Posts tagged with AI

Bruce Tate explains why agentic coding fails when model priors, codebase evidence, and correction channels break down—and why explicit systems are easier to verify.

Learn how to review AI-generated Elixir code by separating functional core from boundary code, reading public APIs first, and catching missed domain requirements.

Bruce Tate explains how AI is reshaping software training, why small teams need ongoing guidance, and how prompt architecture, Git, and human oversight keep agentic coding on track.

Learn how Tidewave's project_eval lets Claude Code inspect, test, and demonstrate behavior inside your running Elixir application through a shared IEx-style workflow.

Bruce Tate argues that cheap AI coding tools are hiding two bills: the real cost of tokens and the maintenance cost of code built without human guidance.

Install 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.

Bruce Tate argues that AI changes how we should choose programming languages: not by GitHub stars, but by problem fit, operational characteristics, abstractions, and training data consistency.

Learn how Claude's context hierarchy, AutoCompact, and memory tradeoffs affect AI-assisted Elixir development, and why structured oversight starts with managing what enters context.

Bruce Tate lays out Groxio's position on AI: use it where it strengthens human judgment, pay the full costs it creates, compensate the people whose work trained it, and reinvest the dividend in juniors and craft.

Why Elixir's functional core, process isolation, OTP recovery, and runtime metadata make it a strong language for AI-assisted development without losing architecture decisions.

Bruce Tate argues that AI has not removed coding from junior development. It has made every keystroke an act of teaching, making planning, review, prompt discipline, and mentorship the new training ground.

Learn how Bruce Tate manages Claude context windows with compacting, clearing, and priming while preserving layered Elixir architecture and one source of truth per layer.

Bruce Tate argues that AI did not eliminate junior developers. It moved their work toward judgment, verification, architecture boundaries, and training that grows future seniors.

Bruce 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 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.

Bruce Tate argues that code is no longer the core asset – judgment is. The organizations that win will protect senior craft, measure mentorship, and reinvest AI's dividend in training juniors into future seniors.

Bruce Tate argues the AI coding crisis is not a junior talent problem but a training failure, and outlines the concrete skills teams need to teach explicitly now.

Bruce Tate traces how AI coding tools moved from helpful completion to unchecked delegation, leaving teams with faster output, weaker design, and less room for judgment to grow.

AI coding tools are increasing output while hiding codebase drift, review overload, and lost mentorship. Bruce Tate argues teams should reinvest the time AI gives them in training and craft.

Learn how meta workflow generation turns prompts into reusable project commands, making AI development workflows durable, repeatable, and reviewable.

Learn when AI tooling should live globally versus in the project so shared workflows stay versioned, visible, and aligned with the codebase.

Learn when to use rules, skills, sub-agents, and slash commands so your AI workflow scales with structured oversight instead of context-heavy repetition.

If you keep retyping the same AI instructions, you do not have a workflow. Learn a practical three-layer structure to keep coding agents consistent.

A fast Phoenix LiveView build can look impressive, but hidden structural debt appears when you inspect what AI generated under speed pressure.

A 30‑minute Phoenix LiveView demo looks magical – until you see how the yes loop creates hidden scope and long‑term maintenance cost.

Learn the Ask → Plan → Agent workflow, a two-level safety net, and context discipline for checkpoint-based AI coding in Elixir.

The model didn't forget your architecture—it just never lived anywhere durable. Learn how to anchor decisions in structure instead of prompts.

Stop comparing features and benchmarks. Learn to match AI agents to your workflow with a practical decide-vs-execute rule you can use today.

Why AI agents lose context, how the conveyor belt model explains it, and a practical habit Elixir developers can use immediately to get better results.

Explore the five modes of collaborating with AI coding agents in Elixir — and why 'vibing' creates fragile systems.