jevmodel.org account

Sign in for 100,000 free input tokens

About 500 Jev requests in the playground or from your own code with an API key. Packs start at $9.90 when you need more. No card required.

By signing in you agree to our terms. We only use your email for your account.
Jev Model · Data matching

Entity Matching

Same, different, or worth a human look.

Deduplication pipelines stall on judgment calls: "Acme Inc." vs "Acme Incorporated", same address, different phone. Give Jev both records and get a three-way verdict your merge job can act on.

One statefocused questions
  • Record AName, identifiers, location from source one
  • Record BThe candidate match from source two
  • Match policyWhich fields matter and what counts as conflicting
Structured answersfor your application
  • Match verdictsame · different · review
  • Confidencehow sure the verdict is
  • Merge riskscore: cost of a wrong merge

Try it with your own rules

Start from the preset below, adapt the questions, and inspect the typed answers. Run it live in the playground — it is the same request shape your application will send.

ChoiceAre record_a and record_b the same legal entity?
Yes / NoIs this pair safe to merge without human review?
ScoreHow costly would a wrong merge be for this pair?
Open in playground

What Jev returns

Illustrative output for the preset below — run it live to get real values for your input.

record_a

Nordwind GmbH, Köln — VAT DE812345678 — nordwind.de

record_b

Nordwind GmbH & Co. KG, Cologne — VAT DE812345678 — nordwind-cologne.de

From one example to a reusable workflow

01

Define the policy in the instructions

Say which fields are strong evidence (VAT, domain), which are weak (city spelling), and what counts as a conflict.

02

Split the decision from the action

Use the choice verdict for same/different/review, and the noul only for "safe to auto-merge" — never let confidence alone trigger an irreversible merge.

03

Route the review bucket

Pairs marked review go to a human queue with the full record pair attached — that is where recall lives.

Keep the criteria separate

CheckWhat it measuresHow to use it
Verdict · ChoiceAre the two records the same entity?Three labels: same, different, review — review is a first-class outcome, not an error.
Auto-merge · Yes/NoIs this pair safe to merge unattended?Threshold the noul per field quality; 0.9+ might auto-merge, 0.6–0.9 reviews.
Blast radius · ScoreHow expensive is a wrong merge here?High-value accounts get a stricter threshold than marketing contacts.
01

Why rules alone fail

Exact-match joins miss suffixes and translations; fuzzy thresholds on edit distance merge things that share a name. A typed decision lets you state the policy in words — "shared tax ID is decisive" — and apply it consistently.

02

Keep the gray zone explicit

The difference between a good and a bad matcher is what happens between obvious same and obvious different. A review label routes those pairs to humans instead of silently merging or splitting.

03

Idempotent and auditable

Each decision returns the full probability distribution. Log it: when a merge is disputed you can show exactly which evidence weighed in and how confident the verdict was.

FAQ

How big can the records be?

Both records plus your match policy must serialize under 8,000 characters of state. Company and product records fit easily.

Does this replace my candidate-generation step?

No — use blocking or embeddings to find candidate pairs, then Jev judges each pair. It is a decision layer, not an index.

Can I tune for precision over recall?

Yes — that is what thresholds are for. Raise the auto-merge noul bar and let the review bucket absorb the rest.

API keys

Call Jev with your key.

Send state plus typed questions to the local Jev endpoint. Successful requests charge input tokens. Add an Idempotency-Key header when retrying.

+ New key