Skip to content

Solo builder

One person, several assistants, and no one else to ask what was decided yesterday.

Solo builder

Who this is

A founder, a hacker, a maintainer of one serious project. They write the architecture and they also run the assistants that implement it. There is no team to absorb a mistake and no reviewer to catch a session that quietly went the wrong way.

How they work

Short sessions, several a day, often in parallel windows against one checkout. Decisions are made in conversation and never written down, because writing them down feels like overhead for an audience of one. The audience of one is tomorrow's session, which remembers nothing.

What goes wrong

Everything that a team would catch by talking. The same context is re-established every morning; a decision made on Tuesday is quietly reversed on Thursday; a task is abandoned mid-way and rediscovered a fortnight later with no record of what state it was in. Nothing here is a model failure. It is the absence of anything durable between sessions.

14 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. 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 →
  6. 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 →
  7. spent an hour discovering something the repository already knew, twiceA worker learns something expensive about the codebase, uses it once, and it dies with the session because nothing turned it into a durable record. cost: mediumcommon Why, and what to do →
  8. found five worktrees and could not say which of them still matteredIsolation is cheap to create and expensive to reason about: nothing records what a worktree was for or whether its work landed. cost: mediumcommon Why, and what to do →
  9. had two sessions writing into one checkout without either knowingTwo workers in one working tree see each other only as unexplained file changes, and each treats the other as noise. cost: highoccasional Why, and what to do →
  10. went looking for why we chose this and found a chat logA decision that was reached in a session is stored where only that session can read it, so it is neither reviewable nor discoverable. cost: highconstant Why, and what to do →
  11. 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 →
  12. 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 →
  13. 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 →
  14. 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 →