The voice assistant that finds the shipment by tracking number and passes address change requests to operations
For customer service and operations teams: shipment enquiries go to the assistant; requests that depend on the delivery stage go to operations with the reason.
Common problems on the phone line
Tracking questions fill the line
“Where is my shipment?” calls come in all day, and operational questions wait in the queue.
Last-minute address changes
When a request for a shipment already out for delivery reaches the right team too late, the delivery attempt is wasted.
Delay and damage reports are scattered
Reports taken over the phone reach the team without being matched to the shipment record.
How it works in this sector
Every call follows the same four steps; the assistant acts only with defined permissions.
- 01 / 04
Greets
Greets the caller and listens to the tracking number and request.
- 02 / 04
Understands and verifies
Verifies the shipment details.
- 03 / 04
Takes action
Checks the shipment status and whether a change is possible.
- 04 / 04
Confirms or hands off
Hands requests that cannot be changed to the operations team with the reason.
What the assistant takes on
Matches shipment enquiries and operational calls to the relevant records.
- Shipment and delivery enquiries
- Address change requests
- Delay and damage reports
- Tracking number read back for confirmation
- Request matched to the shipment record
Example call
A fictional scenario: what the caller says, what the assistant understands and how it replies.
- Caller
- “I would like to change the delivery address for my shipment.”
- Detected request
- Address change · Shipment verification required
- Assistant response
- I can verify your shipment and check whether a change is possible, or transfer the request to operations.
Address changes depend on delivery stage and organisational permissions.
Illustrative example · Not live system data
Related integrations
The assistant connects to your systems only with defined permissions; your PBX setup is reviewed during discovery.
ERP · CRM
API access only with defined permissions
Inbound and outbound calls
Answering, information and confirmation calls
Operator handoff
Calls that need a person, plus fallback routing
Call summary to the CRM
The call summary is written to the relevant record
Runs on your own server
- Your data stays in-house.
- A single GPU server is enough.
- Several calls at the same time, on the same system.
The architecture supports your compliance processes with restricted API access, configurable retention and operator fallback. Compliance depends on the deployment configuration, data processing practices and your organizational procedures.
The path of a call
- 01Phone lineNetgsm 0850 · SIP Trunk
- 02PBXAsterisk
- 03Your serverSTT → LLM → TTS
- 04Your systemsERP · CRM
Frequently asked questions
- Can it change the address of a shipment that is out for delivery?
- Address changes depend on the delivery stage and your organization's permission rules. Requests that are not possible go to the operations team with the reason.
- Which records can it access?
- The assistant queries shipment records through APIs, only with the permissions your organization defines; the scope of access is set during discovery.
- Does voice data leave the organization?
- No. Speech-to-text, response generation and speech synthesis run on your own server; your data stays in-house. Calls arrive through your telephone carrier and PBX.
- What if the agent can't resolve a request?
- Calls that need a person are transferred to an operator, with fallback routing in place.
Request a demo
Your sector is preselected in the form. Briefly describe your call scenario, and we will schedule an online meeting at a time that suits you.
Let's plan your phone line together
In a discovery call we go through your call flows and the systems to connect.
* Footnote: Latency values were measured on real call recordings (from the moment the caller stops speaking until the first sound arrives, server side). Internet latency adds 0.05–0.3 s. Word error rate was measured on the public FLEURS-tr dataset (200 sentences, 8 kHz telephone audio). Language support is at model level. Live validation was done in Turkish; in other languages, voice and recognition quality may vary by language.