Agents and automation

Agents are appropriate for bounded multi-step action only when permissions, checkpoints, and recovery are designed first. This principle matters because an AI system produces likely output from the context and instructions it receives; it does not automatically know the organization’s current facts, private policy, unstated intent, or acceptable risk.

Use the following sequence for this page: map actions and permissions before automation; separate drafting from committing changes; place human approval before irreversible steps; log outcomes and design rollback or recovery. The sequence is a guide, not a ritual. Skip a step only when its question truly has no effect on the outcome, and strengthen it when mistakes would be costly.

Return to the opening case: An agent can read an inbox, draft replies, update a tracker, and send messages, but one mistaken identity could contact the wrong customer. Begin by rewriting the request as a small contract. Name the intended reader or user, the authoritative material, the operation to perform, the required output, and the review owner. If current information is required, identify where it will come from. If exact calculation or action is required, assign that step to a deterministic tool or an approved system rather than relying on prose generation.

A useful instruction could follow this shape:

Goal: help [reader] accomplish [outcome]. Use only [named sources or supplied material] for factual claims. Perform [specific operation] and return [format]. Mark missing information as TBD or ask a focused question; do not guess. Before the result is used, [named person or role] will check [criteria].

• Granting broad credentials for convenience. This hides an important assumption or removes a review point. Replace it with an explicit rule, a source check, or a human decision.
• Automating an unstable process. This hides an important assumption or removes a review point. Replace it with an explicit rule, a source check, or a human decision.
• Treating successful demos as evidence of reliability. This hides an important assumption or removes a review point. Replace it with an explicit rule, a source check, or a human decision.

Turn Agents and automation into a template you can reuse this week: job statement, required evidence, failure mode to catch, and reviewer. Store it next to your other pick the right ai tool notes. When the job changes, rewrite only the job statement and re-run the same failure-mode list — do not invent a new workflow from scratch. Role of this page: Operational pattern.