Draft product copy and normalise attributes against the source documents on file, refuse the values no document supports, and leave certification, warning and origin fields to your compliance specialist.
Collect the product record, supplier declarations, certificates and the taxonomy from supported PIM.
02
Map each incoming value onto the controlled vocabulary, and keep the document identifier that supports it.
Reason
03
Compose the marketing description and bullets inside the claim vocabulary cleared for that category.
04
Treat certification, warning, origin, fibre and ingredient fields as read-only to the agent.
05
Return an explicit unknown wherever no source document establishes a value.
Decide
06
Check the listing against recall feeds, certificate expiries and the destination-jurisdiction matrix.
07
Hand regulated attributes and first publications to the category manager and the product-compliance specialist.
Out
08
Store the prompt, the model version, the source document and the approver against each attribute version.
09
Execute write actions only inside the approval boundaries agreed during implementation.
→Product statement
The agent proposes attribute values with their sources; the compliance specialist sets the regulatory fields, and the category manager owns first publication in a regulated category.
Example workflow
One listing, source to publication
AgentHuman
1Product record receivedPIM entry, supplier feed, seller onboarding form or syndicated content
2Sources gatheredSupplier declarations, certificates, test reports and the taxonomy in force
3Attributes proposedControlled values, drafted copy, unresolved fields and confidence
4Conformance checks runSource-binding checks, recall and expiry checks, jurisdiction checks and confidence threshold
No human action required
Stages 1 to 4 run unaided and nothing is published at any of them — the agent is proposing, and the approver lane opens at the confidence gate.
5DecisionBranches on the attribute gate
Sourced attribute
Goes to the category manager to approve.
Unsourced attribute
Adds a compliance countersignature first.
Category and compliance approval
The listing is held with its source documents, its unresolved fields and the confidence.
Approve · Correct · Send to compliance
Approved — released to publish▼
6Catalogue and channel systems updatedOnly where write access and approval policy allow it
7Listing evaluatedSource-binding rate, corrections made, marketplace rejections and post-publication suppressions
Retractions
Every correction made in approval is counted in the evaluation.
What should not run autonomously
Human approval stays in control
Outside the boundary — human approval required8 items
Setting a certification, compliance or test-result attribute.
Setting country of origin, fibre content or material composition.
Writing or placing any safety or state-mandated warning.
First publication in a regulated category or a new jurisdiction.
Automation boundaryAgent acts unaided
✓Draft marketing descriptions and bullets inside a cleared claim.
✓Normalise and deduplicate attributes into approved.
✓Generate non-regulatory imagery variants with.
✓Reconcile the published catalogue against recall feeds for the named owner.
Any write happens inside the boundaries agreed at implementation, never ahead of the approvers' sign-off.
Naming the manufacturer identity block or the EU responsible person.
Recall, stop-sale, suppression and republication decisions.
Clearing brand-owned copy, imagery or trademarks.
Changes to the taxonomy or its controlled vocabulary.
Example output
One attribute, annotated
Everything the agent proposes is attached to the document that supports it.
Enrichment output · single listingIllustrative example
Listing
Proposed value
Field type
Document of record
Confidence
Approver
Outdoor jacket
Water-resistant to the ingress class stated on the test report
Marketing field
Laboratory test report
87%
Category manager
As receivedTaken from the supplier declaration and the test report on file — nothing on this side is inferred.
Sources usedSupplier declarationLaboratory test reportCertificate of compliance
Why this valueThe report rates ingress, so the wording stays rated and the absolute stays out.
ActionApproveCorrectSend to compliance
What the score decidesBelow the configured threshold the listing picks up a compliance read before it reaches.
Value
Where AI adds value
The same four claims, placed at the point in the workflow where each one applies.
Where the value landsValue 01 – 04
Every listingFrom the record and its documents
03Enrichment
Propose against the source
Draw on supplier declarations, certificates and test reports, and cite the document behind each value.
01Approved path
Say what the product is
Descriptions, bullets and controlled attributes come back drafted and already cited.
02Human review
Put the regulated fields in front
Unsourced values, expiring certificates and regulated categories are flagged, so review starts where warranties attach.
04Build an evidence trail
Each attribute keeps the source that supports it and who approved it.
