Generating a Consistent Enterprise: Synthesis and Reference-Free Evaluation of Multi-System Business Data
Benjamin Gruenbaum and colleagues at Eon describe a generator that builds a complete, internally consistent fictional enterprise across 66 business products with no real dataset behind it, and evaluate realism with reference-free checks fixed before tuning.
Ask this paper
What it generates: From an industry, company size, business model, applications and a seed, it produces a workforce, customers, deals, tickets, calls, chats and documents. One entity graph is projected into the native formats of 66 products so a customer has one identity across CRM, support desk and call system.
Reference-free evaluation: A five-axis scorecard of 28 statistical checks, an adversarial detector for marks of synthetic generation, and soundness checks including a classifier test against a shuffled copy.
Progress under a fixed yardstick: Over 23 generated companies mean realism rose from 60.3 to 99.1 and the weakest company from 41.1 to 94.9. The detector went from flagging 55.2% of records to none, and scores hold on an unseen seed.
Question-driven databases: A second generator builds relational databases from a list of business questions with forced qualifying rows, controlled near misses and exact labels.
Use for agents: Companies are served through simulators over MCP and REST and as container images, which gives enterprise agents a test estate with exact ground truth.
Abstract
Synthetic relational data is normally produced by a model trained on a real dataset, and its quality is measured as the distance to that dataset. This paper describes a generator that has no real dataset at either end. Given an industry, a company size, a business model, a set of business applications, and a random seed, it produces a complete fictional enterprise: a workforce, a customer base, sales deals, support tickets, recorded calls, chat messages, and documents, all consistent with one another. One entity graph is projected into the native formats of 66 business products, so the same customer appears in the CRM, the support desk, and the call system under one identity. Because no real counterpart exists, realism is built in from cited reference statistics and verified by reference-free measurement: a five-axis scorecard of 28 statistical checks, an adversarial detector that hunts for the marks of synthetic generation, and a set of soundness checks that include a classifier test against an independently shuffled copy of the data. Because these instruments existed before the generator was tuned, progress is measured under a fixed yardstick: over 23 generated companies, mean realism climbed from 60.3 to 99.1, the weakest company from 41.1 to 94.9, and the detector, which initially flagged 55.2% of all records, now flags none. The scores hold on a seed never used during development. A second generator builds relational databases from a list of business questions. It forces qualifying rows for each answerable question, adds controlled near misses, and computes exact labels from the finished tables. The generator runs as a hosted service at https://console.era.eon.io. A company built there to a specification is served through its simulators over MCP and REST, and the simulators are also published as container images for offline use