AI Agents

Your organisation’s AI team — five preloaded role agents, direct persona chats, and an AI-guided wizard for creating custom agents

Every organisation comes with a preloaded AI team: five agents, each with a role, a persona, and safe defaults. They appear under AI → Agents the first time anyone opens the roster, and each one can be chatted with directly or dispatched to work autonomously.

Your default AI team

Agent	Role
AI Team Lead	Your first point of contact. Triages requests, routes work to the right specialist, files tickets for anything that outlives the conversation.
Developer	Application delivery: Helm charts and values, deploys, CI/CD workflows, and pull-request demos.
Database Admin	Stateful workloads: StatefulSets, volumes, operators, and backup hygiene. Verifies backups before proposing anything that touches data.
SRE	Reliability: alert triage, golden signals, incident timelines, and postmortem notes. Evidence-first.
DevOps	The platform itself: clusters, node pools, add-ons and stacks, GitOps drift, and IaC. One reversible step at a time.

The defaults are deliberately conservative: they never run on a schedule, they only propose changes (every mutation waits for your approval), and they cost nothing until you talk to them or press Run now. Delete any you don’t want — they stay deleted, and you can re-hire them individually from the agent catalog at any time.

Fleet status at a glance

The Agents page is a triage surface: every row shows what its agent’s latest run is doing, and what — if anything — it needs from you.

Status	Meaning	Call to action
Needs your input	The run parked on a question or an approval and resumes once you answer.	Respond — opens the exact chat conversation the agent is waiting in.
Blocked	The mission ended because the agent judged the goal blocked; its verdict explains why.	Review — opens the agent with the run’s transcript and outcome.
Failed / Expired	The last run errored or ran out its budget window.	Review
Working	A run is live right now.	View live — follow the transcript as it streams.
Goal met / Completed	The last run finished cleanly.	—
Never run	The agent has no run history yet.	Run now (admins)

Each row also swaps its goal prompt for the latest run’s outcome summary once one exists, so the list reads as “what happened last”, not “what was asked months ago”.

Agents that need a person sort to the top of their section, and a summary strip above the list counts them — need input, blocked, and failed chips filter the list to just those agents. Finished one-off missions fold away under Completed missions, keeping old dispatches out of the way without deleting their history. In the sidebar, the AI Agents item carries a badge with the number of agents currently waiting on your input — the same way the Board badges tickets that need a human.

Chat with an agent

Every agent has a Chat action — on the roster, on the agent list, and on its detail page. It opens the AI chat scoped to that agent: the conversation carries the agent’s persona, so the SRE talks incidents and evidence while the Database Admin double-checks backups before anything else. The persona only ever narrows what an agent may do; the platform’s normal approval rules for mutating actions apply unchanged.

The chat URL carries the scope (/organisation/ai/chat?agent=…), so a refresh — or a bookmarked link — keeps you talking to the same teammate.

Create your own with the AI wizard

New agent on the Agents page starts a short interview instead of a form. The wizard asks for a role, drafts a name (shuffle it if you disagree), lets you pick focus areas, a cluster scope, a communication style, and guardrails — then writes the agent’s persona for you. Review and edit the persona before hiring; the result is a real agent that behaves exactly like the preloaded team.

Prefer the classic form? The wizard’s footer switches to Manual setup at any point.

Creating, deleting, and running agents requires an organisation admin role. Chatting with an agent is open to every member.

Autonomy and budgets

Each agent carries an autonomy level — Observe (read-only), Propose (suggests, you approve), or Autonomous (executes low-risk reversible actions itself) — and hard budgets for tool calls, turns, and runtime. Budgets are the hard stop for autonomous work; the defaults ship with Propose and modest budgets.