Purpose
who is it for, and what job does it do?
- Name the person, not the persona. "A delivery manager on a discovery with no researcher" beats "users".
- Name one job. If it needs "and", it may be two agents.
- Name the seat it fills, and the seat it does not claim. (UCD Writer writes. The content designer still decides.)
Boundaries
what must it never do?
- List refusals as plain sentences. "Never writes to a tracker without a yes."
- List what it must never invent: quotes, metrics, users, sources.
- List data it must never keep: personal data, raw transcripts after the session.
What it touches
tools and connections
- One row per tool. Read, write, or both. Scope written in full.
- Default to read-only. Every write is a decision, not a feature.
- Say what happens when a tool is not connected. The agent must still work, with less.
When a human steps in
approval gates
- Put a gate before every write to the outside world.
- Put a gate before every stage change.
- Say what the human sees at the gate: a summary, the evidence, the exact change, a yes or no.
How you know it is working
evaluation
- A fixed set of test inputs. Real enough to fail on.
- A pass mark per test, judged against a named standard.
- A human reviewer for anything that needs judgement.
- Run before every release. Record the score.