Diagnose the catalog and draft improvements

On this page you can diagnose your Amazon product catalog (product page) and “propose” revisions. The AI does not create or finalize the catalog unconditionally. The flow is always “AI proposes → a human reviews and approves → listing-ready data is output → apply manually in Seller Central / Vendor Central,” and Picaro performs no writes to the catalog (no automatic updates or uploads).

About this page

Item	Details
What you can do	A full diagnosis of the current catalog and a Rufus-perspective diagnosis, improvement proposals for the product title / Bullet Points / product description / Item Highlights, and formatting into listing-ready data for Seller Central / Vendor Central
Applies to	Amazon product catalogs (product title / Bullet Points / product description / Item Highlights)
Data & connection needed	The target ASIN. The AI reads the current product title / brand / category / Bullet Points / product description / image count from the public Amazon product page (supported marketplaces: Japan / US / Germany / UK; default is Japan)
Scope	Proposal and formatting only (read-only). A human applies the changes manually in Seller Central / Vendor Central. Picaro performs no writes to the catalog

Terms used on this page

• Product title … the headline of the product page. The item where you want to balance searchability and identifiability.
• Bullet Points … the bulleted list of the product’s key points. Only the first few lines show on smartphones, so put the most important information first.
• Product description … the body copy that conveys use-case scenes and detailed specifications.
• Item Highlights … an item that conveys key points as short, comma-separated phrases.
• Rufus … Amazon’s generative shopping assistant. It answers shopper questions like “can I use this for X?” or “what size is it?” based on the product information.
• Seller Central / Vendor Central … the admin consoles where sellers and vendors register and edit their Amazon catalog. Catalog changes are applied here by a human.

What can and cannot be retrieved

• Diagnosis is read-only from the public Amazon product page; no catalog writes are performed.
• Price and reviews are not retrieved. For images, only the count is handled — image content cannot be diagnosed.
• Item Highlights are also not retrieved, so if you want them diagnosed, paste the current content (Prompt 6).

Always have a human verify before applying

Before registering proposed copy as-is, a human must always verify the following. The AI flags the parts that need verification, but cannot make the final call.

• Legal and regulatory: applicable regulations such as the Pharmaceutical and Medical Device Act and the Act against Unjustifiable Premiums and Misleading Representations (Japan) (phrasing that touches on efficacy claims or misleading superiority)
• Amazon listing policies / prohibited phrasing: references to price, shipping, or warranty; “No. 1” claims and superlatives
• Brand guidelines: notation rules and tone
• Fact checks: unverified performance figures, certifications, awards, ingredients, country of origin, and compatibility can only be confirmed by the brand

When to use this

• You want to prioritize where to start fixing the current product page
• You want to check, with an eye on exposure and purchase decisions via Rufus, whether the information needed to answer questions is in place
• You want improvement proposals for the product title / Bullet Points / product description / Item Highlights
• You want to line up the current catalog and the proposed version to route to internal review or brand confirmation
• You want to shape approved improvements into a form that is easy to register in Seller Central / Vendor Central
• You want to revisit the product page of a product ad that isn’t getting clicks (often triggered by analysis on a related page)

Before you run

• Target ASIN … have the ASIN of the product you want to diagnose (e.g. B0XXXXXXXX) ready.
• Marketplace … you can specify Japan / US / Germany / UK (default is Japan).
• Current Item Highlights (optional) … if you want Item Highlights diagnosed, have the current content on hand, since they are not retrieved.
• A human applies changes manually … this page goes only as far as proposing and formatting. Character limits, input fields, and category templates differ between Seller Central and Vendor Central and can change, so check the destination’s latest specifications before applying.

Quick reference

Goal	What you get	Changes	Prompt
Run a full 4-lens diagnosis of the current catalog	Per-lens assessment and reasoning with fix priorities	Proposal only	Prompt 1
Diagnose the catalog from the Rufus perspective	Per-item assessment, missing information, and improvements	Proposal only	Prompt 2
Draft product title improvements	Multiple options × reasons for change × needs brand confirmation	Proposal only	Prompt 3
Draft Bullet Points improvements	A current → proposed comparison table × reasons for change	Proposal only	Prompt 4
Draft product description improvements	Improvement proposal × reasons for change × what changed	Proposal only	Prompt 5
Draft Item Highlights improvements	Phrase-format improvements × rationale for adoption	Proposal only	Prompt 6
Compare the current catalog with the proposed version	A per-item current / proposed / reason comparison table	Proposal only	Prompt 7
Format approved improvements into listing-ready data	Listing-ready text and review data	Formatting only / manual apply	Prompt 8

This page goes only as far as “proposing”

As the “Changes” column shows — every row is “Proposal only” or “Formatting only” — this page does not update the catalog directly. A human applies the changes manually in Seller Central / Vendor Central.

