Skip to content

Engineering lead

Accountable for what shipped, without having watched any of it being written.

Engineering lead

Who this is

The person who is asked on Monday what happened last week and has to answer with something better than a feeling. They did not write the code and did not run the sessions; they are responsible for it anyway.

How they work

By reading. Status, ownership, what is blocked, what is finished, what was decided and why. Every one of those is a question about state, and every one of them is answered today by asking a person who is themselves reconstructing it from memory.

What goes wrong

Status that nobody can reconstruct from the repository. "Done" that means a model said done. Ownership that exists only in somebody's head, so two people are assigned the same work and a third piece of work is assigned to nobody. Three roadmaps that disagree, none of which is wrong enough to delete.

28 moments

Every moment that names this one. Derived from the moments; this page keeps no list.

  1. re-explained the same context to a brand-new sessionRepository knowledge that only ever existed in a conversation has to be re-transmitted by hand to every worker that follows. cost: mediumconstant Why, and what to do →
  2. found two agents fixing the same bug in two branchesTwo workers spend a day each on one defect because ownership was implicit and neither could see the other. cost: highcommon Why, and what to do →
  3. watched the strongest model, at maximum effort, rename a variableCapability, reasoning depth, context size and verbosity collapse into one habit — everything on — because nothing ever named them separately. cost: mediumconstant Why, and what to do →
  4. accepted "done" because the model said so, and paid for it the next morningA fluent completion claim is accepted as evidence because nothing wrote down, beforehand, what would have to be true. cost: highcommon Why, and what to do →
  5. opened CLAUDE.md and AGENTS.md and found two different rulebooks for one repositoryEach provider reads its own hand-edited file, nothing relates them, and which contract applies depends on which tool is open. cost: highcommon Why, and what to do →
  6. watched a session undo last week's decision, for the reason it was madeA decision whose reason lived in a conversation cannot be reviewed, only re-argued — by a worker with less information than the first one had. cost: highcommon Why, and what to do →
  7. found a task "in progress" that nobody had touched for three weeksA status that was authored rather than computed is true at the moment of writing and decays silently from then on. cost: mediumcommon Why, and what to do →
  8. asked what the workers did last night and had only transcripts to grepA conversation log records what was said, not what happened, so the operational question has to be answered by a person reading prose. cost: highcommon Why, and what to do →
  9. read three roadmaps for one project and believed none of themA plan kept in prose is a snapshot, and every copy of it drifts on its own schedule; stored status is an assertion that stays true after the world moves. cost: mediumcommon Why, and what to do →
  10. watched the always-loaded instruction file grow past a thousand linesEverything important gets appended to the always-loaded file, so every session pays for every rule and reads none of them carefully. cost: mediumcommon Why, and what to do →
  11. watched one worker revert another worker's change, on purposeA worker sees an unexplained change in its path, judges it wrong, and removes it — correctly, on the evidence it had. cost: highoccasional Why, and what to do →
  12. found finished work on a branch that nobody ever mergedWorkers produce far more than integration absorbs, and nothing distinguishes work that is done from work that is done and landed. cost: highcommon Why, and what to do →
  13. changed a policy in one place and found the old one still in force in three othersA decision is updated at its source and the generated copies keep serving the previous version, with nothing reporting the difference. cost: highcommon Why, and what to do →
  14. found a rule everyone believed was enforced and nothing ever invokedEvery artefact of enforcement exists — the rule, the script, the test — and no path connects them, so the control is fiction. cost: highcommon Why, and what to do →
  15. found code that contradicted a decision the repository had written downThe decision was recorded and the implementation went the other way, because nothing relates a decision to the paths it governs. cost: highoccasional Why, and what to do →
  16. found a substantial change that no issue, ticket or plan ever asked forWork arrives with no bounded contract behind it, so its scope, its acceptance criteria and its ownership are all decided after the fact. cost: mediumcommon Why, and what to do →
  17. closed an issue whose acceptance criteria nothing had actually checkedCompletion is recorded as a state change in a tracker rather than as evidence in the repository, so the two drift immediately. cost: highcommon Why, and what to do →
  18. was asked how far the milestone had got and had to go and ask four peopleProgress is an aggregate that exists only in people, because the parts it aggregates were never recorded in a form anything can add up. cost: mediumcommon Why, and what to do →
  19. read a promise in the README that no test stood behindA sentence describing what the software does is written once and never connected to anything that would fail if it stopped being true. cost: highcommon Why, and what to do →
  20. had a green pipeline over generated files that no longer matched their sourcesTests exercise the code and say nothing about the committed outputs derived from it, so the build is green and the artifacts are wrong. cost: mediumcommon Why, and what to do →
  21. let a fast, cheap session make a decision the whole codebase now lives withCapability is dialled down for cost and nothing distinguishes the tasks where that is prudent from the ones where it is expensive. cost: highoccasional Why, and what to do →
  22. could not say why one provider was used for that work and another for thisProvider and model selection is made implicitly, per session, and recorded nowhere, so it cannot be reviewed or repeated. cost: mediumcommon Why, and what to do →
  23. looked at the bill and could not say which of it produced anythingConsumption is measured per account and outcomes are recorded per person, so the two can never be joined. cost: mediumcommon Why, and what to do →
  24. lost a failure a worker had already reproduced, because the session endedA failure observed inside a session is described in that session and nowhere else, so the next one starts from the report rather than the evidence. cost: mediumcommon Why, and what to do →
  25. published a page that promised more than any test could supportPublic material is written by a different act from the code, so it drifts ahead of the behaviour and nothing brings it back. cost: highcommon Why, and what to do →
  26. watched a worker spend a day on an approach that had already been ruled outNegative results are the majority of experimental output and the part nobody records, so the search space is re-explored. cost: mediumcommon Why, and what to do →
  27. could not reproduce a result because nothing recorded the state it came fromThe result is recorded and the conditions that produced it are not, so it is an anecdote rather than a measurement. cost: highoccasional Why, and what to do →
  28. was asked who made a change and under what policy, and had only a commitAttribution stops at the commit, so what authorised a change, what verified it and what governed it are unrecoverable. cost: highcommon Why, and what to do →