GESOBAU resolved 66% of qualified tenant calls with Parloa voice agents

GESOBAU AG, Berlin's state-owned housing association, put Parloa voice agents on its tenant phone line. The agents answer calls around the clock, sort each request, pass emergencies and repair requests to the right people and open tickets in SAP; Parloa reports that 66% of qualified calls are now resolved and 82% of callers are identified automatically.

The problem

GESOBAU manages roughly 48,800 apartments and the portfolio keeps growing, so call volume grows with it: more than 18,000 tenants call every year about repairs, permit applications and rent payments. The company wanted calls answered without wait times, routine requests handled faster, better-quality records of what tenants asked for, and more staff time for complex tenant concerns.

How they did it

1. Write down clear goals before choosing a platform; GESOBAU's included phone accessibility, faster routine inquiries, better recorded information and a searchable record of what tenants call about.
2. Map the existing service processes with an implementation partner (here infinit.cx) and pick the call types the agent should handle: repairs, permission requests such as keeping a pet, rent questions and emergencies.
3. Connect the phone system (Microsoft Teams telephony), backend applications and SAP through APIs so the agent can look up data in real time, trigger processes and update records; GESOBAU's SAP integration partner Datatrain built the central APIs on SAP Business Technology Platform.
4. Design the dialogs and routing: the agent identifies and classifies each issue, resolves it when it can, sends emergencies straight to the emergency team with the full conversation context, forwards repair requests to building managers or service providers, and creates tickets for permission requests.
5. Build fallback scenarios for calls the agent cannot handle and point tenants to forms and information in the existing InfoCenter.
6. Schedule automatic deletion of personal data in call logs to stay within data protection rules.
7. Roll out in stages and use the classified call data to adjust processes and staffing; the next step GESOBAU plans is letting the agent complete more tasks itself, such as sending requested documents.

Results

• 66% of qualified calls resolved, as reported by Parloa.
• 82% of callers identified by phone number or by name and address, as reported by Parloa.
• 354 distinct issues identified and classified since launch, giving GESOBAU a database of phone inquiries for planning, as reported by Parloa.
• Calls answered 24/7 without wait times, as reported by Parloa.

As reported by the source (Parloa customer story); AgentGid did not measure these figures.