Campaigns (New)
Run outbound calls at scale. Each number you add to a campaign becomes a task — your agent dials it, handles replies, and logs everything automatically.
Overview
-
What it is? A campaign is a set of call tasks generated from your contact list.
-
What it does? Creates tasks, places calls, retries when needed, and records outcomes.
-
What you configure? Who to call, when to call, retry rules, and priority.
Campaign types
Choose a type based on how your contact list is structured.
TYPE 01 — Batch
Upload a CSV of contacts and launch all calls in one go. Best for static, pre-assembled lists.
TYPE 02 — Realtime
Push contacts one-by-one via API as they arrive. Best for live lead streams or instant follow-up triggers.

Guide for Batch Campaigns
Use when you have a static list of numbers to call. For example, a list of leads along with their contact details in a .csv file.
How to create Batch Campaigns?
-
Go to
Campaigns → Batchand click+ Create Campaignfollowed byBatch. -
Fill out basics:
Field
Purpose
Name
Internal label (e.g., Abandoned Cart Recovery 12 Jan)
Agent
Which AI agent will place the calls
Calling Number
Caller ID shown to recipients
Priority
Normal(default) orLowest,Low,High,Highest -
Upload CSV (up to 5K rows).:
-
First column header must be
phoneand phone numbers must have respective country codes. -
Provide context to agent in other columns as per your requirements and reference them in your prompt using column headers. (e.g.,
${name},${orderId}).
-
-
Time settings
-
Timezone: Controls schedule & calling hours.
-
Start Time: Start now or schedule to start later.
-
End Time: Campaign stops and archives any pending tasks.
-
Calling Hours: Daily calling window (e.g., 10:00–20:00). Calls pause outside this window.
-
-
Retries (Follow-ups)
Set the number of retries for the campaign. Each retry happens after the set interval from the last call within allowed hours.
-
Slot Allocation
A Slot is just a unit of concurrent calling capacity: One slot = One simultaneous call that your org/workspace can run at a time.
So if your organisation has 6 total slots, across all workspaces, you can only have 6 calls in progress at the same time. The 7th call will have to wait until one of the running calls finishes.
Select number of slots you want to allocate to each campaign. Teams can divide their total calling capacity across multiple campaigns and run them in parallel depending upon the total number of slots you have for the organisation.If not specified, user will use all the available slots in the workspace.
Soft Slot
Hard Slot
A soft slot is a temporary cap: if a workspace has 5 slots allotted in the start, but eventually if 3 more slots get free from some other workspace, it will combine both of them and start using 8 slots to complete the tasks even faster.
A hard slot is a strict cap: if a workspace has 5 hard slots, it will never run more than 5 concurrent calls, even when other allocated slots become free and are available to use for calling.
-
Follow up settings
Setting
Purpose
Retries
0= single attempt.≥1= additional attempts allowed.Retry Interval
Gap from the last attempt’s end‑time before the next retry.
Retry Conditions
Which call outcomes should be retried (see table below).
Every CSV row becomes a task with identical config (agent, caller ID, retry rules, etc.) only the callee’s number and context differs.

Guide for Realtime Campaigns
Ideal for on‑demand or event‑driven calls (e.g., instant lead follow‑up). Example use case:- A user fills a google form. Your AI agents then receives the information and calls the user back after a certain interval of time immediately.
How to Create Realtime Campaigns?
-
Go to
Campaigns → Realtimeand click+ Create Campaignfollowed byRealtime. -
Fill the Campaign Name, Select your Agent and Slot Limits.
-
Click
Create– this generates a Campaign ID and a sample JSON body for create task API input. -
Use the Create Task API to push tasks dynamically (check API reference)
{
"phone": "+9189xxxxxxxx", //phone number to call
"from": "+9180xxxxxxxx", //your agent's number
"agent": "agent_id",
"start": 1000, //10 AM
"end": 1800, //06 PM
"timezone": "Asia/Kolkata",
"startAfter": 1748629800000, //start time for 1st attempt
"endAfter": 1748629800000, //end time for this task
"priorities": [ //attempt wise priority
100,
50,
],
"retries": 2, //total attempts
"intervals": [ //gap between attempts
180000
],
"retryOutcomes": [ //outcomes for re-attempt
"voicemail"
],
"context": { //context for agent
"name": "Tarun"
},
"campaign": "campaign_id"
}
Batch vs. Realtime — at a glance
|
Aspect |
Batch |
Realtime |
|---|---|---|
|
How contacts are added |
CSV upload (up to 50k rows) |
Create Task API, one at a time |
|
Task configuration |
Same for all rows (agent/phone + settings) |
Fully customisable per task |
|
Best for |
Static lists |
Continuous lead streams, instant follow-up |
|
Campaign ID required |
Yes |
Yes |
Understanding follow-up settings
Retry outcome options
|
Outcome(s) |
Auto‑included? |
Notes |
|---|---|---|
|
|
Yes |
User did not pick or call could not be placed. |
|
|
Yes (if agent uses this outcome) |
User provides a specific time for callback. |
|
|
No |
Voicemail detected. |
|
|
No |
Call connected but user silent. |
|
Any custom outcome |
No |
Defined in call analysis. |
Retry intervals
-
Next attempt time =
last_attempt + retry_interval. -
If that time falls outside Calling Hours, the attempt waits until the next window starts.
The interval array length in create task API is always retries -1.
