Live Rung 02 · Be Sellable
Product Readiness · Be Sellable

AI is already choosing products. Make sure it gets yours right.

Connect your catalogue and watch AI shopping agents try to serve realistic customer needs. Herm shows whether they find the right product, answer the questions that matter, trust the underlying evidence and send the shopper somewhere they can actually buy.

Product-feed URL, XML, CSV, JSON, Google Merchant Center or API. Tests repeat on a schedule: read the methodology.

◍ herm · journey replay LIVE
journey 31 / 50 · herm test profile · claude
  1. 01 Shopper need
  2. 02 Agent
  3. 03 Recommendation
  4. 04 Evaluation
Shopper need

“I’ve got rosacea-prone skin and I want to start using vitamin C. I reacted badly to one last year, so I need something that won’t sting. I’d like to stay under £40.”

won’t stinggentle form of vitamin Cfragrance-freeunder £40UKrosacea-prone · first actives
Agent
14 products retrieved · 4 shortlisted
Velora Bright Boost C
fragrance-free · 10% vitamin C in stock · £38.00
Selected
Velora Bright Boost C Intense
Rejected · strength above stated tolerance
Rejected
Velora Clarity C Gel
Rejected · strength above stated tolerance
Rejected
Velora Overnight Repair Mask
Rejected · overnight repair step not matched to a first vitamin C
Rejected
Recommendation

Velora Bright Boost C

£38.00
variant30 ml · fragrance-free
availabilityin stock · UK
velora.com/p/bright-boost-c-30ml
Herm evaluation
Correct category
Correct market
Budget respected
Fragrance-free claim supported
Gentle-form suitability
Tolerance confirmation
Valid retailer destination
Result FAILED
Root issue
Insufficient active-form evidence across 34 variants.
stage 4 of 4 · evaluation
Illustrative shopping test
01 The gap

Your feed can pass every check and still fail the customer.

Feed validation asks whether your information is structurally accepted. It is a necessary check, and it is not the same question as the one a shopper is asking.

Product Readiness asks whether an AI shopping agent can use that information to satisfy a real customer's buying need correctly: the right product, the questions resolved, the claims supported, and a place to buy.

◍ herm · two verdicts
validator verdict ✓ 2,140 / 2,140 accepted · 0 errors
herm verdict ✕ 19 / 50 journeys failed
Technically present
Volume
Strength
Price
Base
Format
GTIN
Structurally complete. Channel-accepted.
Questions the agent must resolve
Will this sting on rosacea-prone skin?
Is the vitamin C a gentle form, or L-ascorbic acid?
Can I use it every night?
Does it suit a barrier that is already compromised?
How does it differ from last year’s formula?
Decision-relevant. Mostly unanswerable.
02 The framework

Four things have to be true for a sale to survive an agent.

Every shopping test is evaluated across the same four stages. A journey that clears three of them still ends in a customer who cannot buy the right thing.

Find 01

Can the agent retrieve the right eligible product?

Evaluated on
customer needcategoryeligibilityvariantmarket
Answer 02

Does the available product information resolve the shopper's important questions?

Evaluated on
decision-relevant questionscoverageevidence source

Agent Answerability lives here.

Trust 03

Can the agent rely on the identity, claims and commercial facts it is using?

Evaluated on
approved claimsevidencepriceavailabilityproduct identitymarketdestination
Close 04

Can the shopper reach an appropriate place to buy?

Evaluated on
valid product URLretailer destinationavailabilitygeography

Close covers reaching an appropriate place to buy: a valid product URL, a retailer destination, availability and the right geography. Herm does not process payment, create carts or execute checkout.

03 The management view

One number for the health of the catalogue. One for the customer's experience of it.

The Be Sellable Score is a diagnostic health view across Find, Answer, Trust and Close. It tells a product team where to work.

The Sellable Intent Rate is the customer-journey outcome: the share of tested buying situations that end with an appropriate, evidence-backed and commercially valid recommendation with a working path to purchase.

Both are reported per market, per category and over time. Scoring weights and thresholds are not published.

◍ herm · be sellable
Velora Skincare · Run 12 · 14 Aug 2026
71
Be Sellable Score
↓ 4 vs run 11
62 %
Sellable Intent Rate
31 of 50 journeys
Find 84
Answer 58
Trust 76
Close 91
Read as

Answer is the weakest dimension and the score fell after a catalogue update. Section 06 shows what a single dimension drop resolves to.

Live product · sample workspace
04 Agent Answerability

See what your product information can answer, and what it cannot.

