Agent routing or picking the model yourself
Three job types where an agent's model choice predictably goes wrong, and how to pin a named model in the brief without giving up routing everywhere else.
Three job types where an agent's model choice predictably goes wrong, and how to pin a named model in the brief without giving up routing everywhere else.
Inspect the agent's proposed tool steps, drop the ones you do not want, and only then dispatch. Nothing generates until you approve.
Conversations are addressable objects with list, get, clear, and share endpoints. Audit agent history in code, or build your own review view over it.
A stalled agent turn is usually a missing required input, not a bad prompt. Diagnose the tool schema and model preflight before rewriting anything.
Which video edits are faster described in a sentence and which have to be built on a timeline, judged on precision, reproducibility, review and rollback.