The Loop  ·  Issue N°016

The Loop

A field journal of the AI frontier — for engineers who ship.

In this issue

12 more pieces

  1. · Guides

    Writing a CLAUDE.md that actually helps

    The file that Claude loads on every turn deserves the same care as a hot code path. What to put in it, what to keep out, and what a useful one looks like.

    Apr 20, 2026 · by AI Blog Editor

  2. · Guides

    A field guide to Claude Code: CLAUDE.md, hooks, skills, plugins

    Four primitives, often confused: the passive memory, the deterministic harness layer, the model-invoked capability, and the bundle. A pragmatic walkthrough, with diagrams and a decision picker.

    Apr 20, 2026 · by AI Blog Editor

  3. · Guides

    Building agents that actually work

    Ten lessons from shipping agent-based features — from loop design to tool discipline to failure modes you will not see in demos.

    Apr 20, 2026 · by AI Blog Editor

  4. · Guides

    Skills that earn their keep

    Not every repeated task deserves a skill. The three tests a skill should pass, and eight scenarios where you guess the right shape.

    Apr 20, 2026 · by AI Blog Editor

  5. · Guides

    Prompt caching: the cheap win most people skip

    The largest single cost lever the Claude API gives you, and it's still the one most teams haven't turned on. How the cache works, how to structure for it, and what it actually saves.

    Apr 20, 2026 · by AI Blog Editor

  6. · Guides

    Tool use in one picture

    Four message shapes cover 95% of tool use. See each one as a live JSON conversation — single call, parallel fan-out, agent loop, forced choice.

    Apr 20, 2026 · by AI Blog Editor

  7. · Guides

    When extended thinking earns its cost

    Thinking helps when the model would commit to the wrong first answer. It doesn't help on tasks the first pass already nailed. A pragmatic guide with a directional chart.

    Apr 19, 2026 · by AI Blog Editor

  8. · Guides

    The eval harness nobody regrets building

    Stop shipping changes on vibes. A small seed set, an honest rubric, a fast grader, and a CI gate. How to build the measurement discipline that keeps you from lying to yourself.

    Apr 19, 2026 · by AI Blog Editor

  9. · Guides

    Agent loops that don't self-destruct

    A loop without a budget, a success signal, and a log is a cost leak with extra steps. Design patterns for agents that stop when they should.

    Apr 18, 2026 · by AI Blog Editor

  10. · Guides

    RAG on two axes: size × freshness

    Place your project on the grid and the right technique is usually one of five. When to paste it in a prompt, when to index, when to just let Claude call your search API.

    Apr 17, 2026 · by AI Blog Editor

  11. · News

    Three AI design tells I won't ship

    The side-stripe card. The gradient headline. The card-grid hellscape. How to spot them, why they spread, and what to do instead.

    Apr 16, 2026 · by AI Blog Editor

  12. · News

    Stop building chatbots

    The best AI features feel like the product got smarter, not like talking to a robot. An argument for invisible AI, with three worked examples.

    Apr 15, 2026 · by AI Blog Editor

One letter a week. New pieces, field notes from the trenches, and the occasional marginalia. No tracking beyond what your email client does anyway. Unsubscribe whenever — no hard feelings.