Pre-sorts calls, emails and requests overnight; decisions are made in the morning.
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.
Everything comes in through one central number and a few mailboxes. Every message is read, matched to a request type, assigned to a case and forwarded to the right team. The reply often takes two sentences after that; the routing before it takes longer.
By 06:00, before the first call comes in, Monday's 140 messages are sorted into nine request types, with up to 70% less manual routing effort.
The reduction of up to 70% in manual routing effort is this agent's headline figure. The number of messages, the request types and the assignment time describe a typical Monday in the service centre; they are not measured values.
The agent reads the messages from the mailboxes and the fax inbox and assigns each one to a request type. Anything it cannot assign with confidence goes into a separate pile.
Received by 06:00, 140 messages sorted into 9 request typesThe agent finds the matching case for every message using patient number, name and reference date. If it finds none, it notes this on the message.
128 messages assigned to a case, 12 without a matchThe agent writes a draft for recurring requests and attaches it to the case. The inbox specialist reads, edits and approves it.
37 drafts in the work queue, each linked to its source messageIt files the draft with the case. The inbox specialist approves and sends it.
It flags requests with a medical element and passes them to the responsible department. The care team provides the information.
It recognises them as complaints and puts them at the top of the pile. Patient management writes the reply.
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.