Not every step needs the expensive model
Tier selection is not a preference, it is a function of three facts about the task. Two platform constraints rule out most of the combinations you would guess.
orchestration
8 posts
Two agents, one working tree, one disaster
Parallel agents sharing a working tree corrupt each other silently. Worktrees fix it, and cost 4.3 seconds and 364 MB each — not the 200ms the contract claims.
Where your AI coding bill actually goes: I measured one long session
22 articles and 110 generated assets in one session. What the retries cost, and the one change that cut attempts per asset from roughly 1.8 to 1.1.
Put the control flow in code, not in the prompt
Sequencing belongs in a script and judgement in the model. One routine commit cost 180k tokens as reasoning and seconds as bash. Here is the line.
Where to put the human
Gate placement for autonomous agents. Reversibility is the criterion, not confidence, and the consent surface matters as much as the question.
One level of fan-out, and why that is enough
A subagent cannot delegate, so the top session is the only scheduler. Designing around that, and why a barrier between stages costs more than it looks.
What to log when the actor is a model
Agent telemetry that survives the session: log the measurement rather than the verdict, and build a schema with no slot for the things that must not travel.
Teaching an agent when to stop
Enumerated halt classes make stopping checkable; a mood does not. The forbidden reasons that stall a drive, and the undeclared halt I made anyway.