Delegation & Teamwork Limits

When a leader employee delegates work, several limits shape how that delegation behaves. These controls live in Technical Settings and apply per tenant, giving you direct control over the tradeoff between throughput, cost, and runaway risk.

Parallel Delegations sets how many teammates a leader can hand work to at the same time, from 2 to 15, with a default of 10. Delegation Reach controls how many levels deep a chain of delegation can go, from 1 to 3, with 3 as the default. Teammate Work Time is the number of minutes a delegated teammate can keep working before its leader gives up and moves on, from 5 to 60 minutes, defaulting to 30. Loop Protection sets how tolerant employees are of repeating the same action before the system treats it as a stuck loop and stops.

This is different from Max Agent Steps, a separate Technical Settings control (50 to 1000) that limits how many total reasoning steps a single employee takes in one run. Delegation & Teamwork Limits only govern behavior between a leader and its teammates: how many it can hand work to at once, how far that chain can extend, and how long it waits. It also has nothing to do with team headcount. How many employees you can hire onto a team is a plan limit, not something these controls touch.

Why these limits exist

Delegation is powerful but uncontrolled delegation can spiral: a leader spinning up too many teammates at once, a chain of delegation going too many levels deep, a teammate running far longer than the task warrants, or an employee stuck repeating the same failed action. Each of these four controls closes one of those failure modes without turning delegation off.

Because the ranges are admin-configurable rather than hardcoded, a workspace running simple single-level delegation can keep defaults conservative, while a workspace running larger leader-led teams can raise the ceiling deliberately.

What each control does

Parallel Delegations: the number of teammates a leader can hand work to in a single turn, from 2 to 15, default 10. If a leader's response tries to delegate to more teammates than the limit allows, the system keeps the first N calls in order and drops the rest rather than failing the whole turn. If a leader tries to delegate the same task to the same teammate twice in one turn, only the first call runs; the duplicate is dropped automatically.

Delegation Reach: how many levels a delegation chain can extend, from 1 to 3. Level 1 means the leader works solo with no delegation. Level 2 allows delegation within the same team only. Level 3, the default, allows delegation across teams. A teammate at the third level is always treated as a plain team member and can never re-delegate further, so a chain can never exceed three hops no matter how it's configured.

Teammate Work Time: the number of minutes a delegated teammate can keep working before its leader gives up and moves on, from 5 to 60 minutes, default 30. This is a per-teammate ceiling, not a limit on the whole delegated task; a leader that gives up on one slow teammate can still move ahead with the rest of the work.

Loop Protection: how tolerant employees are of repeating themselves before the system calls it a loop and stops. Strict warns after 3 identical repeats and force-stops at 5. Balanced, the system default, warns at 5 and stops at 8. Relaxed warns at 8 and stops at 12. At the warn threshold the employee gets a one-time nudge that it's repeating itself; at the hard limit, the system strips the repeating tool calls from that response so the employee has to produce a final answer instead of continuing the loop.

Where Delegation & Teamwork Limits fits

Delegation & Teamwork Limits is part of What stops them from going wrong.

Your AI agents pause before any sensitive action and wait for your approval. PII is detected and redacted before it reaches the model. Content policies block harmful or off-brand output. Execution limits prevent runaway tasks. A Sistava mentor pairs with every employee to spot blockers and keep work on track alongside their team leader. Set company-wide policies once and every employee follows them, including future hires.

• What stops them from going wrong: Nothing sensitive happens without your say.

