Human in the loop for AI agents
The short answer
Human in the loop means an AI agent stops and asks a person before certain decisions, and settles the rest itself. For a founder running coding agents, the calls worth stopping for are what's in or out, anything touching customers, money or data that can't come back, anything against a rule you set, and real choices between options.
The two ways it goes wrong
- Too much loop. Every question comes to you. You become the bottleneck, and your agents wait.
- Too little loop. Agents decide things that were yours, and you find out from a customer.
The fix is the same for both: say which decisions are yours, in writing, and let agents settle everything else.
Decisions that need you
- Scope. It changes what's in or out of the job, or the outcome.
- Customers. It affects customers, revenue, security or data that can't come back.
- Your rules. It goes against a rule you set.
- Real options. Two good paths, and the choice is a product call.
Everything else, such as naming, small layout calls or which test to add, the agent settles and notes.
How an agent should ask
Three lines: the topic, the question, and the options with the one it would pick. You should be able to answer in one line. One open question per job at a time, and the agent keeps working on anything that doesn't depend on the answer.
Answer once
Save each answer as a rule, with the reason. The next agent reads the rule before asking. Over time fewer questions reach you, because the settled ones stay settled.
Human in the loop vs human on the loop
In the loop, the agent waits for you on certain calls. On the loop, the agent acts and you review afterwards. Most founders want both: in the loop for the four kinds of decision above, on the loop for everything else, with a clear record of what was done. See human in the loop in the glossary.
Copy this
Paste this into your CLAUDE.md or AGENTS.md, so every agent knows which calls are yours.
## Ask me only if
- it changes what's in or out, or the outcome
- it affects customers, money, security or data that can't come back
- it goes against a rule in this repo
- it's a real choice between options
## How to ask
Topic: <one line>
Ask: <the question, one line>
Options: A - <...> B - <...> (I'd pick: <A/B>)
## Everything else
Decide, note what you decided, and carry on.
Where Annsa fits
Annsa's Needs You list holds the questions your agents raise, each in that three-line shape with the options. You answer in the app or from your terminal, and you can save an answer as a principle every agent reads before asking. Needs You
See how it fits together in Direct your agents.