AI agents as teammates
Giving an agent a role name and goal does not make it a reliable colleague. When an agent can take multiple steps and use tools, role ambiguity creates action risk—not merely a poor answer.
The limit of the teammate metaphor
Thinking of an agent as a teammate helps design roles, service expectations, and handoffs. It does not give the agent personhood, equal status, or human accountability.
Seven parts of an agent role card
‘Do research’ is not a role definition. These boundaries need to be visible together.
Goal
Which outcome does the agent support, and how is success recognised?
Context
Which information does it need, and how does it judge freshness?
Tools
Which systems may it read or use?
Authority
May it only recommend, or also create, change, and send records?
Constraints
Which data, users, or actions are out of bounds?
Handoff
When does it transfer to a human, with which context and options?
Failure behaviour
Does it stop under uncertainty, use a safe fallback, and leave an event record?
Role-design case
A market-research agent
An agent will scan internal documents and external sources to recommend a new market. The team wants speed, but some documents are sensitive, external evidence conflicts, and the investment decision is expensive to reverse.
Where should the agent stop?
It may gather evidence from permitted sources, expose conflicts, and recommend options. Sensitive access requires separate permission and source uncertainty stays visible. It does not execute the investment; a named human receives the evidence and trade-offs at handoff.
Four properties of sound delegation
Narrow but meaningful scope
The agent owns work connected to an outcome, with boundaries clear enough to prevent open-ended authority.
Least privilege
Tool and data permissions stay at the minimum scope required for the task.
Context-rich handoff
The agent reports what it tried, the evidence, and the human decision needed—not merely ‘I failed’.
Observable work
Actions, sources, errors, and intervention points can be inspected later.
Misconception
“An agent with a role and goal can be managed like a capable employee.”
Agents do not carry intent, social judgment, or organizational responsibility. Their performance depends on explicit boundaries, access control, evaluations, observation, and human ownership.
Test your understanding
If an agent joined your team, which one action would you not permit without human approval, and which signal would trigger handoff?
Justify your answer through outcome, permission, risk, and reversibility—not job title.
Keep this
Design the agent like a teammate, while keeping authority, observation, and accountability inside the human organization.