Matching Format to Use, Not Forcing One Format

Choosing the Format Is a Judgment Call

Given the three output surfaces -- inline, Artifact, and structured data -- selecting among them is a deliberate decision tied to how the deliverable will be used, not a habit applied uniformly. Two illustrative failure directions:

• A two-line answer does not need an Artifact -- wrapping a trivial response in a separate editable window adds friction without benefit.
• A polished one-pager that will be iterated on and shared with a client should not be buried in a chat scroll as an inline message -- it needs the persistence and shareability an Artifact provides.

The Exam's Canonical Format Scenario

A one-page proposal that will be refined over several rounds and shared with a client fits an Artifact: a separate, editable, shareable window suited to a substantial, self-contained deliverable. Neither a long inline chat message, raw JSON, nor a single unformatted paragraph serves that same lifecycle.

Forcing Everything Into One Format

The most common failure is defaulting to a single format across every kind of output -- always inline, or always structured -- rather than asking what the specific deliverable needs. A spreadsheet-bound figure forced into prose loses its predictable shape; a two-line answer forced into an Artifact adds unnecessary overhead.

Common exam traps

• Forcing everything into one format. Match the surface (inline vs. Artifact vs. structured) to how the output will actually be used, not to a personal default.