Organises documents and evidence for accreditations.
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.
For the self-evaluation report, module handbooks, examination statistics and graduate numbers are gathered from campus management, document management and the evaluation system. Every figure needs a source, and every source has a different cut-off date. By the time everything is in one place, the first extracts are already out of date.
The quality officer starts the self-evaluation report with an extract that gives the source and cut-off date for each of the 60 indicators; preparation takes her 60% less time.
The 60% reduction in preparation time is this agent's headline figure. For this example, the cluster is assumed to have 68 module descriptions and 31 outstanding pieces of evidence; at another university both figures would differ.
The agent pulls module descriptions, examination statistics and evaluation extracts from the connected systems. For every extract it records the source and the cut-off date.
Re-accreditation cluster 2027, 68 module descriptions, 5 programmesThe agent attaches each of the twelve indicators per programme to the section that requires it. Where a source has a different cut-off date, it writes both dates side by side.
60 indicators assigned, 8 flagged with a differing cut-off dateFor every section, the agent files the evidence with source and reference and lists the open points first. Before approval, quality management assesses which evidence meets a criterion.
selbstbericht_reakk_2027.docx, 5 programmes, 31 outstanding pieces of evidence listedIt submits the draft and the evidence list to quality management. University leadership signs off the report.
It sets requirement and evidence side by side and names every gap. The quality officer makes the assessment.
It only counts a promised professorship once it appears in the staff records. Until then it reports the post as vacant in the resources chapter.
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 or private cloud. 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.