skip to content

Archive

AI controls, agent systems, banking governance, production practice. 412 essays, newest first.

  1. AI Controls Architecture

    Risk teams know risk. The open problem is designing controls for systems that are non-deterministic, probabilistic, and attackable in natural language.

  2. Governing Agents the Way Cells Govern Themselves

    Six cell biology mechanisms that reveal what the networking 'control plane' metaphor misses about governing AI agents.

  3. The Risk Without an Engineering Solution

    Every other agentic AI risk has an engineering answer. Prompt injection doesn't. That changes everything about how you design controls.

2026
  1. Your AI Is an Echo Chamber (And That's Sometimes Fine)

    AI agrees with you by design. That's great for creative flow and dangerous at the decision point. Know when to switch modes.

  2. Enterprise AI Agents: The Transformation Is Organisational, Not Technical

    The companies that win with AI agents aren't deploying the most agents — they're redesigning their organisations to work with them.

  3. Honesty as Default, With One Exception

    A two-tier honesty framework: be honest by default, override only when truth would harm someone vulnerable.

  4. Compounding: The Only Mental Model

    If you could only keep one mental model, keep compounding. It applies to skills, reputation, writing, and tools.

  5. Over-Capture, Then Cull

    Don't filter during capture. Capture is cheap. Ideas are expensive. The cull is where quality happens.

  6. Hooks Are Life Infrastructure

    Event-driven hooks in AI coding tools aren't just for linting — they're programmable triggers for life routines, habits, and systems.

  7. Composure Is a Skill

    Rushing is a habit, not a response to reality. You break it by deliberately not rushing when you could.

  8. Your AI Tools Should Watch You Fumble

    The best time to improve a CLI isn't when it breaks — it's when you review the breakage log at the end of a work session.

  9. Mining Your LLM

    Your AI already knows things that would make it better at helping you. The trick is extracting that knowledge and making it permanent.

  10. Building a Bus Alert System in One Session

    How a real need on a Hong Kong bus turned into a GPS-powered alert system in under two hours

  11. The Debate Round Is Where Value Lives

    Independent parallel reviews produce overlapping findings. The cross-critique round produces resolution. That's where multi-agent value actually emerges.

  12. The Confidence Trap

    Why the thinkers who make you feel like hard questions are resolved deserve the most scrutiny.

  13. When LangGraph Earns Its Keep

    LangGraph is the SAP of agent orchestration — powerful at scale, overkill for most. Here's the line.

  14. Your AI Pipeline Is Probably MapReduce

    Most AI workflows are parallel-then-aggregate, not agent graphs. Knowing the difference saves you from framework theatre.

  15. The Expert Illusion

    Why 'you are an expert' is the most popular and least useful prompt engineering technique

  16. Planning Needs Eyes

    A 3-pass AI planning pipeline caught 0 out of 6 design issues. The same planning done in-session with tool access caught 2.5. Planning isn't a prompt problem — it's a tools problem.

  17. What If Your Vault Had Residents?

    Not tools that search your notes — personalities that live in them, form opinions, and disagree with each other.

  18. Put the Rule Where It Fires

    Documenting a rule is half a loop. The rule only works when it fires at the moment of decision — not when it sits in a file nobody reads.

  19. What Human Memory Teaches AI Agents (and What It Doesn't)

    A calculator doesn't simulate forgetting — it manages its context budget. What to cherry-pick from cognitive science for AI agent memory, and what to leave behind.

  20. When to Make Your Pipeline Agentic

    Most LLM pipelines don't need agents. The ones that do share a specific pattern — the step needs to decide what to do next, not just process what it's given.

  21. The MTEB Leader Barely Beats a Free Model on Agent Memory

    I benchmarked 10 memory backends and multiple embedding models on actual agent memory retrieval. The results challenge common assumptions about what matters.

  22. China's AI Stack Is Now Hardware-Deep

    DeepSeek V4 launching on Huawei Ascend NPUs signals that China's AI ecosystem is decoupling at the silicon layer — deeper and more durable than model-level divergence.

  23. AI Vendors Are Not Neutral Infrastructure

    The DoD-Anthropic dispute reveals a new category of operational risk: foundation model vendors can unilaterally revoke access based on their own values, not just SLA violations.

  24. Three APAC Regulators Are Converging on AI Governance — Banks Should Build One Framework

    MAS, PBOC, and HKMA are independently arriving at similar AI governance requirements. Banks regulated by all three have a narrow window to build one superset framework instead of three silos.

  25. The Agent Governance Gap Is Already Here

    Agentic AI isn't a future governance problem — it arrived ungoverned, and this week saw the first enforcement action.

  26. Your Agent Pays the Cold-Start Tax Every Morning

    Agent memory isn't knowledge management. It's performance infrastructure — and the gap between a stateless agent and one that accumulates context is measurable.

  27. The Knowledge That Disappears When You Try to Capture It

    Enterprise AI keeps promising to capture institutional knowledge. The most valuable kind resists capture by design.

  28. What AlphaSense Charges Ten Thousand Dollars For

    I built an AI landscape intelligence pipeline for zero marginal cost. Here's what it does and what it can't.

  29. The Eval Gap

    The scarce AI skill isn't building — it's knowing if what you built actually works.

  30. The CLI Boundary

    Which parts of an AI dev workflow can be wrapped in a CLI, and which can't — learned the hard way by building the wrong thing and measuring it.