← Ben Lai

Changelog

A public version of the feed the homepage uses for its local, private "since you were here" diff. No account, no analytics, no server-side memory.

  1. Essay

    Your last mile is a human

    Many products are automated until the final awkward step. That human step is not an exception. It is part of the system.

  2. Essay

    The product spec is a commitment

    A spec is not a brainstorm with headings. It is a promise about what the team is choosing not to rediscover every week.

  3. Essay

    Make the reversible choice

    Teams waste courage on decisions that can be changed. Save the hard process for the choices that actually close doors.

  4. Essay

    The team calendar is technical debt

    Recurring meetings are production load on the people who build the product. Treat them like any other long-running process.

  5. Essay

    Your backlog is not a strategy

    A backlog is inventory. Strategy is the reason most of that inventory should never be built.

  6. Essay

    The best security feature is a boring log

    Security work often starts with controls. It should also start with whether you can explain what already happened.

  7. Essay

    Write the postmortem while it is small

    Waiting for a major incident before writing clearly about failure teaches the team to practice only under stress.

  8. Essay

    The agent should ask fewer questions

    Clarifying questions are useful when they reduce risk. They are waste when the system could have carried the context itself.

  9. Essay

    Pricing is an ops decision

    Pricing does not end on the pricing page. It becomes metering, invoices, support policy, limits, exceptions, and renewal work.

  10. Essay

    The most important test is the retry

    Happy-path tests prove the first attempt works. Production usually wants to know what happens after the first attempt fails.

  11. Essay

    Measure the work you refuse to automate

    Manual work is not always bad. Unmeasured manual work is how teams lose weeks without noticing.

  12. Essay

    The release train needs brakes

    Shipping on a schedule is good. Shipping without a stop condition is just confidence wearing a timetable.

  13. Essay

    Your support macro is a roadmap

    Repeated support macros are not just saved replies. They are product gaps that have learned to speak politely.

  14. Essay

    One good default beats ten settings

    Settings look like user empowerment. Often they are product indecision exported into the account page.

  15. Essay

    The staging environment lies

    Staging is useful, but it is not production with lower stakes. Its data, traffic, permissions, and failure modes are usually fiction.

  16. Essay

    The AI budget needs an owner

    LLM spend hides inside product usage, experiments, support tools, and developer workflows. Without one owner, nobody is managing the whole bill.

  17. Essay

    Ship the negative path

    Products are usually designed for yes. The no path is where trust is either preserved or quietly burned.

  18. Essay

    The on-call rotation is the org chart

    The real ownership model is not in the planning doc. It is in the list of people who get paged when the system tells the truth.

  19. Essay

    Your database has product opinions

    Schema choices decide what the product can remember, forget, enforce, and explain. That is product work in SQL clothing.

  20. Essay

    The best demo has a log file

    If a demo cannot show what happened under the surface, it is selling magic where the buyer needs machinery.

  21. Essay

    Delete the feature flag

    A stale feature flag is a branch in production. Every branch has a carrying cost, even when the flag is set to true.

  22. Essay

    The model card belongs in the repo

    If a model is part of production behavior, its assumptions and limits should live beside the code that depends on it.

  23. Essay

    The invoice is product feedback

    Billing questions are rarely just billing questions. They are the moment customers explain what they thought they bought.

  24. Essay

    The cheapest scale test is a limit

    You do not need a heroic load test to learn how the system fails. Add a limit and watch what tries to exceed it.

  25. Essay

    Your PR template is a control surface

    A pull request template is not paperwork. It is the cheapest place to make risky changes explain themselves.

  26. Essay

    The cache is a contract

    A cache is not just a performance trick. It is a promise about freshness, invalidation, and what users are allowed to believe.

  27. Essay

    Stop optimizing the empty state

    Empty states are easy to polish because nobody is angry yet. The loaded, messy, half-broken state is where the product earns trust.

  28. Essay

    A good API has one boring path

    Flexible APIs look generous until every customer integrates differently. The best path should be narrow, obvious, and hard to miss.

  29. Essay

    Write the runbook before the incident

    A runbook written after the outage is a memoir. A runbook written before it is a control surface.

  30. Essay

    The agent needs a manager, not a persona

    Giving an agent a personality is easy. Giving it scope, escalation, metrics, and consequences is the actual management work.

  31. Essay

    The first dashboard should be boring

    Your first dashboard should not answer every question. It should make the next bad week easier to understand.

  32. Toolbox

    CLI receipt contract

    A JSON receipt shape for state-changing commands, suitable for logs, support tickets, and rollback notes.

  33. Toolbox

    Goal mandate template

    A pasteable goal block for coding agents that makes the stop condition explicit before implementation starts.

