Skip to content
Jack Smyth/Differentiation/Facts with Flair
Experiment 01 · differentiation

Facts with flair.

Same product. Same specs.
A clearer reason to choose.

A practical test of differentiation: help a shopping agent see a buying decision, not another list of interchangeable features.

01 / See the difference

A product, reframed.

Eight Australian retailer examples. See the source, the rewrite and exactly what changed before trying your own.

Calming Orthobed - Mink

Snooza · checked 2026-10-29
The source

The Snooza calming Ortho Bed is an orthopaedic mat, designed for dogs who like to sprawl out or curl up. The covers are easily removable and replaceable; the Australian foam base is replaceable; covers are fully washable; and like all Snoozas, this bed is built to last. Non-slip pads are adhered to the base for wooden or tiled floors. The cover is removable and machine washable. It is also replaceable and repairable. Foam can be spot cleaned and is also replaceable.

Open the retailer source ↗
A different frame · same source facts

Treat it as parts, not one wash load.

Treat it as parts, not one wash load. The removable cover is machine washable; the Australian foam base can be spot cleaned, and both cover and base are replaceable. That gives you separate routes for routine cover care and cleaning the foam, rather than one blanket washing instruction. Non-slip pads are adhered to the base for wooden or tiled floors.

Base · Australian foamCover care · machine washableBase care · spot cleanedFloor contact · Non-slip pads
What changed

Turns repeated care statements into distinct cover and foam maintenance routes, with component replacement kept explicit.

  • The removable cover is machine washable; the Australian foam base can be spot cleaned
    Prevents the cover care instruction being mistaken for a whole-bed washing instruction. ShoppingComp: grounding and constraints ↗
  • both cover and base are replaceable
    Makes component replacement an explicit maintenance consideration without claiming cost or environmental savings. OpenAI shopping research ↗
  • Non-slip pads are adhered to the base for wooden or tiled floors
    Retains the stated floor context as a product attribute rather than claiming stability on every surface. OpenAI commerce: beyond copy ↗

Pre-generated with Flint, editorially refined and separately reviewed. This is not the live six-gate QA certification.

02 / Try the same thinking

Your product. The same constraint.

Flint reads the page, writes from its extracted facts, then checks the result. Usually 1–3 minutes. Review before publishing.

Powered by Flint from Springboards

The method is part of the point.

The examples are dated source snapshots, not live prices or stock. Flint drafted; editorial refinement and a separate Flint review improved the framing. No retailer endorsement, market-uniqueness proof or ranking uplift is implied.

Live runs preserve exact source values and return specifications, narrative, three “Why this one” lines, agent-readable attributes and six QA gates. A failed gate stays visible. Automated QA checks the extracted source; it is not independent verification. Page reads and generated output are not persisted by this core app.

The experiment runs here; the existing Facts with Flair service handles page extraction, model calls and signed snapshots. Flint from Springboards provides the generative model. Shopping research and ShoppingComp inform the emphasis on explicit, comparable facts—not a claim that a phrasing change causes better rankings.

Use this experiment with your agent

The identity MCP's get_work tool, id w-fwf, explains the experiment. The Markdown guide and example data expose exactly the same source-backed comparisons.