{"id": "TTC-108", "slug": "teach-one-agent-a-bounded-role", "title": "Teach one agent a bounded role", "level": "practitioner", "summary": "Teach one repeatable role with explicit inputs, outputs, sources, exclusions, escalation, and tests before adding tools or broader autonomy.", "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_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.", "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.", "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."], "prerequisites": ["TTC-102", "TTC-105"], "next_lessons": ["TTC-109", "TTC-110", "TTC-112"], "copyable_material": "# TTC-108 \u2014 Teach one agent a bounded role\nObjective: Perform one repeatable role with a clear start, finish, and owner.\nProcedure: Follow the named inputs, approved sources, ordered method, output template, stopping rules, and escalation path.\nRequired evidence: Retain citations, questions, draft output, test results, and approved corrections.\nBoundaries: No adjacent role, external action, new source, or permission is implied; conflicts go to the named owner.\nCompletion test: Normal, missing-information, and forbidden-action tests all reach their specified outcomes.\nReview rule: Treat generated work as a draft until the named human reviewer accepts it.", "sources": [{"title": "Custom instructions with AGENTS.md", "publisher": "OpenAI", "url": "https://developers.openai.com/codex/guides/agents-md/"}, {"title": "Artificial Intelligence Risk Management Framework (AI RMF 1.0)", "publisher": "National Institute of Standards and Technology", "url": "https://www.nist.gov/itl/ai-risk-management-framework"}], "version": "1.0.0", "reviewed_on": "2026-10-03", "review_status": "reviewed", "next_review_criteria": "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.", "canonical_aliases": ["/train-an-ai-agent/"], "canonical_url": "https://teachthecompany.com/school/teach-one-agent-a-bounded-role/"}