  34. Toolbox

    MCP production dependency policy

    A short policy for allowing an MCP server into a production-adjacent agent workflow.

  35. Toolbox

    Prompt cache audit checklist

    A mechanical review for prompt templates that should hit provider prefix caches instead of paying cold-start prices.

  36. Toolbox

    Worktree agent launcher

    A small shell script that gives each coding agent an isolated git worktree and branch from fresh main.

  37. Steelman

    Managed frontier APIs may keep the long tail

    The local-model argument underweights operations, compliance, and opportunity cost; many teams may rationally keep paying frontier prices for boring calls.

  38. Steelman

    Verbosity can be cheaper than ambiguity

    The essay treats output tokens as waste too quickly; in some agent systems, extra words are the audit trail that prevents a much more expensive support or safety failure.

  39. Steelman

    Kafka buys organizational clarity, not just throughput

    The Postgres-default argument may understate the value of an explicit event log when multiple teams need replay, ownership boundaries, and independent consumers.

  40. Essay

    Secrets are not configuration

    Config explains how a system should behave. Secrets decide who the system is allowed to become. Treating them the same is how quiet incidents start.

  41. Essay

    The calendar is part of the architecture

    A system that only works when one person is online has a hidden dependency. The calendar is where that dependency shows up.

  42. Essay

    Your CLI needs a receipt

    A command-line tool that changes state should leave behind proof. Otherwise every operator becomes a detective.

  43. Prediction

    State-changing AI or ops CLIs will be expected to emit receipts that make later audit possible.

    Prediction opened at 58%, resolves by 12/31/2027.

  44. Essay

    The model switch is a product change

    Changing models is not an implementation detail. It changes tone, latency, failure modes, cost, and sometimes the user's trust.

  45. Prediction

    Teams will increasingly treat LLM model changes as product changes, not implementation details.

    Prediction opened at 64%, resolves by 6/30/2027.

  46. Essay

    Don't hire a platform team to avoid decisions

    Platform teams do not remove product choices. They just make the cost of unclear choices more expensive and more reusable.

  47. Essay

    The migration plan is the feature

    A replacement system is not shipped when the new code works. It is shipped when the old world can move without losing its history.

  48. Prediction

    AI-product teams will treat cache behavior as a product contract because cache misses change latency, cost, and quality.

    Prediction opened at 57%, resolves by 12/31/2027.

  49. Essay

    Latency is a product decision

    Speed is not an engineering vanity metric. It decides which workflows feel safe, which ones feel broken, and which ones users avoid.

  50. Essay

    The second system is a spreadsheet

    The shadow spreadsheet is not a user failure. It is a map of the workflow your product refused to own.

  51. Prediction

    Teams shipping AI features will move model cards or model-behavior notes into the repository alongside code.

    Prediction opened at 55%, resolves by 12/31/2027.

  52. Essay

    The approval button is the product

    If a workflow needs approval, the approval step is not administrative glue. It is the product deciding where trust stops.

  53. Essay

    Your demo is not a deployment plan

    A demo proves the happy path can be performed once. Deployment is the work of making the unhappy paths survivable every day.

  54. Essay

    Logs are a user interface

    Logs are not exhaust. They are the interface your future operator uses when every other interface has stopped being enough.

  55. Essay

    The smallest useful agent

    The useful agent is not the one with the most tools. It is the one with the narrowest job that still removes a human handoff.

  56. Essay

    Stop hiding risk in the backlog

    A risky task does not become safer because you put it below the fold. Backlogs are where uncertainty goes to avoid conversation.

  57. Essay

    The best internal tool is boring

    Internal tools do not need delight. They need memory, defaults, permissions, and a way to undo the expensive mistake.

  58. Essay

    Prompts are interfaces

    A prompt is not a spell. It is the interface between intent, context, and a machine that will happily misunderstand both.

  59. Essay

    Your roadmap needs a trash can

    A roadmap without deletion is just a promise accumulator. The hard part is not adding ideas. It is creating a place for dead ones to stay dead.

  60. Essay

    The status page is a product

    A status page is not a compliance artifact. It is the interface customers use when your product has already failed them.

  61. Essay

    Vibe-coded code has more bugs. Price it in.

    Recent honest data shows AI-assisted code shipping with around 1.7× the rate of major defects. The pitch isn't "ship faster." It's "ship faster, accept the bug tax, decide if it's worth it."

  62. Prediction

    AI-assisted coding will keep showing a higher serious-defect rate unless teams narrow it to well-tested or low-blast-radius work.

    Prediction opened at 62%, resolves by 6/30/2027.

  63. Essay

    Stop calling it context engineering

    The term sounds like a craft. It mostly hides a budget you refused to write down. Call it what it is — engineering with a token budget — and the work changes shape.

