Getting great results

Write clear instructions

Brief an agent the way you would brief a sharp new hire: state the outcome, the constraints, and how you want to see the result. Vague asks get generic work; specific asks get useful work.

• Lead with the goal, not the mechanics. Say what 'done' looks like.
• Give constraints up front — tone, length, audience, deadline, what to avoid.
• Provide the inputs: name the account, paste the thread, or point to the right knowledge.
• Ask for a plan before a big task: “Outline your approach before you start.”

Decide when to require approval

Sensitive and outbound actions already stop for your approval — you see the recipient and message body before anything sends. Use that checkpoint deliberately.

• Keep approvals on for anything that leaves your account or is hard to undo — external emails, messages to customers, financial actions.
• Let read-only and draft-only work run freely; there's nothing to approve when nothing is sent.
• When in doubt, ask the agent to draft and show you rather than act.

Review the output

Treat agent output as strong first-draft work from a capable colleague: usually right, occasionally wrong, always worth a glance before it counts. Skim for the things that actually matter — names, numbers, dates, commitments — before an email goes out or a figure lands in a report.

Give feedback

Agents get more useful as you steer them. If a draft misses, say what was wrong and what you wanted instead — the correction shapes the next attempt. For preferences you will want every time (your email sign-off, your tone, standing facts), put them in the knowledge base so you never have to repeat them.

Understand the limits

• Agents don't know what they weren't given — provide context rather than assuming they can infer it.
• They can hit a step limit on very long tasks; break big jobs into milestones (see troubleshooting).
• They aren't a substitute for professional judgment on legal, financial, or medical decisions.
• Untrusted content they read (a web page, an inbound email) is framed defensively against prompt-injection, but you should still review actions taken off the back of it.

Safe autonomy

As you build trust, you can let agents run longer and intervene less — but do it gradually. Start with tight, well-defined tasks and full review; widen scope as you see reliable results. Keep approvals on for irreversible actions no matter how much you trust the day-to-day work. Autonomy is something you grant on purpose, not a default you forget to check.