Live Rung 02 · Be Sellable
Product Readiness · Be Sellable

Give AI the product information it’s missing.

Herm turns recurring Shopping Test and Agent Answerability failures into evidence-backed product-data improvements. Review the proposed changes, update your existing commerce systems and re-run the same journeys to see whether the problem was resolved.

Product Enrichment improves the structured product and commerce information AI systems read when selecting and recommending products: read the methodology.

◍ herm · product enrichment · outerwear
run 12 · UK
Shopping Test 31 Failed

“Find me a waterproof hiking jacket under £200 that works for high-output walking.”

Reason

Agent cannot determine which products are intended for hiking versus casual use.

Root cause
Intended use
missing or ambiguous across 214 products
◍ herm · proposed enrichment · awaiting brand review
3 of 214 shown
Finding, affected products, proposed values and evidence are shown. Root-cause and evidence-selection internals are proprietary.
Proposed value → evidence
Kessock Trail Shell Jacket Evidence verified
outerwear · 3 variants
Intended use · proposed value

High-output hill and mountain walking in sustained wet weather.

Evidence behind this value
Approved product specification membrane, venting and breathability rating
Product document wet-weather guidance sheet v4
Status

Ready for brand review, not published.

Live product · sample workspace
01 Scale of the gap

The same missing fact can break hundreds of shopper journeys.

Product Readiness tells you what failed. Product Enrichment is where the underlying product information gets better, on the brand’s approval and through the brand’s own publishing route.

◍ herm · scale
One missing fact
intended_use
Products carrying it
214
Shopper intents affected
38%
measure act measure
brand approves · brand publishes
02 Diagnosis

Move from failed tests to the catalogue issue behind them.

A list of failed tests is a symptom list. Herm groups them into the product-information issue they share, and scopes it: how many products carry it, and how much of the tested suite it affects.

◍ herm · root cause
run 12 · 3 clusters
Root issue
Intended use
missing or ambiguous
Affected
214
products
Observed impact
38%
of wide-fit intents affected
Recommended action

Add authoritative fit, waterproofing and field-test information.

waterproof_declaration incomplete · 88 productsdestination geography mismatch · 12 products
Live product · sample workspace
03 Scope

What Product Enrichment improves.

Product Enrichment works on structured product and commerce information: the information an AI system reads when it selects and recommends a product.

Product attributes

The structured facts an agent filters and ranks on.

Suitability and intended use

What the product is for, and under what conditions.

Variant distinctions

What actually separates one variant from the next.

Approved claims

Statements the brand has already signed off.

Compatibility

What the product works with, and what it does not.

Commercial eligibility

Market, availability and destination facts.

Product Enrichment

Structured product and commerce information used for product selection and recommendation.

AttributesSuitabilityVariantsEvidenceEligibility
Content Suite

Long-form editorial and web content.

GuidesArticlesExplainersComparison content

The two can complement one another. They are separate engines, and a Product Readiness failure may need one, the other or both.

04 Product level

See exactly what would change on the record.

Every proposal is a field-level diff against the product’s current information. Nothing is hidden inside a summary, and nothing changes until your team approves it.

◍ herm · proposed diff · Kessock Moorland Trek Mid GTX
Current
fitstandard
intended_activityhiking
waterproofyes
weight342 g
Proposed · 3 changes
intended_use new Multi-day hill and mountain walking on mixed terrain.
fit_width new Standard and wide. Last width 105 mm on the wide variant.
endurance new Cushioned for consecutive long days.
Questions this would close
“Is this appropriate for multi-day walking?”
“Do they come in a wide fitting?”
“Are they comfortable over three consecutive days?”

Customer-facing information labels are shown. Internal field names appear only where a brand asks for them.

05 Evidence

Don’t fill gaps by guessing.

Each proposed value resolves to approved evidence. Where nothing authoritative supports a value, Herm does not propose it.

Herm should not convert absence of information into invented product facts. An unsupported value stays unproposed and remains visible as an information gap for the brand to close.

◍ herm · proposed values
4 candidate values on one family
Proposed values with their evidence and status
Proposed valueEvidenceStatus
Multi-day hill and mountain walking on mixed terrain approved product specification · wet-weather guidance sheet v4 Proposed
Wide fitting, last width 105 mm approved claim register v4 · fit test summary 2025 Proposed
Suitable for technical winter ground nothing authoritative addresses winter or technical use Not proposed
Recommended for trail running specification supports it · Brand Intent restricts it Held · Brand Intent

How evidence is selected and prioritised between sources is not published.

06 Sources

Product enrichment should come from information the brand can defend.

You decide what counts as authoritative. Herm proposes from the evidence you supply, and names the source behind every value.

Connected product feed

The catalogue you already publish to channels.

Approved product specifications

The technical record your product team owns.