Answerability measures decision-relevant information, not field completeness. A record can be 100% complete against a feed spec and still leave the questions that matter in real buying decisions unresolved. Select any cell to see the evidence behind it.

Explore Agent Answerability →
◍ herm · answerability · vitamin C serums & active form
6 questions × 4 families
Shopper question
Vitamin C Serums
Barrier Creams
Cleansers
Mineral SPF
A gentle form of the active?
Fragrance-free, or unscented?
Will it sting at first?
Safe on compromised skin?
How does it differ from last year’s formula?
Suitable for nightly use?
Supported Partial Unknown Conflict · review Not applicable
Question → family → evidence

Vitamin C Serums · “A gentle form of the active?”

Unknown
No evidence found
not present in the connected source
not present in approved claims
no product-page equivalent

The agent cannot resolve this question. It will either omit the product or answer from a third-party source you do not control.

Live product · sample workspace
◍ herm · answerability
Vitamin C Serums · 6 shopper questions · 34 variants
A gentle form of the active? 0 of 34 variants unknown
Fragrance-free, or unscented? 34 of 34 variants supported
Will it sting at first? 12 of 34 variants partial
Safe on compromised skin? 31 of 34 variants supported
How does it differ from last year’s formula? 0 of 34 variants unknown
Suitable for nightly use? 18 of 34 variants partial
Live product · sample workspace
05 Brand Intent

Correct according to the catalogue isn't always correct for the brand.

A recommendation can be factually consistent with your feed and still be commercially wrong: the advanced retinoid for the first-time user, the discontinued formulation over the current one, the unapproved claim.

Brand Intent lets you state what correct means. Herm then evaluates both factual accuracy and commercial intent.

Explore Brand Intent →
◍ herm · brand intent
6 active · applied to every test
Never recommend Velora Bright Boost C Intense for an already compromised barrier. Product rule · 1 SKU family On
Velora Clarity C Gel is for oily and congested skin rather than a sensitised barrier. Positioning rule · 6 variants On
Do not use “hypoallergenic” without approved evidence. Claim rule · catalogue-wide On
Prefer the current generation where alternatives otherwise fit equally. Merchandising rule · catalogue-wide On
Sustainability claims must use approved evidence. Claim rule · catalogue-wide On
UK shoppers must not be routed to US-only sellers. Market rule · UK / EN On
Rules are authored by the brand. Herm reports where an agent's behaviour conflicts with them.
06 Diagnosis

Don't stop at “19 journeys failed.” Find the problem behind them.

A list of failures is not a work plan. Herm groups failing journeys into the product-information problem they share, tells you how many products carry it, and what to add.

◍ herm · root cause
run 12 · 3 clusters
Root issue
suitable_foot_shape
evidence incomplete
Affected
214
products
Observed impact
38%
of gentle-form intents affected
Recommended action

Add authoritative form, fragrance and tolerance-study information.

fragrance_declaration incomplete · 88 productsdestination geography mismatch · 12 products
Live product · sample workspace
07 Product enrichment

Turn a failed journey into a better product record.

Each finding carries the products it affects and proposed product-data changes with their evidence. You approve what is accurate, export it, and apply it through the workflow you already use.

Explore Product Enrichment →
  1. 01 Finding 19 failed journeys, one root issue
  2. 02 Affected products 214 products, 34 variants first
  3. 03 Proposed data field-level changes, each with evidence
  4. 04 Review queued for brand review
  5. 05 Approve brand decides what is accurate
  6. 06 Download / export no write-back to your PIM
  7. 07 Source updated, re-test you publish, Herm re-runs the same journeys
◍ herm · proposed product data
34 variants · awaiting approval
suitable_foot_shape · 34 variants THD ascorbate, a buffered form. Declared per variant across 10% and 15% strengths. approved claim register v4 · fit test summary 2025
fragrance_declaration · 34 variants Fragrance-free. No masking fragrance declared in the specification. spec sheet · product page · QA sign-off 14 Aug
intended_use · 12 variants Daily maintenance on an intact barrier. Not intended for post-procedure or broken skin. brand product page · merchandising guidance
Approve Download Export proposed changes

What Herm does not do. Herm does not write into your PIM. Approved changes are exported and applied through your existing product-data workflow. Herm then re-tests the same journeys.

08 Re-test

Fix it. Run the same shopper again.

Readiness is not an audit you pass once. The same buying situation, the same evaluation context, re-run after the product data changes.

This is measured improvement inside the Product Readiness evaluation. It is not a claim about external sales.

