Classify the enquiry
The agent reads the incoming message and assigns it to an enquiry type. It flags anything with a deadline separately.
Received 2026-0913, enquiry type dog licence deregistration, priority normalClassifies enquiries, prioritises cases and drafts well-founded replies.
Developed in Germany · Hosted in the EU or on-premises
Delivered together with
A question about dog licence tax arrives in the shared inbox with no subject line and is passed on by hand. Along the way the text is read several times, and in the end two departments word the same answer differently.
The service centre notices it in its processing time, up to 65% of which goes on forwarding.
The reduction of up to 65% in processing time is this agent's headline figure. The stops in the chain trace a typical route through a front office, not an inbox that was actually analysed.
The agent reads the incoming message and assigns it to an enquiry type. It flags anything with a deadline separately.
Received 2026-0913, enquiry type dog licence deregistration, priority normalThe agent checks the enquiry type against the allocation of responsibilities and names the department. Where two departments could be responsible, it shows both with its reasoning.
Proposed department: tax office, unit 20.3, alternative: citizens' officeThe agent drafts a reply in the authority's house style and files the enquiry, its route and the draft with the case. The caseworker edits it, adds to it and sends it.
antwort_entwurf_2026-0913.txt, 11 lines, 1 form referenceIt presents a draft. The caseworker sends it.
It proposes the department according to the allocation of responsibilities and drafts a reply. The department that signs it off is accountable for its accuracy.
If the sender also rings about the dog licence tax, the agent knows nothing of that call unless someone notes it in the shared inbox or on the case. Its draft is based solely on what is in writing.
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 establish the realistic effect for your organisation in the assessment before the pilot.