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

# Behaviour

> An agent whose model and tools are unchanged, and whose decisions have shifted. Built from decisions already held, not from a new signal.

This platform detects two kinds of drift and used to miss the one that matters
most:

|                                   | Detected                |
| --------------------------------- | ----------------------- |
| The agent's tools changed         | yes, MCP manifest drift |
| The agent's model changed         | yes, provenance binding |
| The agent's **behaviour** changed | this                    |

An agent whose model version and tool manifest are both unchanged, but whose
decisions have shifted, was invisible. That is exactly what a prompt edit or a
new retrieval corpus produces without touching anything under change control.

## Built from what is already there

```http theme={"system"}
GET /v1/agents/{agent_id}/behaviour
```

No new instrumentation and nothing extra to send. The fingerprint is computed
from decisions the ledger already holds: the mix of outcomes, which gates the
agent tends to stop at, the shape of what it attempts.

That matters for a reason beyond convenience. A behavioural signal an agent
reports about itself is a signal an agent can be wrong about. This one is
derived from what the platform observed, so a changed agent cannot describe
itself as unchanged.

## What a shift looks like

Not "this decision was wrong". The platform does not have an opinion about
correctness, and any product claiming to detect that from outside is selling a
feeling.

What it can say is that **the distribution moved**: an agent that refused at
`policy` twice a week now does so forty times a day, or one that never reached
`review` now reaches it constantly. Both are worth a human asking what changed,
and neither requires knowing what the right answer was.

## What to do with it

A behavioural shift is a **prompt to investigate**, not a refusal. The things
that actually stop an action are the [nine gates](/concepts/the-nine-gates),
and they are unaffected by this.

The useful pairing is with [certification](/concepts/certification): a
certificate pins the provenance and the manifest an agent was cleared against,
behaviour catches the change those two cannot see, and together they cover the
ways an agent stops being the thing that was approved.