How Can a Public Agency Answer Every Call if Most Aren’t for It?

Public agencies with a clear mandate attract calls from people who aren’t sure what that mandate is. Some callers have a genuine report. Others want general information, or have a problem that belongs to a different authority. Every one of those calls takes a human agent’s time.

KPK (Komisi Pemberantasan Korupsi), Indonesia’s Corruption Eradication Commission, established in 2002, uses an inbound AI voice agent integrated with AI Rudder’s AI Contact Center to sort those calls first. KPK reports 70% of unnecessary calls prescreened, with the remaining calls transferred to human agents in real time.

The Problem With an Inbound Line Everyone Can Call

KPK’s case study describes two pressures. As a key anti-corruption body, it receives requests for information and complaints by phone. And some callers aren’t fully aware of KPK’s role and the types of cases it handles, which leads to reports outside its jurisdiction and takes time away from the cases that are.

The human agents who should be taking down serious reports also spend time explaining what the agency does and redirecting callers elsewhere. When volume rises, real reports wait in the same queue as everything else.

How the Inbound AI Voice Agent Works

KPK’s solution is an inbound, LLM-powered AI voice agent, integrated with AI Rudder’s AI Contact Center (AICC), that handles the first part of each call.

The agent answers and finds out what the caller needs. When the caller wants general information or has an issue outside KPK’s jurisdiction, the agent can explain and close the call. When the call needs a person, it transfers the call to a human agent in real time, with AICC’s AI and human collaboration passing the context along so the caller doesn’t have to start over.

Because the agent runs on an LLM, it can handle complex questions in natural conversation, and callers say what they need in their own words. And because it is a voice agent, it can take many calls at once, so busy periods don’t build a queue in front of the human team.

What KPK Reports

From KPK’s approved case study:

• 70% of unnecessary calls prescreened
• 100% efficient real-time transfer to human agents
• Human agents can focus on high-priority cases
• A large volume of inbound calls handled simultaneously

For an agency, the third result is the purpose. Prescreening frees the people who handle serious reports to spend their time on them.

Where Else This Pattern Fits

Any inbound line where a large share of calls can be resolved or redirected without a person benefits from the same setup: government hotlines and the service lines of banks, insurers and telcos. Government and public services is one of the industries AI Rudder works with, alongside banking, insurance, telco and logistics.

Questions Agencies Ask About Inbound AI Voice Agents

Can the AI voice agent tell which calls need a person? In KPK’s setup, the agent prescreens calls and transfers those that need a human agent in real time.

Does the caller have to repeat themselves after transfer? AICC is built for AI and human collaboration, with the AI passing context to the human agent at transfer.

Can it handle many calls at once? Yes. KPK reports that the agent handles a large volume of inbound calls simultaneously.

How is security handled? AI Rudder is built to meet SOC 2 and ISO 27001 standards, alongside GDPR and PDPA requirements and relevant IMDA and CSA standards.

Next Step

Look at last month’s inbound calls and estimate how many your team redirected or answered with general information. Get a Demo and we’ll show you how an inbound AI voice agent would prescreen them.