Integrations
Typical integrations
Five system groups connect to the same agent. Which of them are in scope is decided in discovery.
Integration availability depends on the client's existing systems and API access.
Agent controls
Six layers between the model and the catalogue
Each control wraps the next. The map beneath names what escapes.
L6 · Outermost — last line of defenceInward → L1 · closest to the model
L6Rollback / safe modeHold publication and fall back to proposals when evaluation or production signals degrade.Roll back
L5Version monitoringTrack model, prompt, taxonomy and controlled-vocabulary changes.Track
L4TraceabilityRecord the source document, the proposed value, the approver and the publication time.Record
L3Category approvalHold listings for the named approvers; it governs release, not whether an approved attribute is right.Gate
L2Policy guardrailsTest values against the controlled vocabulary, the source binding and the jurisdiction matrix; a failure returns the listing.Restrict
L1Confidence thresholdsRoute low-confidence listings to a compliance read before the category manager sees them.Require review
Model coreListing produced — controlled values, drafted copy, unresolved fields and confidence
L1 – L2Test whether a listing may stand
L3Puts the release in two named hands
L4 – L5Hold the source behind every attribute
L6Stops publishing and holds drafts
How Nestack evaluates it
Evaluate the whole enrichment path — not only the finished listing.
Coverage runs the whole depth of the workflow, and every layer is cut by slice.
Surface — the listing the shopper reads
Depth of coverage ▼
E1Final-output evaluationDid every regulated attribute trace to an unexpired document of record?
E2Step-level evaluationDid the agent use the current declaration, certificate and taxonomy?
E3Tool evaluationDid it read and write the correct product and the correct field?
E4Confidence calibrationDo low-confidence attributes actually attract more corrections?
E5Slice evaluationHow does performance change across specific product taxonomies?
E6Business outcomeHow many published listings were corrected, suppressed or withdrawn?
Floor — the listing the market reads
Failure modes
Where each failure originates in the agent
Seven modes, from source to published listing.
Agent lifecycleDirection of processing →
01 · Retrieval1 mode
EN-03
Superseded spec sheet
Fibre content and origin are written from a declaration the supplier has replaced.
Stage gathersProduct records, declarations, with the source each came from
02 · Reasoning2 modes
EN-04
Rated value made absolute
A rated ingress class is normalised into a waterproof flag.
EN-06
Family-wide generalisation
One certified variant's hypoallergenic claim spreads across the parent.
Stage proposesControlled values, drafted copy and confidence
03 · Tool / write2 modes
EN-02
Fan-out before review
An enriched set pushes through the PIM to every endpoint ahead of approval.
EN-05
Suppressed listing restored
A catalogue re-sync republishes a SKU sitting under an open recall.
Stage writesOnly where write access and approval policy allow it
04 · Output1 mode
EN-01
Warning in the wrong language
An EU offer carries a machine-translated warning, or no responsible person.
Stage returnsThe listing the approvers sign and the shopper reads
05 · Change / Version1 mode
EN-07
Attribute silently remapped
A schema update moves a certified value into a field that does not mean the same thing.
Stage tracksModel, prompt, taxonomy and vocabulary versions
Sev-1 · a held act performed by the agentSev-2 · a false attribute reaches the catalogueSev-3 · a source degrades
Newly onboarded sellers in regulated categories, listing into Europe and California at once Nestack reports it by slice rather than in aggregate The cohorts that carry it are named, not averaged away..
Slice performance — reported separately, not only in aggregateIllustrative example
Slice
Failure rate
Lift
Lift vs. threshold
Status
New sellers, regulated, EU and California
9.1%
3.8×
Review
Imported goods with no declaration
6.7%
2.8×
Review
Brand-authorised syndicated content
3.6%
1.5×
Watch
Repeat SKUs, certified attribute set
1.2%
0.5×
Normal
Bar: unsourced-attribute lift vs. the all-listing baseline · scale 0–4.0× · tick marks the 2.0× review threshold2 of 4 slices over threshold
Evidence-linked improvement
A cycle ends as a case in the suite
The cycle is over once the miss is a permanent case rather than a remembered incident.
Improvement cycle · five stagesSwitchback — the path turns at Improve and returns at Learn
01Detect
Unsourced attributes concentrate in one taxonomy.
