The Console
Asking free-form questions across every connected system, pinning a playbook, and choosing a model.
The Console is a ticket-free investigation. You ask something in plain English and the agent works across every data source you have access to.
Use it when there is no ticket yet — a customer is on the phone, an alert fired, or you want to check something before someone files anything.
Asking well
The agent is good at finding things and bad at reading your mind. Two habits pay off immediately:
Name the entity. "Why is checkout failing?" makes the agent guess a scope.
"Why is checkout failing for merchant cedar-sage since about 14:00 UTC?" gives it a
merchant, a subsystem and a time window to filter on, and the answer arrives in fewer
iterations for less money.
Say what you already ruled out. "Payouts are stuck for Acme Coffee — the payout row exists and the bank is verified" stops the agent re-checking what you checked.
Pinning a playbook to a thread
A Console thread can be pinned to any playbook you have access to. Doing so applies that playbook's triage instructions and its data-source allowlist to the whole conversation.
This is worth doing for a focused question: a thread pinned to Platform Reliability will not go rummaging through the payments database, so it answers faster. It is worth not doing when you genuinely do not know where the problem is.
Threads and memory
Every Console investigation gets its own thread, owned by you and private to you. Threads replay the last 20 turns on every call, so multi-turn conversations build on prior answers rather than starting cold. Tool traces stay in the UI and out of the model's context — you keep the audit trail without paying for it in tokens every turn.
Resume a thread from History; the stored tool and cost chips replay with it.
Choosing a model
The composer has a model picker. What it offers is your organization's configured deployments — see AI providers.
Resolution order, highest priority first:
- The model picked for this thread.
- The install's runtime default, set on the Usage page.
- The configured fallback.
An override for a model that is not in the registry is ignored rather than failing. Background triage and the playbook classifier always follow the runtime default — they never use a per-thread override.
Scheduled reports show up here
A playbook can run on a cadence and post its result as a Console thread, listed under Reports. Those threads are shared with everyone who can see the playbook, and you can ask follow-up questions in them like any other conversation — the follow-ups run under the same playbook and tool allowlist.
Report threads cannot be deleted from the thread list. They are org history, not your scratch work.