# Spending Limit Set a ceiling on how many credits your workforce can spend per hour, day, week, or month, so a runaway task or a busy day never turns into a surprise bill. Spending Limit puts a hard ceiling on how many credits your workforce can burn in an hour, day, week, or month, whichever cadence matches how you think about cost. Set it once and every employee's spend counts against the same shared cap, so one runaway task or one unexpectedly busy day can't turn into a bill you didn't see coming. Work that's already running is never interrupted mid-task when a limit is hit, only new spend beyond the cap is held back. Need more room right now, one click releases an extra period's allowance without raising the limit permanently, so a genuinely busy day doesn't require you to renegotiate your own settings. Leave the amount blank and we pick one for you: a default that spreads your plan's monthly credit allowance, plus any bonus credits you've been granted, evenly across the period you chose, then doubles that pace so ordinary work never brushes against it. A monthly limit skips the doubling and simply mirrors your plan's own pool, since a cap above the pool itself would mean nothing. Plans with no fixed monthly allowance, the Free plan, which runs on a lifetime cap instead, and unlimited or Enterprise plans, have nothing to derive a pace from, so the field stays open rather than guessing at a number. It's off by default, so it never surprises a new workspace with a cap it didn't ask for, and it changes nothing about your plan or your credit balance, it only decides how fast that balance is allowed to move. This matters more with an AI workforce than with any single tool, because a whole team of AI employees can work in parallel: several running at once means several spending at once, and a pace control is the only thing standing between that parallelism and a bill you didn't plan for. ## A Brake, Not a Plan Change Spending Limit doesn't touch your plan, your credit balance, or what any individual employee is allowed to do. It's purely a pace control: how many credits can move through the workspace in a given hour, day, week, or month, no matter which employee or task is spending them. That makes it useful in opposite situations. Turn it on tight while you're testing a new workflow and don't want a mistake to run away with your balance. Turn it off entirely once you trust the workspace's normal spend pattern. ## What Happens When You Hit the Limit Work already in flight always finishes, a task doesn't get cut off mid-sentence because the clock ran out. New work that would push spend past the cap waits until the next period starts, or until you release extra room with one click. Budget activity records each actual pause with the limit, usage, and remaining plan credits at that moment, while its local check is completely free. ## Built for a Workforce, Not Just One Employee The cap applies across the whole workspace, every AI employee's spend counts against the same shared number. That's the point: as you hire more employees and more of them run in parallel, Spending Limit is what keeps total spend predictable without you having to set a limit per employee individually. ## Not the Same as the Per-Turn Controls Next to It Spending Limit lives on the same Rate Limits page as several other numbers it's easy to confuse it with: how many employees you can have hired at once, how many actions an employee can take in one turn, how many teammates can work at the same time, how deep a delegation chain can go, and how long a delegated teammate is allowed to run. Two more, model calls per turn and time per turn, are fixed walls against a runaway loop rather than settings you choose. None of those move when you change your spending limit, and your spending limit doesn't move when you change them. Each is its own control, shown on its own row, with its own link back to wherever it's actually enforced. Spending Limit paces credits; the rest bound behavior within a single turn or delegation. ## How It Works **A pre-execution check against a calendar-aligned window, not a mid-task kill switch** You choose an amount and a period. The smallest amount you can set is 100 credits, a floor that exists so a mistyped number cannot lock you out of a plan you already paid for; there is no way to set it to zero, only to switch it off. Periods are calendar-aligned in UTC rather than rolling, so a daily limit always resets at midnight UTC, a weekly one on Monday, and a monthly one on the 1st. The current window's end time is always shown, so you know exactly when the pause lifts. Every time an employee is about to start a new turn, the system checks total spend so far in the current window against your limit. Under the limit, the turn proceeds normally. At or over it, new work is held rather than started, and the employee tells you in chat with a link back to the Rate Limits page, alongside a notification and an email carrying the same link. You hear about a warning at 80% of the window and about the pause itself once each, so a heavy day does not turn into a stream of repeated alerts. If work genuinely cannot wait, there are three ways through it from the same page: release the current period's extra allowance, which doubles the limit for that window only and reverts by itself once the window ends; raise the number outright, which takes effect immediately; or switch the limit off entirely, leaving only your plan's credit allowance in force. None of these grant extra credits, they only change how fast you are allowed to spend the ones you already have. Because this brake sits inside a plan you already paid for, it fails open: if the system cannot resolve a limit for any reason, no cap is applied rather than blocking your team by accident. The plan's own monthly or lifetime credit pool is the layer that actually protects your bill, and that layer stays strict regardless of anything on this page. ## Use Cases ### Cap a runaway autonomous loop before it costs a month's budget An employee working through a schedule or a long delegated task can spend faster than a human would notice. Setting a daily or hourly limit means the worst case is a paused workforce and a notification, never a surprise bill at the end of the month. ### Pace a big one-off job across the days you actually have Before kicking off a large batch task, check how long your current number would last against it, and raise the limit or release the current period's extra allowance if the job genuinely needs to run faster than your normal pace. ### Let a new hire's daily cost show up on the same page as their teammates' The spending limit sits next to every other limit your workforce runs against, plan credits, employee headcount, per-turn controls, so you can see in one place whether a specific number needs raising or whether the team is simply