Product documents

Guidance sheets, manuals and care information.

Brand-approved claims

Statements legal and marketing have signed off.

Market-specific product information

What is true and approved per market.

Only sources supported by the product are shown here.

07 Constraint

Better product data still has to respect Brand Intent.

Evidence can support a use case the brand does not want the product positioned for. Herm does not propose enrichment that violates approved commercial positioning.

The proposal is still recorded, with the reason it was not recommended, so the commercial decision stays visible rather than disappearing.

Explore Brand Intent →
◍ herm · constraint
Proposed value · “Suitable for running” · Kessock Cairn Summit
Evidence
Supported

Approved specification establishes cushioning and outsole suitable for road running.

Brand Intent
Restricted

Do not position this product for running. Approved positioning is hill and mountain walking.

Enrichment outcome
Not recommended for publication
08 Scope

Fix the family, not just the SKU.

Most information gaps are not SKU-specific. Herm identifies whether a proposed value applies to one SKU, a variant, a family or a category, so the work matches catalogue scale.

Where a variant genuinely differs, in insulation, generation or market, the proposal differs with it.

◍ herm · scope · Trail Shell
6 records · 1 proposal set
Where a proposed value applies across a product family
RecordApplies atProposed value
Trail Shell Jacket Family High-output hill and mountain walking in sustained wet weather.
Trail Shell Jacket · Insulated Variant As family, plus cold-weather use down to freezing.
Trail Shell Jacket · 2025 Generation As family. Superseded by the 2026 generation.
Trail Shell Jacket · US Market As family. US sizing and destination.
Trail Shell Pro Family Technical hill walking and scrambling.
Glen Lightweight Shell Family Low-bulk cover for day walks and travel.

Scope is proposed and reviewable. Inheritance logic is not exposed.

09 Review at scale

One diagnosis. Hundreds of products.

Review the whole affected set in one place. Approve or reject each proposal, edit the wording, or filter down to the exceptions that need a person to look at them.

All 214Approved 186Exceptions 7Edited 21
◍ herm · review queue
214 products · 186 approved · 7 exceptions
Enrichment review queue
ProductInformationProposed valueEvidenceReview
Kessock Trail Shell Jacket outerwear · 3 variants Intended use High-output hill and mountain walking spec · guidance v4 Approve
Kessock Trail Shell Pro outerwear · 2 variants Intended use Technical hill walking and scrambling spec · claim register Approve
Kessock Glen Lightweight Shell outerwear · 4 variants Intended use Day walks and travel, not sustained exposure spec · description Approve
Kessock Cairn Summit Mid GTX footwear · 1 variant Waterproofing withheld sources disagree Exception
Kessock Moorland Trek Mid GTX footwear · standard fitting Fit width Standard. Wide available as its own variant. claim register v4 Approve
Live product · sample workspace

Review is per product. Exceptions, meaning conflicts, Brand Intent restrictions and unsupported values, are held back from bulk approval.

10 Approval and export

Herm proposes. Your team decides.

Nothing reaches your commerce systems without a person approving it. Approved changes are exported, and your team publishes them through the systems you already own.

Take the approved changes back to your existing product stack. Herm works alongside your PIM and feed infrastructure rather than replacing it.

Proposed Reviewed Approved Exported Published by you Re-tested
Who reviews
  • Product data
  • Merchandising
  • Legal and compliance
  • Brand
Export formats
  • CSV
  • JSON
  • Feed-ready
  • Per-market split
◍ herm · what Herm does not do today
Write into your PIM or product platform
Publish to your feed on your behalf
Change prices, availability or destinations
Author long-form editorial content

What Herm does not do today. Herm does not write changes directly into your PIM, product platform or feed. Your system stays the record of truth, and your team stays in control of what is published. Once the source system is updated and the new data reaches Herm, the same journeys are run again.

11 The loop closes

Update the data. Ask the same shopper again.

The proof is not that a field was filled. It is that the same shopper journey, run again, reaches the right product for the right reason.

◍ herm · test 44 · run 12 · 14 Aug Before
shopper intent · unchangedWide-fit waterproof trail shoe
result FAILED
reasonWide fitting exists in the catalogue and cannot be retrieved or defended.
agent selectedKessock Trailhead Low
price£110.00 · standard fit
Category fit
Waterproof evidence
Wide-fit evidence
Valid destination
Live product · sample workspace
◍ herm · test 44 · run 13 · 22 Aug After
shopper intent · unchangedWide-fit waterproof trail shoe
result PASSED
changeWide variant published with its own record, fit width stated authoritatively.
agent selectedKessock Trailhead Low Wide
price£110.00 · wide fit
Category fit
Waterproof evidence
Wide-fit evidence
Valid destination
Live product · sample workspace

Product data enriched: approved, exported, published by the brand, then re-tested.

