Autonomous agents run on a number you set on the trigger
Kortix is the open-source CompanyOS, and each trigger carries the hourly and daily cap on how often an agent may start a session
Autonomous agents run on a number you set on the trigger
You have read a page of definitions of autonomous AI agents this week and none of them helps you compare two products. Each describes what a model decides inside a run, then offers a link to the vendor's own platform. The sentence that would settle the purchase is missing: how often the system may act while nobody is watching. Kortix is the open-source CompanyOS, and the triggers that start an unattended session are rows in kortix.yaml with a cap beside them.
A cap on the trigger is what makes autonomy a quantity you can read before you buy. What follows is the arithmetic of an unattended run: fires an hour, fires a day, and what stops a loop.
The definitions describe one run and leave the rate out
Microsoft says autonomous agents are "systems that can independently analyze situations, make decisions, and act," and that "they don't just follow preset instructions" (Microsoft). Salesforce says "autonomous agents can execute on tasks and workflows independently" (Salesforce). NVIDIA calls them "advanced AI systems that reason, plan, and execute multi-step tasks to meet a goal, with built-in privacy and policy controls for secure usage" (NVIDIA).
Snowflake is the most careful of the four. Autonomous agents there are "expected to stay engaged with an outcome," and they "track progress and adapt over time" instead of completing one action and waiting (Snowflake). Read all four and one absence stands out: how many runs the system may start in an hour, what it does at the ceiling, who reads the record afterwards.
Snowflake comes closest to a bound. It describes a loop that keeps going until the objective is reached, a time limit expires or a governance boundary forces an escalation. A time limit is named, with no number and nobody assigned to set it. A limit nobody can choose is a limit nobody can check.
So compare on quantity. Every autonomy claim in a scheduled system reduces to three numbers and a default. All of them sit beside the trigger, outside the model.
The hourly cap has a default and the daily cap does not
The triggers reference puts the two keys side by side: max_runs_per_hour is "Runs the trigger starts in any 60 minutes", default 60, and max_runs_per_day is "Runs the trigger starts in a UTC day", with nothing in the default column (Kortix triggers). The Guide states the first one plainly: "A trigger starts at most 60 runs an hour unless you set another limit" (Automations).
Every trigger starts life with a ceiling of 60 fires an hour whether or not anyone chose it. No trigger starts life with a daily ceiling, so the day stays open until someone writes one.
The hourly default matters most for the trigger types with no clock. A webhook or an app event arrives when the outside world sends it. A retry storm from one broken sender is the case that ceiling exists for. A fire past the limit starts no session. That is what the key promises, and it is enough: a sender that storms the trigger cannot buy more than sixty runs an hour. Each cap is one key in the file or one flag in the CLI, and the file is the version you can diff.
triggers:
- slug: nightly-triage
type: cron
cron: "0 0 2 * * *"
timezone: Europe/Berlin
prompt: "Triage new issues. Open a change request for the fixes you are certain about."
max_runs_per_hour: 4
max_runs_per_day: 4
From a terminal, the same trigger is kortix triggers add nightly-triage --type cron --cron '0 0 2 * * *' --timezone Europe/Berlin --prompt 'Triage new issues. Open a change request for the fixes you are certain about.' --max-runs-per-hour 4 --max-runs-per-day 4 --apply. --max-runs-per-hour and --max-runs-per-day apply on every add and set, while the session flags apply only with --apply.
A runaway repeats, so the caps count fires
The expensive failure of an unattended agent is rarely one catastrophic run. It is the same mediocre run two hundred times, each paying for a sandbox and a model call. The unit that repeats is the fire, so the fire is what a cap counts.
The trigger also stops itself when it keeps hitting its hourly limit, on a threshold you can predict. "A trigger that hits its hourly limit 2 hours in a row pauses itself" (Automations). The pause is tied to the hour, not the day: an hour at the ceiling is a busy hour, two hours in a row is a loop, a day at the ceiling is a budget.
overlap is the third key and the one buyers forget. It defaults to skip for a schedule, and skip "holds a fire while the previous run is active" (triggers keys). Without it, a schedule that fires faster than its runs finish stacks sessions, each on its own cloud computer. Raise the fires without overlap and the machine count rises with them.
The schedule cannot ask for less than a minute
A cron trigger takes six fields, seconds first, and the key states the floor in one sentence: "A trigger fires at most once every 60 seconds" (triggers keys). The table's own example is 0 0 9 * * 1, nine every Monday. Paste in a five-field expression from a system crontab and the fields land in the wrong slots; ask for */30 * * * * * and you are asking for two fires a minute, past what the key allows.
The floor decides what a schedule can express. Anything you would want to poll more often than once a minute belongs to a webhook, because the event already exists and a schedule would only guess at it. For work that does belong on a clock, the interval gets the attention, and so does the window behind it: a schedule also takes max_lateness, and "A missed fire later than this does not run" (the same table).
Set that window and the backlog question has an answer. A fire later than max_lateness does not run at all, and the schedule moves to the next one, so a restart replays nothing past the window. The cap and the window both live in kortix.yaml, where the change request that altered them shows what changed.
What the caps do not decide
A cap governs how much work arrives. It says nothing about what lands. A trigger starts a session with nobody present. The session's work still leaves as a change request. The docs give the agent a contract for it: commit on the session branch, push it, open the change request, then "Report the change request number to the person, and stop" (Kortix docs). Merge is default-deny for agents.
That boundary is what makes a high cap defensible. Work reaches main through a change request a person approves, unless an admin granted the merge capability. Raise the fires and you get more proposed work on branches, waiting on whoever holds project.gitops.merge. The starter agent ships kortix_permissions: all, which lets a session merge its own change request, so a high cap is only as safe as that grant.
Six questions to put to any autonomy claim
- How many fires an hour, and was that number chosen? A published default tells you what happens on day one.
- Is there a daily cap, and what is the value when it is unset? An uncapped day is a decision the vendor made on your behalf.
- What happens at the ceiling? A skipped run with a named reason is a control. A silent retry, or a queue that grows without a bound, is not.
- Does a runaway stop itself, and on which counter? A trigger that pauses after two hours at its limit differs from one that only holds the rest of the day.
- What is the fastest interval the schedule accepts? A minute floor and a lateness window are design choices. "Real time" is a phrase from a brochure.
- Does a missed slot replay as a backlog? A restart that fires the last three thousand slots is an outage with a schedule attached.
Two more posts go deeper on the ends of this: where an agentic workflow ends covers the review a run lands in, and human in the loop vs human on the loop covers the per-call policy that sits underneath the caps.
If you want a system whose autonomy you can read off a file, try Kortix. Free to start, free to self-host.