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.

The Ordinary Niacinamide 10% + Zinc 1% 60ml

THE ICONIC · checked 2026-10-29
The source

The Niacinamide 10% + Zinc 1% 60ml formula by The Ordinary incorporates a high 10% concentration of Niacinamide, as well as a 1% concentration of Zinc to balance visible aspects of sebum activity, thereby reducing the appearance of textural irregularities, enlarged pores and visible shine. Note: Niacinamide is not a treatment for Acne. For persistent Acne-related conditions, we recommend consulting a Physician. Apply to entire face morning and evening before heavier creams.

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

For visible shine—not acne treatment.

A formula for visible shine—not an acne treatment. In this 60ml bottle, 10% Niacinamide and 1% Zinc work together to balance visible aspects of sebum activity and reduce the appearance of textural irregularities, enlarged pores and shine. Place it in your routine before heavier creams, morning and evening, applying to the entire face. For persistent acne-related conditions, consult a physician.

Niacinamide concentration · 10%Zinc concentration · 1%Size · 60mlUse · before heavier creams
What changed

Puts the cosmetic-versus-treatment boundary beside the benefit, then connects concentrations and application order to the routine.

  • visible shine—not an acne treatment
    Separates the cosmetic appearance goal from a medical-treatment claim at the point of choice. ShoppingComp: grounding and constraints ↗
  • 10% Niacinamide and 1% Zinc
    Presents the concentrations together as a formula shoppers can match to ingredient preferences. OpenAI shopping research ↗
  • before heavier creams, morning and evening
    Keeps application order and timing explicit as usage attributes, alongside—not instead of—structured product data. 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.