02Diagnose
First the published values are read back against their documents, then the taxonomy version that carried them, until one of the two accounts for it.
03Improve
Version-stamped, with the listings that failed attached to it.
04Verify
Release is conditional on the affected cases passing.
05Learn
It joins the suite and the attribute standard changes with it.
Learn → DetectThe return edge. Each pass begins with more cases in the suite than the one before.
Typical build scope
Twelve workstreams across six weeks
The build scope read against the delivery timeline. Week structure follows the six-week plan — discovery, sources, enrichment workflow, evaluation, integration, then production validation and handover.
WorkstreamWeek 1Week 2Week 3Week 4Week 5Week 6
01Catalogue workflow discovery and boundary definition.
02PIM and supplier-feed assessment.
03Taxonomy, controlled-vocabulary and jurisdiction mapping.
04Product-record and source-document.
05Enrichment logic and source binding.
06Confidence scoring and approval routing.
07Category and compliance.
08PIM, syndication and marketplace integration.
09Attribute regression cases.
10Guardrails and publication.
11Source-trail instrumentation.
12Deployment, documentation and Agent Care handover.
12 workstreams · 6 weeks · bar shows the weeks a workstream is active — several run in parallelFinal scope and sequence confirmed in discovery
Engagement tiers
What each tier includes
Rows are the capabilities named in each tier's scope. Higher tiers include everything below them.
Capability✓ in scope · — not at this tierPilotOne catalogue, one channelProductionProduction catalogue volumeAdvancedMultiple channels / markets
Introduced at Pilot
Enrichment against your sources✓✓✓
Category and compliance approval✓✓✓
Attribute-accuracy baseline✓✓✓
Introduced at Production
Reporting by taxonomy—✓✓
Approval workflow in your systems—✓✓
Approved catalogue write-back—✓✓
PIM integration—✓✓
Introduced at Advanced
Multi-jurisdiction listing rules——✓
Multi-stage catalogue approvals——✓
High SKU volume——✓
Enterprise catalog controls——✓
Build priceFrom $5,000From $8,000Custom quote
Final build priceConfirmed after discovery based on integrations, workflow complexity, transaction volume, approval controls and deployment requirements.
Separate from buildBuild pricing is separate from recurring Agent Care, which covers managed monitoring, evaluations, incidents and verified improvements after launch.
What we need from you
What you bring, and what we build with it
Each input maps to a piece of build scope and a week in the delivery timeline.
You bringWe build with it
01Your taxonomy and its controlled values→Taxonomy and controlled-vocabulary mappingWeek 1
02Representative published listings→Enrichment baseline, normalisation and source bindingWeek 2
03Your supplier declarations and certificates→Source-document mapping and automation-boundary definitionWeek 1
04Access to relevant APIs, feeds or exports→PIM, syndication and compliance assessment, then integration setupWeek 2
05Listings that had to be pulled→Attribute cases and the evaluation suiteWeek 4
06Which attributes may never be generated→Source thresholds, publication routing and controlsWeek 3
07A named category manager to approve attributes→Category and compliance approval workflow, then pilot and production validationWeeks 5–6
Nothing else is requiredDeployment, documentation and Agent Care handover are ours.
Delivery timeline
Four phases across six weeks
Each phase occupies its own weeks, with a genuine overlap in the fifth rather than a padded one.
PhaseW1W2W3W4W5W6
DiscoveryW1
BuildW2 – W3
EvaluateW4 – W5
Pilot & LaunchW5 – W6
Week focusW1Catalogue workflow discovery, taxonomy mapping and the automation boundaryW2Supplier content sources in placeW3Enrichment logic, confidence scoring and publication controlsW4Attribute testing and publication guardrailsW5Syndication integration, pilot listings and targeted correctionsW6One catalogue release approved by the category manager, then handover
Reading the bandEach bar is its named weeks. The fifth is doubled because the work is.
At the end of W6Validated on a real release, then Agent Care carries it.
DurationSix-week plan shown · typical delivery 4–6 weeks depending on scope confirmed in discovery.
Next step · Retail AI agent
Build a catalogue agent around the documents your attributes have to match.
Show us your taxonomy, your source documents and who signs a regulated field. If your certificates, declarations and test reports sit in systems that do not agree, that is the first thing we map, before any attribute is written.