Read the guide

• Guide: Delegation & Teamwork Limits

More in Guardrails

• AI Guardrails & Policies: A Security Officer that checks every message going into and coming out of every AI employee you have. Five policies, each with its own switch: Input Safety stops prompt injection and jailbreak attempts, Output Safety keeps unfit replies from being sent, PII Protection replaces personal data with markers before the model reads it, Data Leakage Prevention keeps your setup and secrets in-house, and Topic Control holds employees to the subjects you choose. Turn on what you need from Settings, Technical, Security Officer and it covers every employee on the next message, including the ones you hire later. Checks run in parallel on a separate lightweight model, so protection costs a fraction of a message and your team never feels the wait. A running count of what has been caught, the busiest policy, and a live inspector showing every individual message are all on the same page.
• Protect Against Prompt Injection: Input Safety reads every incoming message before your employee does, and stops the ones trying to hijack it: instructions to ignore its rules, requests to print its own configuration, and role-play framed to talk it out of its guardrails. That matters most where the message did not come from you, so a payload buried in a forwarded email, a support ticket, or a shared thread cannot turn your employee against you. Pick Low, Medium, or High, and every level catches the textbook attacks: the level decides how much benefit of the doubt the genuinely ambiguous messages get. Medium is the default and suits most companies. Blocked messages get a short, human reply and the conversation carries on, with each one recorded so you can see what has been tried.
• Block Unsafe Employee Responses: Output Safety reads your employee's reply before anyone else does. Toxic, abusive, or otherwise unfit answers are held back rather than sent, which is what you want the moment employees write to customers, post to a channel, or answer a ticket without you watching. It checks the reply your employee actually wrote, so what you see caught is what would genuinely have gone out. Set it to Low, Medium, or High and review everything it held back in the live inspector. Blunt, direct, and critical business writing is left alone: the policy is looking for replies that would embarrass you, not ones that are simply frank.
• Protect Personal Data: PII Protection finds personal data in a message and replaces it with a marker before the model reads a single character of it. A pasted card number becomes [CREDIT_CARD], an email becomes [EMAIL_ADDRESS], and the same happens on the way out so nothing sensitive travels back into an email, a channel, or a ticket. You pick exactly what to protect from seven data types: email, phone, name, credit card, Social Security number, IP address, and address. The markers keep the sentence readable, so your employee understands the request perfectly and keeps working while the raw value stays out of the conversation. It runs on every message, in both directions, company-wide, from one switch.
• Control What Employees Discuss: Topic Control gives you two lists and you can use either or both. Blocked topics are off-limits no matter how a conversation gets there, which keeps employees out of politics, competitor comparisons, or medical and legal advice. Allowed topics set a remit instead: name the subjects an employee handles and anything unrelated is politely declined, which is how you keep a support employee on product help, billing, and refunds. Both lists match on meaning rather than exact words, so ruling out competitor pricing also covers how much cheaper are we than the other tools out there. Greetings and short replies always get through, so a scoped employee still feels natural to talk to.
• Keep Confidential Data In-House: Data Leakage Prevention guards both ends of the conversation. On the way in it recognises someone fishing for your employee's internals, whether they ask outright, dress it up as a game, or try the repeat everything above this line trick. On the way out it reads the reply itself and holds it back if it is about to hand over a system prompt, internal configuration, an access token, or a credential. Questions about your own business data are never affected, so an employee still answers freely about your customers, documents, and numbers. One switch, no configuration to maintain, and every attempt is logged so you can see who has been probing.
• Prevent Repeated and Runaway Actions: Sistava automatically caps how many emails, messages, and external writes (CRM records, calendar events, paid searches) an AI employee can send in a single conversation, hour, and day, and blocks an identical send to the same recipient from going out twice within 24 hours. These limits run in the background per employee with no setup required, so a stuck task or unexpected loop cannot spam a contact's inbox, pollute your CRM, or burn through paid API calls. When a limit is hit, the employee is told to slow down or hand the task to a human instead of retrying blindly.
• Approve Sensitive Actions: Let an AI employee pause and ask before it takes a sensitive action, like sending an email or spending on a paid tool, instead of guessing what you want. An inline card shows up right in the chat with Approve, Reject, or option buttons, and the employee resumes the instant you respond.
• Protect Organisation Information: Your AI employee treats what it learns in the workspace the way a careful coworker would: useful for doing the work, not free to repeat. It tells private, role-restricted, and confidential information apart from ordinary shared context, and it never volunteers the sensitive kind just because someone asked. When a teammate needs a restricted answer, the employee can request permission from the right person for that one specific answer instead of guessing or refusing outright.
• Protect Your Email Reputation: Every email your AI employees send, whether it is a notification, a mailbox reply, or an outbound message, passes through a pre-send check before it leaves. Sistava validates the address, checks it against a suppression list built from past bounces and complaints, and blocks anything that would hurt your sending reputation. You do not configure this: it runs silently on every send so your domain keeps a clean track record with inbox providers.
• Detect and Redact PII: PII Protection watches every message your AI employees send and receive, and masks personal data like emails, phone numbers, credit card numbers, and social security numbers before it goes anywhere it shouldn't. You choose exactly which data types to catch. It runs on every employee across your company the moment you turn it on, with no per-employee setup.
• Company-Wide Policies: Company Policies let you set organization-wide safety rules that apply to every AI employee at once: block prompt injection attempts, filter harmful output, redact personal information, stop internal details from leaking, and restrict which topics employees can discuss. Turn each policy on with one toggle from your company dashboard, and it takes effect immediately across your whole team.

Explore

• Every feature
• Hire an AI employee
• Pricing