Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.ontora.com/llms.txt

Use this file to discover all available pages before exploring further.

Instead of stitching together API calls, you can describe a campaign declaratively in a YAML file and create it with ontora campaigns create -c campaign.yaml.

​
Example

name: Q2 facility-ops interviews
goal: Map current scheduling workflows and identify automation opportunities
description: |
  Talk to facility managers and shift leads about how they assign daily work.
channel: in_app_chat
duration_minutes: 30

interview_context_for_employee: |
  We're trying to understand how scheduling actually happens day-to-day —
  not the official process, but the real one.

success_criteria: |
  Each topic explored with at least 60% of contacts.

topics:
  - name: Daily scheduling
    goal: Understand how shifts are assigned each morning
    priority: high
    success_threshold: 0.7
    sub_topics:
      - Who decides assignments
      - What inputs they use
      - Where the friction is
    questions:
      - "Walk me through how this morning's shift assignment happened."
      - "What's the worst that's happened when scheduling went wrong?"

  - name: Tooling
    goal: Identify what tools facility managers actually use
    priority: medium
    success_threshold: 0.5

contacts:
  - { name: Sam Rivera,    email: sam@example.com,    department: Operations }
  - { name: Jess Thompson, email: jess@example.com,   department: Operations, seniority_level: senior }
Then: 
ontora campaigns create -c campaign.yaml           # creates in draft
ontora campaigns create -c campaign.yaml --start   # creates and immediately starts
The CLI prints the campaign id; if you skipped --start, launch with ontora campaigns start <id> when you’re ready. For larger contact lists, leave contacts out of the YAML and import them after creation: 
ontora contacts import <id> contacts.csv

​
Field reference

​
Top-level

FieldRequiredDescription
nameyesDisplay name
goalyesResearch goal — drives agent behavior
descriptionnoInternal context
channelyesin_app_chat, voice, calendar, etc.
duration_minutesnoSoft limit per conversation
interview_context_for_employeenoShown to participants before the conversation
success_criterianoFree-form description used during synthesis
topicsyesArray — see below
contactsnoArray — see below

​
Topic

FieldRequiredDescription
nameyesTopic title
goalyesWhat we want to learn
prioritynohigh | medium | low
success_thresholdno0.0–1.0; share of contacts that should cover this topic
sub_topicsnoArray of strings
questionsnoArray of starter questions (the agent improvises follow-ups)

​
Contact

- name: Sam Rivera
  email: sam@example.com
  department: Operations
  job_title: Shift Lead
  seniority_level: senior
For bulk lists, prefer ontora contacts import <id> contacts.csv after creating the campaign — see Commands. CSV columns: name,email,phone,job_title,department,seniority. Only name is required.