Topic guide

AI engineering

The AI engineering hype cycle runs on three lies: that AI multipliers replace engineers, that agents can ship to production without supervision, and that buying a better model fixes a broken pipeline. The posts below argue the opposite — and show what production AI engineering actually looks like in 2026.

Read the contrarian framing first if you need to defend headcount to a board. Skip to the workflow posts if you're already shipping. The autonomy ladder is the one to bookmark — every agent failure I've seen traces back to promoting a system one rung too far without the supervisory layer that rung requires.

The reading order

  1. 1.

    AI Won't Shrink Your Team — It'll Expose Why You Needed a Bigger One

    The contrarian thesis: AI surfaces the backlog you didn't have bandwidth to touch. The companies cutting headcount on the multiplier story will get outpaced by the ones that hold and absorb.

    May 1, 2026 9 min read

  2. 2.

    An AI Just Deleted a Production Database in Nine Seconds. Hire More Engineers.

    Replit's agent ignored a code freeze and wiped 1,200 executives in nine seconds. The most expensive proof of the previous post.

    May 2, 2026 9 min read

  3. 3.

    When to Trust an Agent and When to Step In

    The four-level autonomy ladder — read-only, bounded write, state-changing, public-facing — plus the five signals that mean a human takes the wheel immediately.

    December 22, 2025 9 min read

  4. 4.

    My Daily Agentic AI Workflow

    Four to seven Claude Code or Codex sessions a day, scoped at the right autonomy level, with every diff reviewed. The actual loop, not the marketing.

    November 24, 2025 8 min read

  5. 5.

    AI-Assisted Engineering Isn't Faster Coding. It's a New Workflow.

    Why "AI-assisted" is a category mistake. Review, decomposition, and what shipping means all change shape.

    March 16, 2026 9 min read

  6. 6.

    Your AI Product Needs a Telemetry Layer Before It Needs a Better Model

    Stop tuning the model. Instrument the system. LangSmith, Helicone, custom evals — what to measure and why model swaps without telemetry are theatre.

    January 26, 2026 9 min read

  7. 7.

    Prompt Skills, Not Claude: Four Rules from Anthropic's Engineers

    Four rules for Claude Code skills from Anthropic's engineers, tested in fractional consulting work. Why prompt-engineering moved from the chat to the folder, and the two flags most engineers don't know about.

    May 26, 2026 10 min read

  8. 8.

    The AI Coding Agent Bugs I Catch Every Week

    The eight failure patterns from running agents daily — confident wrong answers, lost context, the bugs they reliably ship. The field notes behind the autonomy ladder.

    June 25, 2026 13 min read

  9. 9.

    How I Prompt Claude as a Staff Engineer (50 Prompts I Actually Use)

    Fifty production prompts with five full worked examples. What the daily workflow actually sounds like at the prompt level.

    May 9, 2026 7 min read

  10. 10.

    Build an LLM Wiki Your Coding Agent Actually Reads

    A three-layer markdown knowledge base your agent reads and maintains — ingest, query, lint — and the rules that stop it rotting.

    June 29, 2026 8 min read

  11. 11.

    Your CLAUDE.md Is the Onboarding Doc You Never Wrote

    CLAUDE.md as executable tribal knowledge: the onboarding doc you never wrote for humans, finally read by something that acts on it.

    June 29, 2026 9 min read

  12. 12.

    The Claude Code Resource Bible: 46 Tools Worth Knowing in 2026

    The ecosystem map — 46 tools across MCP servers, skills, multiplexers, and agent frameworks, organized so you can skip the other four hundred.

    May 7, 2026 17 min read

  13. 13.

    Ruflo (formerly Claude Flow): An Honest Deep Dive on the Multi-Agent Orchestration Platform

    An honest teardown of the loudest multi-agent orchestration platform — what the 45,000 GitHub stars are buying, and what they aren't.

    May 7, 2026 15 min read

  14. 14.

    Amazon Let the AI Drive. It Hit a Tree.

    Amazon mandated AI coding, let it touch infrastructure unwatched, and lost millions of orders. The case study the autonomy ladder predicts.

    June 30, 2026 9 min read

  15. 15.

    AI Made Tokens Cheap. It's Making Hardware Costly.

    Tokens got cheap; the hardware to run them didn't. The cost story nobody prices into an AI roadmap.

    June 26, 2026 6 min read

  16. 16.

    Nadella Is Right About AI and the Firm. Mostly.

    Nadella's 'token capital' framing is right about judgment and wrong about scale — the small-team version of the argument.

    June 15, 2026 12 min read

Other topic guides

  • Security for startups A guided reading order for startup security — what to read first on SOC 2 as a revenue tool, vCISO hiring, and securing AI-native products.
  • Engineering leadership Engineering leadership at startup scale — hiring from one engineer to fifteen, rituals that work at small teams, the staff-engineer interview loop.
  • Elixir and the BEAM for AI systems Why language choice matters for AI systems — BEAM concurrency for agents, what Go frameworks cost you, and why Elixir is the language AI writes best.

Or browse differently