---

Prompt 1: Run a full 4-lens diagnosis of the current catalog

Retrieve the current catalog and diagnose it through four lenses: searchability / purchase decision / readability / missing information. As the step before drafting improvements (Prompts 3–6), it prioritizes where to start fixing.

When to use — when you want to set fix priorities before diving into individual improvements.

What you need — the target ASIN. The marketplace (default is Japan).

Retrieve the current catalog for ASIN {{TARGET_ASIN}} and run a full diagnosis.
Use 4 lenses: searchability (how well search keywords are reflected) /
purchase decision (whether the information needed to compare and decide is present) /
readability (structure, sentence length, duplication) / missing information.
For each lens, give an assessment with reasons, and list improvement points
in order of fix priority.

What you can change — the target ASIN (e.g. B0XXXXXXXX) / the marketplace (Japan / US / Germany / UK).

What you get back — an assessment, reasoning, and improvement points for each of the four lenses, plus a prioritized fix list.

Changes — proposal only (read-only, no catalog changes).

Next steps — based on the diagnosis, proceed to drafting individual improvements in Prompts 3–6.

---

Prompt 2: Diagnose the catalog from the Rufus perspective

Diagnose whether the catalog has “information that can answer shopper questions” in place. How complete this is affects exposure via Rufus and purchase decisions.

When to use — when you want to check whether the product information makes it easy for Rufus to answer.

What you need — the target ASIN.

Retrieve the current catalog for ASIN {{TARGET_ASIN}} and diagnose whether the
product information makes it easy for Rufus (Amazon's AI assistant) to answer
user questions.

Diagnosis items:
- Product use cases
- Target users
- How to use
- Size, capacity, materials, ingredients
- Comparison points (differences from similar products)
- Supported environments and compatibility
- Answers to common pre-purchase questions
- Missing or contradictory information
- Duplication across title / Bullet Points / product description
- Coverage of the information needed for a purchase decision

Do not return a score alone — for each item, give the assessment reasoning,
the missing information, the fix priority, and concrete improvement suggestions.

What you can change — the target ASIN.

What you get back — per-item assessment, reasoning, missing information, fix priority, and concrete improvement suggestions. Rather than a score-only answer like a “Rufus readiness score,” it tells you what to fix and in what order.

Changes — proposal only (read-only, no catalog changes).

---

Prompt 3: Draft product title improvements

Diagnose the current product title and propose improvements that balance searchability and identifiability.

When to use — when you want a title that incorporates search keywords without turning into a string of buzzwords.

What you need — the target ASIN. If there are search keywords you want to target, specify them too.

Retrieve the current catalog for ASIN {{TARGET_ASIN}} and propose 3 improved product titles.
For each option, include the reason for the change, the search keywords incorporated,
and the information removed with the reason.
Avoid a string of promotional buzzwords, and stay within the typical character limits.
Do not add claims that have no basis in the current catalog; if you want to include one,
separate it out as "needs brand confirmation."

What you can change — the target ASIN / the search keywords you want to target (add “include ‘XXX’”).

What you get back — improvement options (multiple) × reason for change × supporting information used × items needing brand confirmation.

Changes — proposal only (no catalog changes). Character limits and notation rules vary by category and marketplace, so check the latest Seller Central / Vendor Central specifications before applying.

---

Prompt 4: Draft Bullet Points improvements

Because only the first few lines of Bullet Points show on smartphones, a structure that puts key information first matters. Diagnose the current Bullet Points and propose improvements.

When to use — when you want readable Bullet Points that front-load the important information.

What you need — the target ASIN.

Retrieve the current catalog for ASIN {{TARGET_ASIN}} and propose improved Bullet Points.
Write each Bullet Point in a "headline: body" format, placing the key information first.
Include a current → proposed comparison and the reason for each change.
Do not add claims that have no basis in the current catalog;
separate them out as "needs brand confirmation."

What you can change — the target ASIN.

