Keep exceptions visible
Use the library to give the team example inputs and a clear human check before results are used.
AUT-014 · Automation
We create ten prompts for one team with input examples and human review criteria.
Use the library to give the team example inputs and a clear human check before results are used.
We create ten prompts for one team with input examples and human review criteria.
In the Team prompt library, follow “Approved task”, “Example input” and “Human review criterion” to check the handover against your original question.
Staff can get inconsistent AI output when prompts and review expectations differ for the same task. The service is intended for operations and systems owners. Use the library to give the team example inputs and a clear human check before results are used. It is useful when your team can identify the decision the work needs to support and name someone to review what comes back.
Approved examples, permitted source material and the named human reviewer. Before work starts, explain how the result will be used, which inputs are already approved and whether access or material must come from someone else. Flag gaps in the current information early so they can be handled within the scope or recorded for follow-up.
Confirm approved team tasks, Draft ten prompts with examples and Specify human review checks. The work takes place remotely through an agreed channel. We identify questions that affect the outcome, confirm where your team needs to make a decision and explain any assumptions that remain at handover.
Indicative delivery after agreed inputs are complete: 3–7 working days. Platform, AI usage and connector subscriptions are separate. Timing may also depend on access, client review or decisions outside the agreed scope. Confirm who owns those dependencies before using the estimate for a launch or other commitment.
Begin by checking the team prompt library against the original question and the information your team supplied. Decide whether you can act on the result directly or need to collect evidence, obtain approval or commission a separate implementation. That distinction helps you turn the assignment into a practical next step.
Work is limited to approved inputs and authorised systems. Test normal and exceptional cases before any rollout. AI outputs need human review and should not be treated as final decisions.
Describe the extra work when you enquire. Any change to the published scope, file limits or timing needs separate written agreement.
Wait for instructions about the agreed channel. Share only the material needed for the assignment and confirm that your organisation has the right to share it.
We run a two-hour remote session for up to ten staff using three approved work scenarios.
We create 40 representative cases with scoring guidance and failure examples for one task.
Tell us about your business and the outcome you want to achieve.