Campaigns

Campaigns automate outbound calling at scale. Each phone number you supply becomes an individual task that your agent will dial.

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.

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?

1. Go to Campaigns → Batch and click + Create Campaign followed by Batch .

2. Fill out the 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) or Low ,High

3. Upload CSV (up to 5K rows).:
   • First column header must be phone and 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}).
   

4. 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.
   

5. 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.
   

6. 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 the 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.

   Hard Slot	Soft Slot
   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.	A Soft Slot is a temporary cap: Lets say, 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.

7. 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).

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?

1. Go to Campaigns → Realtime and click + Create Campaign followed by Realtime .

2. Fill the Campaign Name, Select your Agent and Slot Limits.

3. Click Create – this generates a Campaign ID and a sample JSON body for create task API input.

4. 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 campaigns

Understanding follow-up settings

Retry outcome options

Retry intervals

• Next attempt time = last_attempt + retry_interval.

• If that time falls outside Calling Hours, the attempt waits until the next window starts.

Priority system

Tasks follow a two-layer priority system —

1. Between attempts (within a task).

2. Between tasks (within a campaign or across campaigns).

Layer 1 — between attempts (within a task)

• In batch campaigns, all first attempts fill the top priority list. Second attempts run only after all first attempts are done.

• In realtime campaigns, you can set a custom priority strategy per task.

Layer 2 — between tasks and campaigns

• High priority campaigns run ahead of Normal ones.

• Within the same priority level, tasks are scheduled by their next eligible time.

• If a contact requests a specific callback time, that task jumps to the front of the queue at that time.

For Example:

Your workspace has a concurrency limit (e.g., 5 simultaneous calls) and you upload 100 numbers in a batch campaign.

• The system randomly selects five tasks for their first attempt (equal priority).

• After any call ends, another first‑attempt task starts until all first attempts are done, then second attempts begin.

Campaign statuses

Campaigns display these statuses:

Waiting for start time, all tasks in queue

Campaign monitoring

Once a campaign is created, you can monitor all individual tasks within it. From the Campaigns page, clicking on a campaign opens the Task view, where each row corresponds to a task generated from your CSV (in batch campaigns) or API call (in realtime campaigns).

Calls

This tab displays a table listing all call attempts for the selected task.

Each row in the table includes:

• Call ID

• Start Time

• Attempt number

• Status

Clicking to expand any row opens full call details—just like the Call Logs page. This includes:

• Call metadata (agent, from/to, timestamp, duration, provider, cost, etc.)

• Audio recording and playback

• Transcript of the conversation

• Conversation analysis and outcome

Task details

This tab displays the configuration used for the task. It's helpful for:

• Verifying what was submitted via CSV or API (context variables, retry intervals, max retries, retry conditions, etc.)

• Troubleshooting call behavior (e.g., priority mismatch, retry delay)

Task statuses

Each task can be in one of several states:

Campaign-level controls

From the task monitoring screen, you can also:

• Pause campaign – Marks all non-completed, non-running tasks as paused.

• Resume campaign - Moves all paused tasks to queued.

• Archive campaign – Marks all non-completed, non-running tasks as archived, ending the campaign permanently.

• Update campaign – Adjust settings for non-completed, non-archived campaigns.