Start an agent design with the work you want to improve. Define the person it serves, the inputs it can use, the result it should produce, and the decisions that stay with people.
If you own the process or are building the agent, use these guides to write a pilot brief. Make it specific enough that another person can tell whether the agent completed the job.
Build the brief in three steps
- Choose a useful use case. Compare candidate tasks by usefulness, available evidence, reversibility, and the effort needed to judge results.
- Define a focused agent job. Specify the trigger, inputs, task, output, handoff, boundaries, and completion conditions.
- Design approvals and handoffs. Decide what triggers human review, what the reviewer receives, and what happens while review is pending.
Make the output easy to inspect
For a weekly project-meeting brief, make the job testable:
- Trigger: The project owner requests preparation for the next meeting.
- Approved inputs: The current agenda, project record, and approved notes from earlier meetings.
- Draft result: An agenda recap, open questions, and links to the sources behind factual statements.
- Pass check: Each factual statement is supported by a linked source, and assumptions are marked for review.
- Stop check: If the agenda is missing or sources conflict, list the gap, route it to the project owner, and wait for clarification instead of choosing a version or inferring a commitment.
Use the routine case and the stop case as separate evaluation examples. The focused job brief guide expands these fields; evaluation guidance helps test them.
Move from design to a pilot
Use knowledge, tools, and connections to decide what the workflow needs. Then follow evaluation before production to test the design. For AgentShelf configuration concepts, see the agent harness.
All guides in this topic
- Choose an AI Agent Use Case: Choose work with a clear owner, variable steps, approved information, a reviewable result, and a useful signal for success.
- Define a Focused Agent Job: A useful agent brief names the trigger, user, result, approved context, allowed actions, stop conditions, and human handoff.
- Human Review for AI Agents: Human review is most useful at clear decision points where approval, correction, or escalation can change the outcome.
- Design Agent Handoffs Across Systems: Treat a cross-system handoff as pending until the receiving system acknowledges the request and reports what happened next.
- Use Structured Outputs to Make Agent Results Reviewable: Define required fields, allowed values, evidence references, and review conditions, then validate both output shape and the facts it contains.