Live Rung 02 · Be Sellable
AI Commerce Readiness Test · Product Readiness

See what happens when AI shops your catalogue.

Connect a sample of your existing product catalogue. Herm runs realistic shopping journeys, evaluates whether the agent finds and recommends the right products, and shows the information gaps that get in the way.

The test runs on a sample of your catalogue and does not change your feed, Merchant Center account or PIM.

◍ herm · readiness test · walking & hiking footwear
catalogue sample · UK
58%
Sellable Intent Rate
of tested shopper intents completed correctly
Find 71
Answer 44
Trust 68
Close 79
Journeys failed
5 of 12
Questions unanswered
4
Products behind them
38
Illustrative shopping test. Result contents shown. Scoring, thresholds and evaluator internals are proprietary.
01 What the test actually tells you

A feed-health check tells you whether the data is valid. This test tells you whether AI can use it.

Validation and readiness ask different questions of the same catalogue. One is about structure. The other is about whether a shopper’s need can be satisfied from what the record contains.

The gap. A catalogue can pass the first and fail the second.

Traditional validation
  • Are required attributes present?
  • Are the formats valid?
  • Are identifiers resolvable?
  • Will the channel accept the file?

Answers whether the channel will accept the file.

AI Commerce Readiness Test
  • Can the agent find the right product?
  • Can it answer the decisive question?
  • Is the claim it made supported?
  • Is there a valid place to buy?

Answers whether a shopper’s need can be met from the record.

02 What you connect

Start with the product information you already have.

No new data model, no migration, no preparation project. Connect the feed or file you already publish to channels and the test runs on a sample of it.

Optional, and it improves the test. Herm can start outside-in, and your customer insight makes the test sharper. Don’t have that ready? Start anyway: Herm can build an outside-in test from the catalogue and category context.

Feed URL

The product feed you already publish.

XML

Standard product XML export.

CSV

A spreadsheet export of the catalogue.

JSON

Structured product records.

Google Merchant Center

Read the product data already in your account.

API

Connect directly from your own systems.

Optional · improves the test
ICPCustomer / audience descriptionCustomer researchCommon use casesCategory insightsBuying criteria
03 How the test works

Catalogue in, shopping journeys run, evidence out.

Four steps. Nothing to configure before the first run.

Step 1
Understand the catalogue
Herm interprets products, variants, product information, markets and destinations.
Step 2
Create representative shopping situations
Herm tests customer needs rather than merely checking whether fields exist.
Step 3
Let an AI shopping agent try
The agent searches, compares and recommends from the catalogue.
Step 4
Evaluate the outcome
Herm assesses whether the journey could be completed correctly, and where it broke.
◍ herm · step 4 evaluates
Find · Answer · Trust · Close
Find Was the right product surfaced at all?
Answer Were the questions behind the decision resolved?
Trust Was every claim supported by product evidence?
Close Was there a valid market and purchase destination?
04 One shopping test, end to end

A real customer need, attempted by an agent, evaluated against your product information.

The agent searches, compares and recommends from the catalogue you connected. Herm then checks the recommendation against what the customer actually asked for. Select any evaluation line to see the product evidence it was read from.

◍ herm · shopping test · trail footwear · UK
test 04 of 12
Customer

“I need a waterproof trail shoe under £150 for wide feet.”

AI agent recommends

Trail Pro

£129.00 · in stock · GB
Result FAILED

Authoritative product information does not establish fit suitability.

◍ herm · evaluation line → evidence
5 lines evaluated
Evaluation line → evidence
Product category Supported
Product evidence
Connected product feed product_type = trail running shoe
Product description Off-road outsole, mixed terrain
Herm assessment

The requested product category is stated explicitly in the connected catalogue.

Illustrative shopping test
05 What the result contains

You don’t just get a score. You get the failure.

A readiness snapshot for the sampled catalogue, and underneath it the journeys that failed, the questions that went unanswered and the product information behind both.

Readiness snapshot

Sellable Intent Rate for the sampled catalogue, with Find, Answer, Trust and Close.

Failed journeys

The shopping tests that did not complete, and why each one broke.

Unanswered questions

The buying questions your product information could not resolve.

Evidence

The product records behind every pass and every fail.

