, Skills, Sub-Agents, and Slash CommandsHow to Layer AI Execution with Reusable Workflows Instead of Repeating PromptsLearn when to use rules, skills, sub-agents, and slash commands so your AI workflow scales with structured oversight instead of context-heavy repetition.AI Elixir Development Tools Best Practices Workflows
- 10Your AI Tooling Has a Home: Project vs. Global InfrastructureWhy Team-Ready AI Workflows Belong with the Code They GovernLearn when AI tooling should live globally versus in the project so shared workflows stay versioned, visible, and aligned with the codebase.AI Elixir Development Tools Best Practices Workflows
- 11Prompts That Write Prompts: Meta Workflow GenerationTurn Repeatable AI Development Workflows into Versioned Project InfrastructureLearn how meta workflow generation turns prompts into reusable project commands, making AI development workflows durable, repeatable, and reviewable.AI Elixir Development Tools Best Practices Workflows
- 12The Architect in the Loop: Critical Planning and the Limits of VibingWhy AI Plans Need Elixir Judgment Before ImplementationAI can produce a convincing architecture plan, but production systems need structured review. Bruce Tate shows how an Elixir architect catches security and design mistakes before implementation begins.AI Elixir Development Tools Best Practices Architecture
- 13Design for AI: Why Pure Functions Make Better AI PartnersHow a Functional Core Makes Claude Cheaper and More ReliableBruce Tate shows why pure functions and the CRC pattern (construct, reduce, convert) don't just help humans reason about code — they help Claude generate, verify, and stay correct with fewer tokens.AI Elixir Functional Programming Architecture Best Practices
- 14Managing 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
- 15Why Elixir Is Built for AI-Assisted DevelopmentPredictable Code Gives AI Agents Less Room to DriftWhy Elixir's functional core, process isolation, OTP recovery, and runtime metadata make it a strong language for AI-assisted development without losing architecture decisions.AI Elixir Development Tools Best Practices
- 16Inside Claude's Memory: AutoCompact and the Context HierarchyWhy AI Context Is Already Crowded Before You TypeLearn how Claude's context hierarchy, AutoCompact, and memory tradeoffs affect AI-assisted Elixir development, and why structured oversight starts with managing what enters context.AI Elixir Development Tools Best Practices
- 17Installing Tidewave: Two Ways to Wire AI Into Your Elixir AppHow Tidewave Connects Claude to Live Phoenix ContextInstall Tidewave in a Phoenix app and learn the two ways to wire Claude into your Elixir workflow through browser-based Tidewave or Claude Code MCP.AI Elixir Development Tools Best Practices