---
title: "Agents"
description: "An agent in BRAIAN by AETERION is a configured worker that performs process steps. It combines a model, a defined set of tools, a scoped machine identity and the policies attached to it. Agents hold no standing credentials of their own: access is issued per run and expires with the run."
url: "https://aeterion.tech/en/docs/core-concepts/agents"
locale: "en"
publisher: "AETERION SA"
---
# Agents

> An agent in BRAIAN by ÆTERION is a configured worker that performs process steps. It combines a model, a defined set of tools, a scoped machine identity and the policies attached to it. Agents hold no standing credentials of their own: access is issued per run and expires with the run.

Source: https://aeterion.tech/en/docs/core-concepts/agents
Last updated: 2026-09-20

## Agent configuration

An agent declares what it can use, not what it should try. Anything outside the declared tool list is unreachable, regardless of what the model generates.

`finance-agent.yaml`
```yaml
name: finance-agent
model: braian-reason-1
identity: svc-finance-agent
tools:
  - sap.purchase_orders.read
  - sap.invoices.post
  - erp.vendor_master.read
policies:
  - finance.payment-threshold
  - data.residency-ch-eu
max_steps: 24
```

## Identity and credentials

- Each agent maps to one machine identity in the control plane, never to a human account.
- Credentials are minted per run, scoped to the declared tools, and revoked when the run ends.
- Secrets are stored encrypted and are never returned to the model context.

## Limits on autonomy

Agents are bounded by a step budget, a tool scope and the policies attached to them. When a bound is reached the run does not fail silently: it escalates with the full context of what was attempted.

> **Avoid over-permissioned agents** — Grant one agent the tools for one job. A single agent holding read and write access across finance, HR and procurement removes the separation that makes the audit log meaningful.