  64. Essay

    The 25% rule

    AI can only touch the quarter of your week you spend actually coding. The biggest productivity wins live in the other three-quarters and nobody is selling them to you.

  65. Essay

    The /goal command is a confession

    Coding agents now ship with explicit "set a goal" commands. Last year's pitch was that they figured out the goal themselves. The walking back is real, and worth understanding.

  66. Prediction

    Early-stage teams will keep underinvesting in observability until incidents force the first boring dashboard.

    Prediction opened at 60%, resolves by 6/30/2027.

  67. Essay

    The runway you didn't spend is the option you bought

    We had four hundred thousand left when revenue covered burn. We didn't celebrate. We left it in the account. Eighteen months later that four hundred thousand was the reason we said no to a bad term sheet.

  68. Essay

    Your MCP server is a prod dependency

    We installed five Model Context Protocol servers last quarter and version-pinned none of them. The first outage was educational.

  69. Prediction

    Production agent teams will treat MCP servers as governed dependencies with pinning, scoped credentials, and health checks.

    Prediction opened at 70%, resolves by 3/31/2027.

  70. Essay

    The deploy log is your changelog. Tag accordingly.

    Stop writing changelogs by hand. The deploy log already contains everything that changed. The work is in making the deploy log readable — that's a one-day project, not a process change.

  71. Essay

    Local models won the long tail

    The frontier wins demos. A 70B model on one good GPU wins the two hundred calls per day workflow nobody tweets about. The economics flipped this year.

  72. Prediction

    Local or fine-tuned open models will handle most high-volume narrow LLM calls in cost-sensitive production stacks.

    Prediction opened at 68%, resolves by 6/30/2027.

  73. Essay

    Customer support is product research wearing a costume

    I answered support tickets for the first six months of the company. Then I stopped, and within a quarter we shipped three features nobody asked for. The inbox knew what to build. I had stopped reading it.

  74. Essay

    The eval you don't have, production already wrote for you

    Every customer-reported failure of an LLM feature is a test case you refused to file. The dataset is free; you're throwing it away nightly.

  75. Essay

    Observability is a tax you pay before you owe it

    The first incident is when you discover you don't have logs. The second is when you discover the logs aren't searchable. By the third you have observability, and a story about how expensive it would have been not to.

  76. Essay

    One worktree per agent

    Sub-agents and tool-loop trees are not parallelism. Git worktrees are. The unit of useful concurrency in a coding swarm is the working tree, not the model call.

  77. Essay

    Your first hire is a multiplier or a manager. Pick.

    The two failure modes of first hires are "the second me" who does what I do twice and "the senior person" who manages me instead of working. The good first hire does neither.

  78. Essay

    The output token tax

    Inputs got cheaper this year. Outputs didn't. Your verbose agent is paying both halves of a bill that quietly stopped being symmetric.

  79. Prediction

    Output-token volume will become a named margin-control metric for agent products, separate from input-token volume.

    Prediction opened at 72%, resolves by 3/31/2027.

  80. Essay

    Postgres is a queue. Stop reaching for Kafka.

    A team I know spent six weeks operationalising Kafka for a workload doing two hundred messages per second. Postgres did the same job with forty lines and a SELECT FOR UPDATE SKIP LOCKED.

  81. Prediction

    Postgres-backed queues will remain the better default than Kafka for most internal queues under roughly 1,000 events per second.

    Prediction opened at 66%, resolves by 12/31/2027.

  82. Essay

    Every agent should have a passport

    We onboard humans with identity, scope, audit, and approval. Agents get an env var and a system prompt. The next round of incidents will be about this.

  83. Essay

    Pricing pages are written for people who won't buy

    I spent two weeks rewriting our pricing page. Conversion didn't move. What moved conversion was rewriting the sales email — the document everyone who actually paid had already read by then.

  84. Essay

    The 3-person team is the new 50-person team

    A friend's startup did $4M in revenue last year with three engineers and a tax contractor. Their competitor did $6M with forty-two people. The competitor has more meetings.

  85. Essay

    Your prompt isn't cache-shaped

    I asked a team what their cache hit rate was. The lead said "we cache responses, right?" That single misunderstanding was costing them about fourteen thousand dollars a month.

  86. Essay

    The cheapest dependency is the one you delete

    I removed a logging library last quarter. Build time dropped twelve seconds, bundle dropped four hundred KB, the on-call rotation forgot it existed. We had been paying rent on it for three years.

  87. Essay

    You're optimizing the wrong axis of agent cost

    I watched a team spend a quarter dropping their per-call latency by 40%. The bill kept going up. The bottleneck was never speed.