◍ herm · journey 31 · run 12 · 14 Aug Before
intentFragrance-free vitamin C in a gentle form, no stinging, under £40
result FAILED
reasonActive-form evidence unavailable for the recommended variant.
agent selectedVelora Bright Boost C
price£139.00
Correct category
Budget respected
Gentle-form suitability
Tolerance confirmation
Illustrative shopping test
◍ herm · journey 31 · run 13 · 22 Aug After
intentFragrance-free vitamin C in a gentle form, no stinging, under £40
result PASSED
changeForm and fragrance evidence added across 34 variants.
agent selectedVelora Bright Boost C · 10% THD
price£139.00
Correct category
Budget respected
Gentle-form suitability
Tolerance confirmation
Illustrative shopping test

Product data updated: 34 variants, form and fragrance evidence approved 22 Aug, re-tested automatically.

09 Commerce channels & monitoring

Sellability changes when your catalogue does.

Herm tracks the environments and standards that decide whether your products are eligible to be sold by an agent. Products change, channels change, and a journey that passed last month stops passing. Herm tests on a schedule, watches for the changes that matter, and raises the ones worth acting on.

Explore Commerce Channels →
GMC Google Merchant Center requirements Tracked standard
OpenAI Commerce and merchant requirements Tracked standard
ACP Agentic Commerce Protocol Tracked standard
UCP Universal Commerce Protocol Tracked standard
+ new Other AI-commerce standards as they emerge Monitored
catalogue changesnew productsproduct-data changesrecommendation regressionsprotocol / channel changesfailing journeysstale commercial datadestination failures
◍ herm · history
last 14 days
  1. 09 Aug Product updated 34 variants changed in the connected source
  2. 09 Aug Test re-run 50 journeys · vitamin C serums & active form
  3. 10 Aug Answerability decreased Vitamin C Serums · gentle-form questions ↓ 11
  4. 10 Aug Alert raised Sellable Intent Rate below threshold
  5. 22 Aug Product enriched form + fragrance evidence approved
  6. 22 Aug Journey passed journey 31 re-tested · same intent ↑ 9
Live product · sample workspace

Tracked, not certified. Herm follows the published requirements of these standards and environments and reflects the relevant ones in tests.

10 AI Commerce Readiness

First be recommended. Then be sellable.

  1. 01 Brand Visibility Live Rung 01 · Be Visible Does AI consider and recommend the brand?
  2. 02 Product Readiness Live Rung 02 · Be Sellable Can AI identify and correctly sell the product behind that recommendation?
Two ways to lose the sale
High Brand Visibility Low Product Readiness

The brand enters consideration, but detailed customer requirements expose product-information gaps.

Low Brand Visibility High Product Readiness

The catalogue would serve the customer well, but the brand is never in the conversation where that would matter.

11 What this is not

Four different jobs. Only one of them is a shopping test.

Adjacent
PIM

Stores and manages product information.

Adjacent
Feed validator

Checks whether the feed meets structural and channel requirements.

Adjacent
Shopping-agent vendor

Builds the consumer shopping experience.

This product
Herm Product Readiness

Tests whether AI agents can correctly use the brand's product information to satisfy customer buying needs.

Common questions

Do you need our product feed?

Yes, for the full assessment. Product Readiness evaluates the commerce and product information a brand actually provides, so it needs a connected source: a product-feed URL, XML, CSV, JSON, Google Merchant Center or an API.

Is this a feed validator?

No. A validator asks whether your information is structurally accepted by a channel. Product Readiness asks whether an AI shopping agent can use it to satisfy a real customer's buying need. A catalogue can pass every structural check and still fail a shopper, which is the case the tests are built to surface.

Does Herm write changes into our PIM?

No. Proposed product-data changes are shown with their evidence for you to approve, and approved changes are exported for your team to publish through the systems you already own. Once the source is updated and re-connected, Herm re-runs the same journeys.

Does a shopping test complete a purchase?

No. Close covers reaching an appropriate place to buy: a valid product URL, a retailer destination, availability and the right geography. Herm does not process payment, create carts or execute checkout.

Does Herm certify compliance with ACP or UCP?

No. Those are ecosystem specifications Herm tracks. Tracking a standard does not mean Herm certifies compliance with it or performs official validation on its behalf. Where Herm has a specific readiness test for a requirement, the result says so precisely.

Are the scoring weights published?

No. The concepts, units and boundaries are public and documented in the methodology. The evaluator, the scoring formula, the weights and the thresholds are not.

See what happens when AI shops your catalogue.

Connect a feed, pick a category, and watch a shopping agent try to serve fifty realistic buying situations.

Sample figures throughout.