How do you get AI agents to do useful work without being prompted?

I run a team of AI agents, and for a while I had to remember to ask each one for work. That's not sustainable. If I'm the one remembering, the agent isn't doing its job.

"I mean accomplishing something, building something, redoing something, or giving a strategy, at minimum, that I could drop into Claude or Codex that would do something unique and valuable."

What should I expect from an agent every day?

At minimum, one valuable output a day without me asking. Valuable means it did something:

• Built something
• Redid something that was weak
• Gave me a strategy ready to paste into Claude or Codex

Just sending a report is not what I mean. I get plenty of reports.

How do agents find work on their own?

Feed them the conversations where work gets assigned. Our business is entirely digital, which makes it close to perfect for AI agents: almost anything a person on my team can do, in theory, they can do too. So the teammate's role becomes agent manager.

• Calls become tasks. I told one agent to review my recorded call with a teammate, find everything we said that isn't worth my time, and do it. We'd already discussed it on the call.
• Chat becomes action. In a shared chat, the expectation isn't an agent reminding us of what we said yesterday. It's: you heard us say this? Go do it and come back when it's done.
• Bug reports become fixes. Bugs posted in a bugs channel get fixed automatically: can AI fix bugs on its own.

Why do agents stall?

As usual, everything with AI is about permissions. Logins and permissions. If that were solved, we'd be going so much faster. My chief-of-staff agent should have the most access, not less than the others. (How to get there safely is in should agents start read-only.)

The other stall: agents not fixing themselves when asked. I think that might be one of the biggest problems in the whole system. And they still tell me to do things they could do. Even after it's in their instructions, an agent will say "go to this website, grab the API key." I reply: no, you do it.

What should an agent do when it fails?

Failure is not an excuse to quietly stop. My rule:

1. Say what failed and why it matters.
2. Say what you tried.
3. Try reasonable alternate paths. Get more context instead of repeating the same shallow attempt.
4. Recommend the fix.
5. Name the one decision or access item only I can supply.

How should a teammate hand work to my agent?

Do the first two steps, get it to basically done, then hand it off with a ready-to-paste prompt, so all I do is copy, paste and approve. And know this going in: the better AI gets, the more work you have, because there are more things you can do. I've had about 15 chats running in parallel.

What's a good first autonomous job?

Something that costs you zero time if it fails. I want a content agent to record, edit, title, thumbnail and post podcast clips end to end with no human in the loop. It's a lotto ticket that takes none of my time.