Skip to content
Close
SEARCH
Get a demo
Get a demo

The data your AI needs, maintained by the people who know it

Trusted data, intelligent assistance, agent-ready. Business teams maintain the mappings, classifications and parameters that models and agents run on, directly in the enterprise data platform, validated at entry and on the record.
Get the deck
Get a demo

The context only your business teams can provide

AI agents and models need more than raw data. They need business-owned reference data that changes often and today lives in spreadsheets: mapping rules, labels and thresholds, lookup references, decision inputs. NextTables lets the people who understand that logic maintain it directly in the platform, so agents and models consume context that is current and structured.

What agents consume at inference time

Cross-table mapping rules, business-defined labels and thresholds, lookup references that connect datasets, and structured decision inputs that tell an agent how to interpret and act on data. With them, an agent reasons from your rules.

What models consume for training and evaluation

Threshold definitions, scoring weights, simulation parameters, calibration values and reference hierarchies, maintained as tables rather than assumptions buried in a notebook. With them, models train on current inputs.

Maintained where AI already reads

The context tables live in SAP Business Data Cloud, Databricks or PostgreSQL, next to the data they describe. A business user maintains them in the grid or a form, with value help against your master data, and the change is available to every model and dashboard at once. The master data can live in the same platform or in another connected one. What the grid and the forms look like: Built for business teams.

A mapping table maintained in the NextTables grid

Trusted by design

Because every value maintained through NextTables is validated at entry, controlled by enterprise access rules and recorded in an audit log, the data is usable as AI input as it is; the cleansing, reconciliation and provenance work is done at entry. The mechanics: Governed.
Diagram: a business user, an AI prompt and an AI agent all write through the same NextTables gateway, where every change is validated at entry, authorized down to the row and recorded in the audit log before it reaches the enterprise data platform; the two AI paths, rollback and approval are marked as on the roadmap

  1. Validated at entry

    Checked against your master data and your rules before it is written, so a model trains only on values that passed the check.

  2. Authorized down to the row

    Roles scoped to folders and row-level rules decide who may maintain which context, the same way they decide it for every other table.

  3. On the record

    Who changed which value, and when, sits in the audit log inside your platform, so a model's inputs can be traced to a person and a date.

  4. Platform-resident

    The tables live where your models read, in place and as the only copy, and a change is visible at once.

Intelligent assistance, on the way

NextTables is evolving to let AI assist the people who maintain data and the people who build the apps. In both cases AI proposes and the user confirms. Both items are marked Coming Soon

Talk to AI to edit your data

Coming Soon

AI is designed to assist with data maintenance through natural-language prompts: finding records, updating values and applying rule-based mass changes across many rows, with confirmation before every change and safe rollback at any point.

Talk to AI to create your data entry app

Coming Soon

AI is designed to assist across the lifecycle of an app: generating validation logic, creating tables and configurations, assembling a complete application. Every proposed object is reviewed and approved before it goes live.

A governed gateway for AI agents

Coming Soon

As organizations deploy agents that read and write data, the question becomes how an agent writes to the platform safely. NextTables is designed to serve as that gateway: agent-driven updates follow the same validation, authorization and audit log as a person's, and where governance requires it they wait for a human to approve.

Same rules as a person

An agent's write goes through the same validation at entry and the same roles and row-level rules a human user is subject to.

Human in the loop where it matters

Which agent actions pass automatically and which need a person to review and confirm is a decision your team makes, per action.

On the record

Agent-driven changes land in the audit log like every other change, so an agent becomes a traceable channel for data maintenance.

Frequently asked questions

1. Which data is this about?

The context data AI depends on, still waiting for an owner end to end: semantic mapping tables for agents, classification and labeling tables for models, entity resolution references, threshold and rule tables, and the metadata that grounds a prompt.
2. Do we need AI features to use NextTables?

Everything on this page except the two assistance items and the agent gateway is how NextTables works today, and the value for AI comes from data that is maintained, validated and on the record.
3. Where does the maintained data live?

In your enterprise data platform, in the schema your administrator scoped. NextTables keeps configuration metadata only, so models and agents read the platform itself.
4. How do the AI assistance items keep a person in control?

They are designed so that AI proposes and the user confirms, every time, with rollback of any change.
5. When do the marked items arrive?

They are on the product roadmap and marked as such wherever they appear. Release notes and product updates go out by email; sign up on the product updates page.

Bring the table your model is waiting for

Half an hour on the mappings, thresholds and references your AI initiative still keeps in a spreadsheet. Or take the deck to the team first.

Get the deck
Get a demo