Chapter 07 ← Home

Failure modes

Eight ways this goes wrong, each with its fix — including the one that only shows up after you export.

A field guide that only lists strengths is advertising. Eight things worth knowing before you stake a deadline on this, ordered by how often they actually bite.

FailureSeverityWhat happensThe fix
Export shockHigh The design is perfect in the browser and degrades on the way to PPTX or PDF. Name the destination in the first prompt and design within its grammar.
Specifying, not briefingHigh You list contents, get a competent arrangement of them, and cannot tell whether it works. Name the reader, the moment, and the one thing it must not fail at.
Re-prompting the whole thingMedium A small local problem triggers a full regeneration, losing everything that was already right. Comment on the element. Reserve conversation for structural change.
Stale design systemHigh Every output inherits it, so the whole team produces confidently off-brand work at speed. Curate it like the shared asset it is; re-point Claude at the codebase after a rebrand.
Prototype mistaken for productHigh It looks real enough that someone senior assumes it ships next week. Label it on share. One sentence, every time.
Exploration budget burnMedium A dozen directions consumes usage like a dozen directions, mid-deadline. Explore wide early, narrow before the expensive revisions start.
Wrong surface entirelyMedium A settled design gets rehearsed on a canvas, or an open question goes straight to Code. Three questions before you open anything.
Preview driftLow A behaviour you built a team ritual on changes underneath you. Treat capabilities as dated. Re-audition rather than trusting your memory of them.

The three that are structural

Most of the table is operator error and yields to a habit. These three are properties of the product, and no amount of skill removes them.

Not a flaw

A prototype is a performance

No production data, no auth, no backend. It looks real and is not — that is the point, and it is exactly what makes it cheap enough to throw away. The hazard is entirely in how it is received.

Manage itSay what it is when you share it, every single time.
Instrument limit

It authors; you direct

No layers panel, no pen tool, no hand-built component library. For pixel-level typographic control or illustration, this is a different instrument — a good one, but not that one.

Manage itUse it to get to a strong draft, then finish in the tool that does the craft.
Moving target

It is a research preview

Anthropic Labs ships it with limits, and capabilities and integrations keep landing. Expect the product to shift under you.

Manage itDo not build a team ritual on a behaviour you observed once.

The field guides

Seven guides, one method. Roughly in the order a reader meets them: how the field got here, how to work across models, then the tools themselves.