A fixed four-step workflow inside the Wave console: a trigger, an AI agent, a report, and a notification. The agent reads your cluster through built-in tools, so there is nothing to wire up first.

A workflow is not a canvas you draw. It is the same four steps every time, in the same order, and you set what each one does. Every time the trigger fires, the workflow runs as its own isolated session.

Pick an alert you already have in Alerting, or a cron schedule. Wave AI Agent does not ask you to define a second alert here.
The alert, or the cron expression and time zone.
Choose one of the agents you have defined. Its persona, its system prompt and its model come with it, and the built-in cluster tools are attached for you.
Which agent runs.
The run produces a report in Markdown or HTML and, when you ask for it, the reasoning the agent followed to reach it.
Report format, and whether to keep the reasoning.
Post the report to a Slack channel or an HTTP webhook. It reuses the alert channels you already have, so delivery, retries and logs come with them.
The channel, or nothing at all.
Steps cannot be added, removed or rewired. That is deliberate: a workflow anyone on the team can read at a glance, and a run you can compare with the run before it.
A scheduled workflow is the same four steps with a clock in front of them. It is how the daily and weekly reports get made.
Minute through year, in your time zone, and the next four run times printed underneath so you can see what you just typed.
Nodes, pods, workloads, storage, cost, GPU. A cost review can be scoped to cost and nodes alone, and then the agent never reads the rest.
What the report should cover and how long it should be. Presets seed it — daily health, weekly cost, capacity forecast — and you edit from there.

Define an agent once and use it in as many workflows as you like. A diagnosis agent and a cost agent read the same cluster and write very different reports, because you told them to.

Every agent gets the same three tools, attached by the platform. There is no server to stand up first and no credentials to hand out.
The tools read. A workflow writes a report and sends a notification; it does not change your cluster.
One run per trigger, kept in the workflow history. The report says what the agent concluded. The thinking file says how it got there, so you can check the work and disagree with it.


The content in these frames comes from the console design. It shows the shape of a report, not a result measured on your cluster.
Connect a hosted API, or point Wave at a model running inside your own cluster. Each agent can override the default, so the model is a per-job decision.
Any OpenAI-compatible endpoint works: vLLM, TGI, LocalAI, a LiteLLM proxy, or an internal gateway. Give it the service URL.
A cluster service URL resolves inside the cluster, so an air-gapped environment needs no outbound path to a model vendor. Credentials are write-only and shown masked.

Find the root cause when a workload runs out of memory, while the incident is still open.
A health and cost summary for the morning, across the whole cluster.
Early access is open. Tell us which workflow you would run first, and on which cluster.
Request early access