The fields that decide quality
Onlyname is required. In practice three fields decide whether the
conversations are any good, because they go straight into the agent’s prompt:
The rest tune behavior:
An initiative is created as
DRAFT. Only a draft is editable through the
API, so get the configuration right before launching, and treat a launched
initiative as frozen.
Lifecycle
What “ready to launch” means
A launch that is not ready fails with a specific code rather than a generic error, which tells you exactly what to fix:For a WhatsApp initiative, launching publishes the journey for you. You do
not have to author or publish it yourself unless you want a flow other than the
one Boom scaffolded from
maxAttempts. A missing channel on the opening
message is filled in automatically when there is only one sensible answer: the
initiative’s own channel, otherwise the organization’s primary, otherwise its
only sendable one.Participants
Participants exist only inside an initiative, addressed under/initiatives/{id}/participants. There is no global participant list, and there
is no delete: stopping a participant halts their outreach and keeps the data.
Enrolling sends a real message. People on your Do Not Contact list are skipped
by the platform rather than by whoever wrote the flow, so a suppressed contact
enrolled by mistake is not contacted.
Reading results
Three read paths, all covered in extraction: the aggregate summary for the whole initiative, the per participant record with its extracted values, and the full transcripts.Related
Journeys
The flow an initiative runs, and how to shape it when the default is not what
you want.
Extraction
The typed fields every conversation should yield. Set this before launching.
Segments
Define who the initiative reaches, and remember to evaluate it.
Inbound conversations
The other direction, where no initiative is involved.