---
title: "Comment by Cai on \"Stop approving one by one. Batch it.\" | Hashnode"
description: "This is exactly the scaling problem. Per-action approval breaks at exactly the point where agents become actually useful: doing many small things in parallel. T"
url: "https://hashnode.com/posts/stop-approving-one-by-one-batch-it/6af602a77e155c8935ef3cec/comment/6af6c47b1bb983bafbbf9a3d"
---

[Discussion](https://hashnode.com/posts/stop-approving-one-by-one-batch-it/6af602a77e155c8935ef3cec)

Comment [Stop approving one by one. Batch it.](https://hashnode.com/posts/stop-approving-one-by-one-batch-it/6af602a77e155c8935ef3cec)

[Cai](https://hashnode.com/@cailab)

[1d ago](https://hashnode.com/posts/stop-approving-one-by-one-batch-it/6af602a77e155c8935ef3cec/comment/6af6c47b1bb983bafbbf9a3d)

This is exactly the scaling problem. Per-action approval breaks at exactly the point where agents become actually useful: doing many small things in parallel. The practical solution is policy based approval tiers: let the agent batch routine actions under a spending or trust limit you set upfront, and only escalate the high risk outliers for manual review. The batch itself can be a single signed transaction with a countersignature mechanism, so you still have cryptographic proof of what happened, just without the per-action friction.

[Veronica Stewart](https://hashnode.com/@veronicstewart)

[55m ago](https://hashnode.com/posts/stop-approving-one-by-one-batch-it/6af602a77e155c8935ef3cec/comment/6af6c47b1bb983bafbbf9a3d#reply-6af8a4b427e9e878b161f1b4)

Exactly — and that's where batching is meant to lead. Per-action approval doesn't scale, but removing approval entirely isn't the answer either. The batch is the review surface for the policy: you approve the class of actions once, with the list in front of you, instead of rubber-stamping each one as it flies past. Policy decides what's allowed; the batch is where a human still sees what actually ran. Thanks for reading it closely.