Skip to main content
Deploy this agent to put a deliberate step between an investigation and an action. It consumes a completed investigation from any domain and decides what should happen about it, without touching anything itself. This page covers what it takes as input, the three answers it can give, and where it stops.

What it does

You hand it a finished investigation. It reads the findings and the run transcripts behind them — separating what was actually observed from what was inferred — and returns one of three typed decisions: Reading the transcripts rather than only the summary is the point. A confident-sounding finding built on an inference is a different thing to act on than one built on an observation, and the distinction survives into its decision.

What it reads

It holds no cloud, cluster or repository credentials, and has no shell. Its only reach is back into the platform for the investigation it was given.

Before you deploy

There is nothing else to connect. Because it is plan-only, there is no integration to bind and no credential for a target system — which is also why it deploys to either target equally: there is nothing private for a self-hosted deploy to unlock.

Ask it for

It takes a completed investigation rather than a free-text question, so it is normally driven by a workflow step rather than by a person. Where you do invoke it directly, pass the investigation you want a decision on:

Defaults and limits

In a workflow

It is the decision step between investigation and action. An incident workflow investigates, passes the result here, and routes on what comes back: a proposed remedy goes to an executor or to a human for approval, questions go back to the specialists that can answer them, and no-action closes the loop without a change. That routing is what makes the third answer useful. An agent that could only propose fixes would propose one for every finding. See Orchestration and Approvals.

What it will not do

It never mutates a live system. Not as a policy setting, and not as a prompt instruction — it has no credentials for a target system and no shell, so there is nothing to mutate with. A proposed remedy is a recommendation until something else carries it out. Its name invites the opposite assumption, which is worth stating plainly to anyone reviewing its access: this agent plans, and Remediation Executor is the one that acts.

Next steps

Remediation Executor

Carry a proposed remedy out.

Approvals

Put a human decision in front of an action.

Orchestration

How a workflow routes on what this agent returns.

Agent catalog

Every catalog agent, side by side.