Skip to content
AtomicReps

Navigation

23/23Product

Working with Coding Agents.

The delegate-and-supervise discipline of working with autonomous coding agents: when to delegate, scoping work, spec-driven development, instruction files, managing long-run context, reviewing agent-authored PRs, agent failure modes, permissions/sandboxing, verification & accountability, fleet supervision, and honest impact measurement. Distinct from ai_dev_workflow's in-loop AI-assisted craft (boundary = unit of delegation).

  • Working with Coding Agents · 1 of 3

    Spec-Driven Development

    In an agent workflow, where is the least expensive point to inject human judgment and change the direction of the work if needed?

  • Working with Coding Agents · 2 of 3

    Agent Failure Modes

    Asked to fix one null check in auth.ts, an agent returns a 40-file diff: the fix, plus renamed variables and reformatted modules that have nothing to do with auth. Its summary mentions only the null check. Which failure mode is this?

  • Working with Coding Agents · 3 of 3

    Agent Failure Modes

    While fixing a build error an agent inserts array.flattenDeep() in plain JavaScript and says it is standard. The tests then fail with TypeError: array.flattenDeep is not a function. Which failure is this?

Three of the 100 Working with Coding Agents questions.

Keep going with Working with Coding Agents, free
Next pathMobile.23 topics