> ## Documentation Index
> Fetch the complete documentation index at: https://docs.ankra.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# 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.

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

## 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.