Checks hospital invoices automatically for completeness and plausibility.
Developed in Germany · Hosted in the EU or on-premises
Delivered together with
Sovereign hosting in Germany, single-tenant from the first user.
Legal, tax and compliance expertise for legally sound deployment.
Advisory and implementation for the public sector, starting with the AI readiness assessment.
The case is coded, the DRG is determined and the invoice goes out. When a query arrives weeks later, someone has to piece together the file, the coding and the rule as they stood at the time. Until the answer is ready, the amount stays outstanding.
There is no second pass six weeks later if the 18 rules are applied before the invoice goes out, and that is where the 40 to 60% less review effort comes from.
The 40 to 60% reduction in checking effort is this agent's headline figure. The number of rules, the waiting time and the second pass describe a typical query case in hospital billing; they are illustrative, not measured.
The agent reads the case's principal and secondary diagnoses, procedures and supplementary fees and checks them against the stored rules. Every finding is tagged with the rule and where it appears in the file.
Case DRG-2026-11274, 18 rules applied, 2 hitsFor every coded secondary diagnosis, the agent looks for the documented evidence in the progress notes. If the evidence is missing, it flags the code rather than deleting it.
Secondary diagnosis J44.19 with no entry in the progress notes, flagged with page referenceThe agent attaches a note with rules, source references and open points to the case. Correction and dispatch rest with the hospital billing specialist.
abrechnungsnotiz_DRG-2026-11274.pdf, 18 checkpoints, 2 openIt flags the code and names the rule behind it. The hospital billing specialist changes it.
It attaches the note to the case. Approval and dispatch rest with billing coordination.
It compiles the source references for the case. The specialist drafts and signs the reply to the fund.
Connected systems
Operations
A pilot typically runs on your own data within 4 to 6 weeks. The agent connects to your existing systems rather than running as a separate, parallel environment.
EU cloud, private cloud or on-premises. Processing is GDPR-compliant and models are never trained on your data. Details in the Trust Center.
It is based on experience from comparable projects and process benchmarks, not a commitment. We work out the realistic effect for your organisation during the assessment before the pilot.