Topic hub
Product identity
A multi-supplier catalog never lacks identifiers. It has too many: the same contactor or bearing arrives as four strings from four feeds. Product identity is the single resolved entity those records point at, and every downstream job (write-back, deduplication, price comparison, compatibility, AI agent answers) depends on getting it right.
Start with the definition, then move through how identity is resolved, how the decision is stored so it survives the next feed, and how to judge whether a tool or process really produces it. Each page links back to the Product Identity & Evidence Graph, the model that ties them together.
Start here
The concept and the model behind it.
-
Glossary
What Is Product Identity?
Product identity is the resolved entity behind a product's many SKUs, MPNs, GTINs and supplier records. Not a SKU, not a GTIN, not a match score, and the prerequisite for write-back and trustworthy AI agents.
-
Guides
Product Identity & Evidence Graph: Products Aren't Rows
Products aren't rows. They are entities connected to suppliers, variants, documents, attributes and evidence. How Claro resolves fragmented records into a graph your ERP, PIM and AI agents can trust.
-
Glossary
Golden Record Product Data: What Is a Canonical Product Record?
A canonical (golden) record is the single trusted version of a product. Learn how golden record product data powers dedup, enrichment, and AI search.
How identity is resolved
Matching methods, thresholds and the vocabulary of record linkage.
-
Glossary
What Is Entity Resolution?
What is entity resolution? A plain-language definition for product-data teams, with cross-industry examples of how it powers matching, dedup, and AI search.
-
Glossary
What Is Record Linkage?
Record linkage matches product records across supplier feeds, ERP exports, and PIM tables that refer to the same SKU. Plain-language definition with examples.
-
Glossary
What Is Fuzzy Matching?
What is fuzzy matching? A plain-language definition of approximate string matching, how it scores near-identical product records, and where it fits in catalog data.
-
Glossary
Deterministic vs Probabilistic Matching
When to match product records on exact keys and when to score similarity — practical guidance for messy supplier feeds and multi-source catalogs.
-
Glossary
Confidence Score in Data Matching: A Practical Guide
Learn what a confidence score in data matching is, how thresholds work, and why calibration determines whether automated matching is trustworthy.
-
Articles
How Product Matching Actually Works at Scale (and Why LLMs Alone Aren't Enough)
Matching the same product across messy supplier feeds is the hard problem behind every clean catalog. Deterministic vs probabilistic methods, confidence, and why an LLM on its own won't get you there.
Identifiers and why they are not identity
SKUs, MPNs, GTINs and the industrial edge cases.
-
Glossary
SKU vs MPN vs GTIN: What Each Identifier Does and Why All Three Matter
SKU vs MPN vs GTIN explained: who owns each code, how they differ, and why confusing them breaks matching, dedup, and enrichment.
-
Articles
One Product, Five Part Numbers: Why Industrial Product Identity Is So Difficult
Industrial product identity is not fuzzy matching. Learn how MPNs, supplier SKUs, distributor SKUs, packaging codes, replacements, and alternatives relate.
-
Playbooks
How to Group Product Variants Into One Family
A cable gland in five sizes shouldn't be five unrelated catalog entries. Here's how to structure variants so search, filtering, and inventory all make sense.
Making identity durable
Storing decisions, keeping the near-misses, remembering.
-
Glossary
What Is a Product Identity Graph?
A product identity graph turns one-off record matching into persistent identity knowledge: a canonical product linked to SKUs, MPNs, suppliers and documents with scored edges, including NOT_SAME_AS, that survive re-ingestion.
-
Articles
Product Matching Should Produce Knowledge, Not a Score
A 94% match leaves nothing behind for the next ingestion. A SAME_AS relationship with evidence, a confidence score and a reviewer compounds. Why matching output should be durable, and near-misses kept.
-
Articles
From Product Record to Product Memory
A record says what is true now. Product memory says why, since when and on what evidence. The case for canonical records that keep history, sources and decisions, and what that unlocks.
Identity for AI agents
Why agents need resolved entities, and what changes when they get them.
-
Articles
Entity Resolution Is Becoming Infrastructure for AI Agents
AI agents need to resolve product identity before they select, update, quote, or recommend. Learn why entity resolution belongs in the agent execution path.
-
Articles
Agent Identity vs Product Identity in Agentic Commerce
Know Your Agent establishes who may transact. Product identity establishes the exact product, variant, pack, SKU, and offer the authorized agent is acting on.
Evaluating tools
What to ask before you buy matching or resolution software.
-
Guides
How to Evaluate Product Matching Software: 12 Questions to Ask
Evaluate product matching software on difficult records, calibrated confidence, evidence, review workflows, reversible decisions, and safe write-back.
-
Guides
Why Product Matching Looks Easy in a Demo and Falls Apart in Production
A three-tier framework for evaluating product matching against clean identifiers, messy supplier data, and products with no shared identifier at all.
Related topic hubs
Claro
Stop maintaining this by hand
Claro keeps product and supplier data trusted as catalogs change — matching, deduplication, enrichment, and validated write-back into the systems you already run.
Book a demo