Kessock Outdoor sample workspace. A resolved test demonstrates improved AI shopping performance on the tested journey. It is not a claim about real-world sales.

12 Automatic re-testing

When product information changes, the affected journeys run again.

You do not have to remember which tests were touched by a change. Herm can automatically re-run the affected Shopping Tests and show whether the previous failure was resolved.

◍ herm · automatic re-test
change detected 22 Aug
Affected tests
19
selected automatically from the change
Re-run
19
same intents, same market, same suite
Resolved
16
previous failure no longer reproduces
Still failing
3
cause is not the product information

How affected tests are selected is not published.

13 Honest diagnosis

Not every failed journey is a product-data problem.

Enrichment is applied, the test is re-run, and sometimes it still fails. That result is kept and reported rather than smoothed over.

A still-failing test after enrichment narrows the diagnosis. The information gap is closed, so the cause is somewhere else.

◍ herm · still failing
Enrichment applied Re-test still failing
Brand Intent conflict The recommendation is accurate and commercially unwanted.
Destination failure The purchase path is broken or out of market.
Retrieval behaviour The information exists and the agent did not use it.
14 Answerability

Answerability tells you what’s missing. Enrichment helps supply it.

An unresolved shopper question is the measurement. The proposed information is the action. The question is then asked again.

Explore Agent Answerability →
◍ herm · question → enrichment
Question · “Suitable for wide feet?”
  1. Answerability Unknown. No authoritative width information.
  2. Affected 214 products, 38% of the tested suite.
  3. Proposed Fit width at variant level, with last width in mm.
  4. Evidence Approved claim register v4 · fit test summary 2025.
  5. Re-asked Supported. The question now resolves.
15 Where this sits

Structured product information, long-form content, and your system of record.

Three different jobs that are often confused with one another. A Product Readiness problem may require structured enrichment, long-form content, or both, and neither replaces the platform your product data lives in.

Product Enrichment

Structured product and commerce information used for product selection and recommendation.

AttributesSuitabilityVariantsEvidenceEligibility
Content Suite

Long-form editorial and web content published by the brand.

GuidesArticlesExplainersComparison content
Explore Content Suite →
Your PIM or feed platform

Stores and distributes product information. Herm does not replace it.

StorageWorkflowSyndicationSystem of record

Different infrastructure. Product Enrichment and Content Suite are separate engines that can complement one another. Your PIM or feed platform stores and distributes product information; Herm tests how AI agents use it, identifies gaps, proposes evidence-backed improvements and re-tests the result.

16 Evidence of improvement

One issue, from detection to resolved test.

Each enrichment workstream carries its own history: when the failure was detected, what was proposed, when the brand approved it, when the source data changed and what the re-run produced.

◍ herm · enrichment history · intended use
214 products
  1. 10 Aug Failure detected 19 tests · intended use missing or ambiguous
  2. 12 Aug Enrichment proposed 214 products · evidence attached
  3. 18 Aug Brand approved 186 approved · 21 edited · 7 exceptions held
  4. 22 Aug Source updated published by the brand, re-connected
  5. 22 Aug Re-tested 16 of 19 previously failing tests resolved ↑ 16
Live product · sample workspace
◍ herm · what is reported
Tests resolved
16
of 19 affected
Products updated
214
across 6 families
Questions closed
3
question families

Sellable Intent Rate improved on the affected test set. No claim is made about overall sales.

Kessock Outdoor sample workspace values on one affected test scope. Scoring formulas, weights and thresholds are not published.

Common questions

Does Herm write changes into our PIM?

No. Herm proposes, your team approves, and approved changes are exported for you to publish through the systems you already own. Your system stays the record of truth.

What if the evidence does not support a value?

Then Herm does not propose it. An unsupported value stays unproposed and remains visible as an information gap, so it can be closed with evidence you already hold or deliberately not claimed at all.

Can enrichment contradict our commercial positioning?

No. Where evidence supports a use case that Brand Intent restricts, Herm does not recommend the value for publication. The proposal is still recorded with the reason, so the commercial decision stays visible.

Do we have to review hundreds of products one at a time?

No. The affected set is reviewed in one place, with filtering and bulk approval. Exceptions, meaning conflicts, Brand Intent restrictions and unsupported values, are held back from bulk approval so a person looks at them.

What happens if the test still fails after enrichment?

That result is kept and reported. It is useful: the information gap is closed, so the cause is somewhere else, and the diagnosis narrows.

Is this the same as Content Suite?

No. Product Enrichment works on structured product and commerce data; Content Suite works on long-form editorial and web content. They are separate engines that can complement one another, not a shared generation engine.

Fix the product data behind the failed journey.

Start with one category. See the recurring information gaps, the evidence-backed changes Herm proposes, and what happens when the same shopper asks again.

Sample figures throughout.