within its pace. ### Recover from a tight limit without losing the day's work If a limit set too tight pauses the team mid-project, the same page that paused you offers the fix: release this period's extra allowance for an immediate, self-reverting boost, or raise the number outright and carry on. ## FAQ ### Does hitting the spending limit stop work that's already running? No. In-flight work always finishes. The limit only holds back new spend beyond the cap. ### What if I need more credits right now? One click releases an extra period's allowance without permanently raising the limit. ### Is Spending Limit on by default? No, it's off by default. You turn it on and choose the cap and cadence yourself. ### Does the limit apply per employee or across the whole workspace? Across the whole workspace. Every employee's spend counts against the same shared cap. ### What number do you pick if I leave the amount blank? Roughly double your plan's steady pace for the period you chose, spread from your plan's monthly credit allowance plus any bonus credits. A monthly limit skips the doubling and matches your plan's pool exactly. ### Does Spending Limit save me money or lower my bill? No. It paces spend inside the plan and credits you already have. It doesn't change your bill or your credit balance. ### What happens to my limit when I change plans? A number you left blank recalculates for the new plan automatically. A number you typed yourself stays exactly as you set it. ## Where Spending Limit fits Spending Limit is part of How you see what they did. A real-time activity feed shows who is working on what right now. The step-by-step inspector traces every tool call, decision, and reasoning chain. Cost tracking breaks down spend per message, per employee, and per team. Walk through your live 3D office to see your workforce at a glance. - [How you see what they did](/en/features/observability): See everything. Miss nothing. ## Read the guide - [Guide: Spending Limit](/en/guide/monitor/activity) ## More in Monitoring - [Activity Timeline](/en/features/observability/activity_timeline): See every piece of work your AI employees do as it happens: chat replies, scheduled runs, tool calls, delegations, and finished deliverables, all logged as activities you can open and inspect. It runs automatically for every employee with no setup, and a live feed in the workspace sidebar shows actions as they occur so you never have to wonder what is happening right now. - [Action Inspector](/en/features/observability/activity_inspection): Click into any single activity and see exactly what your AI employee did: the model call pipeline, every tool it used with inputs and outputs, cost broken down by category, a duration waterfall, and the plan it followed. Available from the Activity tab, from Inspect on any chat message, or from the sidebar timeline. - [See What Your Employee Is Told](/en/features/observability/prompt_inspection): Open any activity in the Activity Inspector and read the exact system prompt your AI employee received for that run: every instruction, every tool definition, and the manifest of which skills and duties were loaded and why. Nothing paraphrased, nothing summarized, the same text the model saw. - [Credit Usage History](/en/features/observability/credit_usage_history): See exactly where your monthly credits go: split spend from direct employee requests and automation or system work, then inspect every charged system operation, including AI work, tools, Officer checks, knowledge, voice, meetings, video, and email. A burn chart shows the trend over time, and a separate grants table lists every bonus credit you received from promos, referrals, or purchases, with source and date. - [Team Dashboards](/en/features/observability/team_dashboards): Every team gets its own dashboard the moment you open it: team health, the current sprint, work in flight, momentum, objectives, and KPI progress, all built from data the platform already has. On the Custom plan, connect data sources and the same dashboard adds Revenue & Pipeline, Demand & Conversion, and Reach & Engagement cards for that team. - [Data Export](/en/features/observability/data_export): Every workspace surface that shows your history, chat threads, the task board, activity logs, and Drive files, has its own download control that exports the current, filtered view as Markdown, CSV, or JSON. Use it to pull records for an audit, share a run outside the app, or keep an offline copy of what an employee produced. - [Review the Quality of Every Deliverable](/en/features/observability/quality_evaluation): After an employee does real work, a quality reviewer scores each deliverable against a standard and shows the verdict in the activity inspector. Everyday chat is left alone, so you only grade real output. - [3D Office View](/en/features/observability/office_3d): A workforce of AI employees is easy to lose track of as a list of chat threads. The 3D Office View turns it into a place: every employee is a character at a desk, hot-desk, or the lounge, moving between them live as their status changes, so you can see your whole company working at a glance instead of clicking through tabs. - [In-App Notifications](/en/features/observability/in_app_notifications): See the moment an Employee finishes work, needs a decision from you, or your credit balance runs low, through a bell icon in your workspace that always fires. Reply straight from the notification drawer for Employee updates and comment threads, and control which events also reach your email through a short list of categories. - [Reply to Notifications](/en/features/observability/notification_reply): Reply straight from the notification drawer, whether it is an update from an Employee or a comment on your work, and your response goes back with the full context of what it is replying to. No need to open the chat or dig up the artifact first. - [Email Notifications](/en/features/observability/email_notifications): Sistava emails you when an employee finishes work, needs your approval, hits a blocker, or your credit balance runs low, so nothing important gets stuck waiting for you to open the app. You choose which categories of email you want; account security and billing mail stay on because they carry information you need regardless of your other preferences. - [Email Digest Notifications](/en/features/observability/email_digest_notifications): A rolled-up email that summarizes what your AI employees did over a set period, instead of a separate message for every event. Today, notification email in Sistava sends per event and per category (employee updates, task completion, credit alerts, and so on); a digest option that batches those into one scheduled email is planned but not built yet. ## Explore - [Every feature](/en/features) - [Hire an AI employee](/en/market) - [Pricing](/en/pricing)