How loops work
The shape every 1mn feature fits — trigger, discover, decide, act, verify, gate, persist, hand off — and the three properties that decide how autonomous it can be.
A loop is a system that, on a schedule or trigger, discovers work, hands it to an agent, verifies the result, records what happened, and decides the next move — until the goal is met or it hands back to you.
The shape
Every loop in 1mn fits one shape:
| Stage | What happens |
|---|---|
| Trigger | A cron, a webhook, an event, or you. |
| Discover | Pull the relevant signal (errors, metrics, drafts) and dedupe against what’s already handled. |
| Decide | Filter to what this loop is allowed to attempt right now; skip the rest. |
| Act | An agent run produces an artifact — a PR, a draft, a campaign, a report. |
| Verify | Prove it’s correct — tests, a critic, a metric check. This is the hard part. |
| Gate | Irreversible / high-impact actions pause for you. Reversible ones auto-apply. |
| Persist | Record what was tried and the outcome, so it isn’t re-done next time. |
| Hand off | Surface to you only at the edge — low confidence, repeated failure, or a gate. |
What decides how autonomous a loop can be
Three properties of the work (not the agent):
- Verifiability — can the loop prove it succeeded? A clean success signal (tests pass) buys autonomy; “looks right” doesn’t.
- Blast radius — is a mistake reversible? Wrong docs are recoverable; a bad prod deploy or a sent email isn’t.
- Ambiguity — one right answer or fifty? Patching a known bug has one; “build a feature” has a hundred.
This is why engineering loops mature first (tests give a clean signal) while money and strategy stay human-owned.
The trust ladder
Most loops ship in draft-only or recommend mode: a Ranger only ever files a draft ticket, a growth loop hands you a draft to publish, an engineering loop opens a pull request it never merges. The irreversible step — merging, publishing, spending — always stays a manual gate you own, no matter how autonomous the loop that produced the work. There's no single autonomy dial to slide: each loop's blast radius already fixes how far it's allowed to go, and you decide what to do with every artifact it hands back.
Where you control them
You turn loops on and set how often they run from a few surfaces, grouped the way the work is:
- Autonomous background loops — the digests, monitors, content drafts, and competitor scans — appear as cards on the Loops view (
/dashboard/loops), one card per loop, each showing its cadence and recent run health. Open a card's schedule to enable or pause the loop, set its cadence (in days) and run hour, or hit Run now. A loop only shows up here once it's enabled. - Rangers — the daily discovery agents — are scheduled from the Rangers tab: each has its own enabled toggle, run hour, and run days. See Set a Ranger's schedule.
- Per-surface loops — Watchdog and Dogfooding are turned on and scheduled from their own tabs (Watchdog's enable toggle plus Find now; the Dogfooding schedule).