◍ herm · root cause
  1. 5 failed shopping journeys
  2. One shared information gap
  3. Fit suitability not published at variant level
  4. 38 products affected
◍ herm · answerability preview
Questions your product information could not answer confidently
Suitable for wide feet?
Heavy rain?
Difference from previous model?
Beginner suitable?

Product Readiness expands this into full Agent Answerability across your catalogue.

Brand Intent · preview

And what if the agent’s answer is factually possible, but wrong for your brand?

Agent recommendsProduct A for running
Brand ruleDo not recommend Product A for running
Brand Intent failure Explore Brand Intent →
06 What happens next

If the test finds a problem, Product Readiness keeps going.

The test is the first run of the same loop the full product operates continuously.

Shopping Tests

Expand the test set across categories, markets and customer situations.

Explore →
Agent Answerability

Find the customer questions your product information leaves unanswered.

Explore →
Brand Intent

Define what commercially correct AI behaviour means for your brand.

Explore →
Product Enrichment

Improve product data, with the evidence behind each proposed change.

Explore →
Re-test

Run the same shopping journeys again and see whether the result moved.

Monitoring

Catch regressions when products, feeds or markets change.

Explore →
07 Scope

Where the test ends and Product Readiness begins.

The test runs on a sample and reports selected findings. The full product runs continuously across the catalogue.

AI Commerce Readiness Test
  • A sample of your catalogue
  • A limited set of shopper tests
  • A readiness snapshot
  • Selected findings with their evidence
Product Readiness · Live
  • Full catalogue
  • Scheduled Shopping Tests
  • Complete Answerability
  • Brand Intent
  • Product Enrichment
  • Multiple markets and environments
  • History
  • Alerts
  • Re-testing
◍ herm · test limits
commercial confirmation required
Test limits, pending confirmation
LimitValue
SKU sample size unset
Number of tests unset
Markets included unset
Test environments unset
Report availability unset
Card / account required unset

The test uses the same evaluation as the full product, on less of the catalogue.

08 Trust & privacy

Your catalogue is commercial data. Treat it that way.

Product feeds carry pricing, margins, ranging and launch information. The test is built to read what it needs and change nothing.

Data modification boundary. The test does not modify your product feed, Merchant Center account or PIM. Product Enrichment may later propose improvements. You review them, download them and update your own source system.

Confirmed
  • The test does not modify your product feed, Merchant Center account or PIM.
  • It runs on a sample of the product information you connect, and nothing else.
  • Proposed product-data changes are exported for you to publish. Herm does not write them back.
Answered specifically

Retention, deletion, model-training use, access and security posture are answered in the policy framework, and by the security team for anything it does not cover.

Questions about retention, deletion, model training and access are answered in the policy framework rather than summarised here. Anything not covered there, the security team will answer directly.

09 Scope discipline

Not another feed validator.

It is a controlled test of whether an AI shopping agent can use the supplied product information to satisfy representative customer needs correctly.

Simulation environment. Herm’s primary shopping simulation environment uses and extends Anthropic’s open-source Commerce Agents reference implementation, providing a real commerce-agent architecture for testing product discovery, comparison and recommendation. Herm independently provides the Product Readiness evaluation, shopper-intent testing, Brand Intent and diagnosis.

A Merchant Center replacement
A PIM
A protocol converter
A feed validator
A certification

Textual attribution only. No partnership, endorsement or certification is implied, and the test is not the live consumer shopping experience of any model provider.

Before you connect anything

What is Sellable Intent Rate?

The share of tested shopper intents an AI shopping agent could complete correctly from the product information supplied.

Does the test change anything in our systems?

No. The test does not modify your product feed, Merchant Center account or PIM. It reads a sample of the catalogue and evaluates what an agent can do with it.

Do we need to prepare our data first?

No. Connect the feed or file you already publish to channels. There is no new data model, no migration and no preparation project, and nothing to configure before the first run.

Is this the same measurement as full Product Readiness?

The same evaluation, on less of the catalogue. The test runs a limited intent set against a sample and reports selected findings; the full product runs continuously across the catalogue with Brand Intent, enrichment, re-testing and monitoring.

Do we need customer research to start?

No. Herm can build an outside-in test from the catalogue and category context alone. Adding your own customer insight makes the test sharper, and it is optional.

Your feed is ready. Find out if AI is.

Connect your catalogue and start the AI Commerce Readiness Test.

Sample figures throughout.