# Wake your bots on real work instead of a timer, and give each one its own read budget

PaperChase agent use case (free feed entry), version 1.0. Source: [@BIGMayrr](https://x.com/BIGMayrr/status/2115953180190077092), 2026-10-29.

## What they did

He counted the waste first: seven bots waking hourly is about 1,176 runs a week, and one bot on a five-minute timer is about 2,016, most of them finding nothing. He kept one scheduled routine for the checks that must happen, made the rest start only when there is work, moved handoffs from email drafts into one shared ledger file, gave each bot its own read budget with a hard stop, separated test runs from real actions, and gave a single bot the spending job with a small cap and his approval on every purchase. He says the launch now runs in about 60 runs.

## Worth knowing

Shared limits are the quiet failure: without per-bot budgets, one chatty bot can use the read allowance the others need. Run counts are his estimates, not measured invoices.

## Workflow template

```text
Apply this workflow to [your project]:
1. Count how often each bot wakes and how often it finds real work.
2. Keep one scheduled routine for checks that must happen on a clock; make the rest start from a trigger such as a webhook, a new file or a ledger entry.
3. Replace email handoffs with one shared ledger file that each bot appends to.
4. Give each bot its own read and run budget with a hard stop when it hits the limit.
5. Run tests in a true dry-run mode and require approval for any real action during testing.
6. Put spending in one bot with a fixed cap and your approval on every purchase.
Stop and ask me before anything irreversible: deploys, payments, sends or deletes.
```

## Steps

1. **Count how often each bot wakes and how often it finds real work.** Count how often each bot wakes and how often it finds real work.
2. **Keep one scheduled routine for checks that must happen on a clock; mak.** Keep one scheduled routine for checks that must happen on a clock; make the rest start from a trigger such as a webhook, a new file or a ledger entry.
3. **Replace email handoffs with one shared ledger file that each bot appen.** Replace email handoffs with one shared ledger file that each bot appends to.
4. **Give each bot its own read and run budget with a hard stop when it hit.** Give each bot its own read and run budget with a hard stop when it hits the limit.
5. **Run tests in a true dry-run mode and require approval for any real act.** Run tests in a true dry-run mode and require approval for any real action during testing.
6. **Put spending in one bot with a fixed cap and your approval on every pu.** Put spending in one bot with a fixed cap and your approval on every purchase.

## Credit

Workflow reported by @BIGMayrr: https://x.com/BIGMayrr/status/2115953180190077092
Related: https://x.com/imthatcarlos/status/2115888663275938256
Related: https://x.com/whemohere/status/2115836615595635041

Summary and template written by PaperChaseWebb in our own words. Questions: mgmt@paperchasewebb.com