Guide: Prepare a call flow before session one
Long readRunning calls
What to settle before the first call opens — which transport, what gets asked first, how long to wait, and where a person takes over.
Keep readingGuidesStack docs
Operator playbook
How to run the calls you can open today
The order a deployment usually needs. Prepare the flow, read the transcript, open capability behind flags, and fail without dropping the call. Each guide assumes what is live today — browser and mobile voice, key-gated telephony, orchestrated vendor models.
Running calls
Prepare a call flow before session one
What to settle before the first call opens — which transport, what gets asked first, how long to wait, and where a person takes over.
Keep reading
4 / 4
Guide: Reviewing call transcripts
Medium readOperator console
How to read back what accumulated during a call — what to look for, what to record, and what to carry into the next one.
Keep readingGuide: Staging capability behind flags
Medium readPlatform
A feature flag is a level, not a switch. Risky paths default off and only come up once what they do is observable.
Keep readingGuide: Handling a failed call
Medium readReliability
Failure is chosen, not eliminated. Tell apart what wavered, step down instead of dropping, and close out what is left in the console.
Keep readingThe consoles these guides run on
Published agents — each persona shows voice, language, and publish date; drafts stay unpublished until you say so. 
Console Home — pick voice tools, watch usage, and choose the voice the next call will use.
The principles, briefly
Need the stack map, or a remaining deployment question?
Docs describe how the pipeline is assembled. Support tables what is live, gated, and still being wired.