Introducing Schema-2
August 7, 2026
Schema-2 is a Data Language Model: AI that understands business data directly. It takes tables and databases as they are, across any number of sources, and returns what the data is, how the sources relate, what is missing, and what can be predicted from it. No shared keys, no labels, no preprocessing step.
Schema-2 is available to use starting August 13, 2026, through the SchemaLabs API, platform, and supported third-party registries. Rates are in Pricing.
Every AI initiative built on business data begins the same way. Before a model can run, someone has to establish what the fields mean, how the sources relate to one another, which records can be trusted, and what the model should predict. That work is repeated for every new source and every new project, and it is the step that most often stalls the initiative.
Schema-2 performs it in a single call, on the data as it stands.
Multiple tables that share no key. One request.
The data stays as it is. The understanding happens inside the model: no mapping, no labels, no preprocessing.
| full_name | phone | signup_date | |
|---|---|---|---|
| Ana Kaya | 555-0142 | ana.k@… | 2024-11-03 |
| Devraj Nair | 555-0199 | d.nair@… | 2024-12-01 |
| Mira Ostrom | 555-0210 | null | 2025-01-17 |
| holder | phone_e164 | card_brand | credit_limit |
|---|---|---|---|
| KAYA, ANA | +1 555 0142 | Visa | 12000 |
| NAIR, DEVRAJ | +1 555 0199 | Mastercard | 6500 |
| OSTROM, MIRA | +1 555 0210 | Amex | null |
| c1 | c2 | c3 | c4 |
|---|---|---|---|
| +15550142 | 34.90 | 5812 | 04/01/25 |
| +15550210 | 1290.00 | 5732 | 09/01/25 |
| +15550199 | 12.40 | 5411 | 11/01/25 |
Vertical and agentic AI cannot wait for business data readiness
A vertical AI meets customer's raw data on the first day of onboarding; AI agents meet new sources mid-task, at runtime, with nobody available to explain it. Neither can pause for a quarter while a data team prepares that data, and no human team can sit inside an inference loop.
Performance, measured
Benchmark summaries below. To review all results in full detail, protocols, datasets, per-dataset tables and competitor sources, go to the Schema-2 model card.
Given a table it has never seen, with column names removed and no documentation, Schema-2 names the industry sector from cell values alone. Correct on the first attempt in 86.3% of cases.
Use it forCataloguing a data lake, routing incoming files to the right pipeline, triaging a new dataset before anyone opens it.
Systems that depend on column names lose roughly seven points of accuracy when those names are absent, obscure, or stripped for privacy. Schema-2 does not move.
Use it forLegacy systems, acquired databases and anonymised exports, with no renaming project or data dictionary needed first.
The same customer in two systems that never shared a key. Schema-2 leads the published state of the art on all six standard datasets. On Person, the hardest, it reaches 79.1 against 41.8.
Use it forCustomer deduplication, post-acquisition record merges and supplier consolidation across systems with no common ID.
Which column here corresponds to which column there, decided from the values alone. Every published matcher reads the schema names. Schema-2 does not, and still leads all four scenarios.
Use it forData migrations, warehouse consolidation and partner integrations where the column names do not line up.
Point estimate says a claim will cost $1,200; distribution says how likely every other outcome is. Across 102 datasets and 51 models, Schema-2 places first, with a 4.4x margin.
Use it forPricing, demand planning, reserve setting and risk, where you need the range and not a single number.
Training and serving data going incomplete in different ways at the same time, which is what production actually does. Schema-2 holds the top mean across the grid, narrowly.
Use it forProduction scoring where fields drop out, sensors fail or forms arrive half finished.
Averaged over nine ways of hiding data across twenty real datasets, Schema-2's reconstructions carry 1.8x less error than the next best frontier LLM and 2.3x less than the best classical method.
Use it forRepairing partial records before they reach a report, a downstream model or a regulator.
A missing diagnosis code or an empty churn flag cannot be averaged in, and filling with the most common value erases the rare categories that carry the signal. Schema-2 beats that floor on all eight datasets.
Use it forMissing diagnosis codes, blank churn flags and unset status fields, where the rare category is the one that matters.
Zero-shot: no labelled examples of anomalous rows are required. Schema-2 leads the 57-dataset standard suite, though the top of this field is closely grouped, and the chart shows that.
Use it forFraud screening, equipment monitoring and data-quality checks with no labelled history to train on.
After fifty fine-tunes on fifty different domains, one after another, Schema-2 keeps 80.3% of what it could do on each. A gradient-boosted stack keeps nothing: it is rebuilt from scratch every time.
Use it forOne endpoint that follows the business into new products, regions and datasets instead of a rebuild per use case.
The model card has the full record
Protocols, per-dataset tables, every competitor source, the four benchmark families this post omits, and the limitations in full.