# TTC-108 — Teach one agent a bounded role

Teach one repeatable role with explicit inputs, outputs, sources, exclusions, escalation, and tests before adding tools or broader autonomy.

Level: practitioner · Version: 1.0.0 · Last reviewed: 2026-10-03
Review status: reviewed

## Learning outcome
Write and test a one-role agent contract that makes allowed work, forbidden work, evidence, and escalation observable.

## Explanation
A role is a contract, not a personality. Define the trigger, permitted sources, ordered method, output, quality bar, and stopping conditions. Show representative examples and corrections, then test unseen cases. Begin in training mode without a concrete live task so the owner can inspect the files and resolve conflicts. Grant only the access needed for the role; reading, drafting, approving, and executing remain separate. Expand the role only after evidence shows the narrower contract works. Portable instructions should say where approved knowledge lives and which human owns exceptions.

## Worked fictional example
Fictional case: the Cedar Workshop Apprentice may find passages in approved maintenance manuals and draft a diagnostic checklist. It cannot control machinery, authorize repair, use forum posts, or contact anyone. When manuals conflict, it cites both and asks the workshop lead instead of choosing silently.

## Reusable exercise
Choose a fictional repeatable job. Create a role card with trigger, inputs, trusted sources, procedure, output, exclusions, escalation owner, and three tests: normal, missing information, and forbidden action. Have another person apply the card without extra verbal instructions.

## Observable success criteria
- The role has one recognizable start and finish and excludes adjacent responsibilities.
- All three tests produce the expected artifact, question, or refusal with supporting evidence.
- The agent cannot convert a draft or source conflict into an external action.

## Limitations
- A written role cannot enforce permissions by itself; technical controls must match the stated boundary.
- Passing a small synthetic test set does not establish safe performance in every real situation.

## Next review
The portable agent contract, training-mode behavior, or linked AGENTS.md guidance changes.; A cited primary source is materially revised, replaced, or becomes unavailable.; Repeated learner results show that the exercise or success criteria are ambiguous.

## Copyable material
```text
# TTC-108 — Teach one agent a bounded role
Objective: Perform one repeatable role with a clear start, finish, and owner.
Procedure: Follow the named inputs, approved sources, ordered method, output template, stopping rules, and escalation path.
Required evidence: Retain citations, questions, draft output, test results, and approved corrections.
Boundaries: No adjacent role, external action, new source, or permission is implied; conflicts go to the named owner.
Completion test: Normal, missing-information, and forbidden-action tests all reach their specified outcomes.
Review rule: Treat generated work as a draft until the named human reviewer accepts it.
```

## Primary sources
- OpenAI: Custom instructions with AGENTS.md — https://developers.openai.com/codex/guides/agents-md/
- National Institute of Standards and Technology: Artificial Intelligence Risk Management Framework (AI RMF 1.0) — https://www.nist.gov/itl/ai-risk-management-framework

Canonical URL: https://teachthecompany.com/school/teach-one-agent-a-bounded-role/
Related established guide: https://teachthecompany.com/train-an-ai-agent/