If you are going to run an agent yourself, this is the rota. It is written to be genuinely usable rather than exhaustive: four cadences, a handful of items each, and an honest note on which ones a managed platform takes off the list and which stay yours no matter where the agent runs.
Four cadences. Daily: confirm it ran and check the spend. Weekly: read a sample of output and scan for repeated errors. Monthly: patch the host, review credentials, and check the cost trend. Quarterly: rotate keys, re-test against changed models and APIs, and prune agents nobody reads any more.
Cadences
Daily, weekly, monthly, quarterly
Daily time
Under a minute, if you have run records
Removed by a platform
Most of monthly, some of daily
Always yours
Reading the output and judging it
The checklist at a glance
Cadence
Item
Yours on a managed host?
Daily
Confirm every scheduled run fired
No, it is recorded for you
Daily
Check spend against normal
No, capped and visible
Weekly
Read a sample of output
Yes, always
Weekly
Scan for repeated errors
Partly, alerts surface patterns
Monthly
Patch the host
No
Monthly
Review credential scope
Yes, in one place
Quarterly
Rotate keys
Yes, in one place
Quarterly
Re-test after model drift
Yes, always
Quarterly
Prune unread agents
Yes, always
Daily: did it run, and what did it cost
The whole daily check is two questions, and with run records in front of you it takes under a minute. Without them it takes ten and you skip it, which is how agents end up dead for a week.
Did every scheduled run fire? A missing run matters more than a failed one, because a failure at least tells you something.
Is yesterday's spend in the normal range? A step change is the earliest sign of a retry loop.
Anything in the error log that is not the usual flaky-network noise?
Weekly: is the output still good
The check that catches quality drift, and the one no tool can do for you. Read a sample the way a reader would, not the way its author would.
Read two or three actual outputs end to end. Would you act on them?
Look for repetition: the same items resurfacing every day usually means a filter or a date window broke.
Scan errors for anything that appeared more than twice. Once is noise, three times is a pattern.
Check anything the agent touches that you did not read: files written, messages sent, tickets created.
Monthly: the host and the credentials
Mostly infrastructure work, and mostly what a managed platform removes. If you self-host, none of it is optional.
Apply operating system and dependency security updates, then confirm the agent came back up afterwards.
Review which credentials exist, what each can do, and whether any are broader in scope than the agent needs.
Check the month's total spend against the month before, per agent rather than in aggregate.
Confirm your backups, or confirm honestly that you have none and that this is a decision rather than an oversight.
Quarterly: rotation, drift, and pruning
The slow-moving work. Easy to defer indefinitely, which is exactly why it belongs on a calendar rather than in your memory.
Rotate provider and integration keys, and remove any that no longer correspond to a running agent.
Re-test against current models. Deprecations and version changes shift behaviour without shifting your prompt.
Re-test integrations whose APIs or markup may have changed since you last looked.
Prune. An agent whose output nobody has read in three months should be turned off, not maintained.
What a managed platform removes, honestly
Not everything, and it is worth knowing which is which before you decide. Qoren handles host patching, restarts, health monitoring, encrypted secret storage, run records, and a hard spend cap, so most of the monthly list and half of the daily one stop being yours.
Removed: host patching, restart policies, uptime alerting, run recording, spend enforcement, and secret storage.
Reduced: credential rotation, which becomes one edit in one place rather than a hunt through files and shell history.
Unchanged: reading the output, judging whether it is good, and re-testing after a model changes. That is the judgment work, and no host can take it.
With run records and a spend cap already in place, the recurring checks are a few minutes a day plus a longer weekly read of the output. Without them the same work takes far longer, because every check starts with establishing whether the agent is even alive.
Run OpenClaw or Hermes without managing infrastructure.
Deploy a managed agent environment, configure the runtime, and keep the agent online without Docker, VPS setup, or server maintenance.
