CRM lookup and write-back
Reads the customer record for context before speaking and writes the outcome back to it automatically when the call ends.
In-call actions
What a voice agent can do during the call
A Dring agent does not just answer and talk. While the customer is still on the line, it reads and writes to your CRM, transfers to a human, sends a link, takes a payment, books a slot, routes through your PBX, switches channel and closes with a scored, structured outcome.
Eight actions, during the call
Acts inside your systems, live
Each action below is a tool the agent can call mid-conversation, with the result read back to the customer before the call ends.
Live warm transfer
Escalates to a human agent mid-call with the full conversation context attached, so the customer never repeats themselves.
SMS/WhatsApp links and forms
Sends a link, a form or a request for a photo to the customer's phone without leaving the call, then reads the reply back.
Payments on the call
Collects payment during the conversation through Stripe, iyzico or a connected bank, with the confirmation read back masked.
Calendar booking
Checks real availability and books, moves or cancels an appointment directly in Google Calendar or Outlook.
Virtual PBX routing
Runs on Dring's virtual PBX or your own SIP trunk, with queues and routing rules applied to where the call lands.
Channel switch
Moves the conversation to WhatsApp, SMS or email mid-call when that is the better place to finish the task, same memory carried over.
End-of-call analytics
Closes every call with a structured summary: intent, outcome, sentiment and next action, scored and written to your systems.
Guardrails on actions
Every action, controlled
An action that touches a live system needs limits, not just capability. These are the same guardrails that apply across the platform's tools.
Read-only by default
Every integration starts able to look up data only. Nothing is written until a write action is switched on for that tool.
Per-tool sign-off for writes
Each write action, a CRM update, a payment, a booking, is enabled explicitly, tool by tool, not as a blanket permission.
Idempotent actions
An action is safe to retry: a repeated call to the same tool with the same parameters does not double-charge, double-book or duplicate a record.
Every tool call logged
What was called, with what parameters, and what it returned is recorded against the conversation for audit.
Transaction control for high-risk actions
Payments and other high-risk actions carry their own confirmation step and limits before the transaction completes.
Human handover any time
The customer, or the agent itself when it is unsure, can move to a human through live transfer at any point in the call.
Three calls, three actions
What it looks like on the line
Three short transcripts, each ending with a different action completed before the call closes.
The item arrived damaged, I want to return it.
Sorry to hear that. I am sending a WhatsApp link now so you can photograph the damage.
ActionWhatsApp link sent
StatusPhoto received
Got it, your return is approved. A label is on its way.
Can I just pay the rest now over the phone?
Sure, I can take that now. Confirming the amount and the card ending in the digits you gave.
Card•••• 4821
ResultPayment confirmed
Payment received, your receipt is on its way by email.
I need to book a check-up next week.
Tuesday at 11:00 is open. Shall I book that for you?
CalendarSlot booked
ConfirmationSMS sent
Booked. You will get an SMS confirmation with the address now.
How actions are configured
From catalogue to live tool
Adding an action to an agent goes through the same pipeline as any other change to a live line.
- 01
Choose the tool from the catalogue
Pick the CRM, calendar, payment provider or messaging channel from the integration catalogue.
- 02
Bind it to the agent
The tool is attached to the specific agent and the point in the conversation where it can be called.
- 03
Set permissions
Read-only, or a specific write action, is switched on explicitly with its scope and limits.
- 04
Test in the pre-release suite
The action is exercised in simulated conversations before it reaches a live line.
- 05
Monitor
Every call to the tool is logged and visible on the dashboard once the agent is live.
FAQ
In-call action questions
Can the agent take a payment without a human on the line?+
Yes. Payment collection runs through Stripe, iyzico or a connected bank with its own confirmation step, and the card details are never read back in full.
What happens if a write action fails mid-call?+
The agent reports the failure to the customer rather than guessing at a result, and the attempt is logged for the team to review.
Can actions be limited to certain hours or lines?+
Yes. Permissions are set per tool and per agent, so a write action can be scoped to specific lines, hours or agent versions.
Do all agents get all eight actions by default?+
No. Each agent is bound to the specific tools it needs, chosen from the catalogue during setup.
See these actions on your own call flow
Walk through which actions your busiest line needs, live.