What you get back — a current → proposed comparison per Bullet Point × reason for change × items needing brand confirmation. The “headline: body” format is the structure recommended in Amazon’s (US) official guidance, and it also helps scannability in Japanese catalogs.

Changes — proposal only (no catalog changes).

---

Prompt 5: Draft product description improvements

Diagnose the product description and propose improvements that avoid duplicating the Bullet Points while adding the story and detailed information needed for a purchase decision.

When to use — when you want to add use-case scenes and detailed specifications while avoiding duplication with the title and Bullet Points.

What you need — the target ASIN.

Retrieve the current catalog for ASIN {{TARGET_ASIN}} and propose an improved product description.
Avoid duplicating the title / Bullet Points, and structure it to add
use-case scenes, detailed specifications, and answers to pre-purchase questions.
Include a comparison with the current version and the reasons for the changes.
Do not add claims that have no basis in the current catalog;
separate them out as "needs brand confirmation."

What you can change — the target ASIN.

What you get back — the improved product description × reasons for changes × differences from the current version × items needing brand confirmation.

Changes — proposal only (no catalog changes).

---

Prompt 6: Draft Item Highlights improvements

Item Highlights convey the product’s key points in short, comma-separated phrases. Place information that did not fit in the title but is useful for search, comparison, and purchase decisions. Current Item Highlights are not retrieved, so paste the current content into the request.

When to use — when you want to supplement, in short phrases, the key points that don’t fit in the title.

What you need — the target ASIN, the current Item Highlights (write “not set” if unset).

Retrieve the current catalog for ASIN {{TARGET_ASIN}} and propose improved Item Highlights.
The current Item Highlights are: {{CURRENT_ITEM_HIGHLIGHTS (write "not set" if unset)}}

Use short comma-separated phrases, prioritizing material / use / usage scenes /
objective comparison features, and as a rule do not include information
that duplicates the title.
Do not include references to price, shipping, or warranty, exaggerated claims, or emojis.

What you can change — the target ASIN / the content of the current Item Highlights.

What you get back — an improved comma-separated phrase list × the rationale for each phrase × a duplication check against the title.

Changes — proposal only (no catalog changes).

---

Prompt 7: Compare the current catalog with the proposed version

Line up the improvement proposals from Prompts 3–6 against the current catalog, item by item. This becomes the review document for approval decisions and brand confirmation.

When to use — when you want to route a document that lines up the current and proposed versions to internal review or brand confirmation.

What you need — nothing (use in the same conversation where the Prompts 3–6 proposals already exist).

Summarize the improvement proposals so far into a comparison table against the
current catalog, item by item (title / Bullet Points / product description / Item Highlights).
For each item, include current / proposed / reason for change / expected effect /
items to verify.

What you can change — the range of items to compare (the proposals present in the same conversation are the target).

What you get back — an item-by-item comparison table of current / proposed / reason for change / expected effect / items to verify. It can be used as-is for routing to internal review or brand confirmation.

Changes — proposal only (no catalog changes).

---

Prompt 8: Format approved improvements into listing-ready data

Format improvement proposals that have passed human review and approval into a shape that is easy to register in Seller Central / Vendor Central. No automatic upload or unreviewed application is performed. Registration is always done by a human in Seller Central / Vendor Central.

When to use — when you want to shape approved improvements into a form that is easy to register.

What you need — the destination (Seller Central / Vendor Central). Use in a conversation where the approved improvements already exist.

Format the approved catalog improvements for easy registration in
{{DESTINATION (Seller Central / Vendor Central)}}. Output the following separately:
- Proposed content (listing-ready text per item)
- Reasons for the changes
- Product information used as the basis
- Phrasing that needs verification (flagged for legal / pharmaceutical / brand review)
- A pre-application checklist
Distinguish the "listing data" from the "review data (with reasons and basis)."

What you can change — the destination (Seller Central / Vendor Central).

What you get back — listing-ready text per item, plus review data with reasons, basis, and verification flags.

Changes — formatting only (no upload or application is performed). Character limits, input fields, and category templates differ between Seller Central and Vendor Central and can change, so always check the destination’s latest specifications before applying. A human applies the changes manually.

---

Related categories

• Find high-performing keywords and product targeting — detect low-CTR product ads (a trigger for catalog improvement)
• Analyze where shoppers drop off from search to purchase (SQP) — find “keywords worth incorporating” from market search terms
• Analyze high-performing search patterns with N-grams — reflect high-contribution search terms in the catalog