# Ask Your Employee About Sistava

Ask your employee about Sistava itself and get a real answer: what plan you're on, what a feature costs to unlock, what your limits are, or who else you could hire. Your employee reads the live plan and feature data at the moment you ask, so the answer matches what your account actually has right now, not a guess from training data.

Your AI employee does not just work inside external tools. It operates the AI Employee platform itself. Ask it to hire a new team member, adjust a skill configuration, connect a tool, or update a duty, and it navigates the platform interface and makes the changes for you. You give instructions. It handles the clicks.

This turns every employee into a self-service administrator. Instead of opening settings panels and toggling options yourself, describe what you want in chat. "Add the SEO writing skill." "Connect my Google Calendar." "Change the approval mode to always ask before sending emails." Your employee configures itself and the platform around it.

Platform control is especially powerful for team leaders. A leader can onboard new hires, assign skills across the team, adjust schedules, and reorganize the org chart, all through conversation. The platform becomes something your AI workforce manages, not something you have to operate manually.

The same awareness works the other way round. Ask your employee about Sistava itself and it answers from your live account: which plan you are on, what your limits are, which features you already have and which are still locked, and who else you could hire. It reads that at the moment you ask rather than recalling it from training, so the answer matches what your account actually holds right now.

Because the answer comes from live data, it changes the second your account does. Unlock something today and the very next question about it gets the new answer, with nothing to refresh and no delay. Asking is a read and only a read, so looking up your plan never alters your plan, and anything that touches billing stays a decision you make.

That makes your employee the quickest place to get an answer about the product itself. Instead of hunting through settings pages to work out whether a capability is included, ask the employee already sitting in front of you. And when you describe a problem rather than a job title, it can walk the roster of available roles and teams and tell you which one fits the work you just described.

## An AI Employee That Manages Itself and Its Teammates

Platform Control gives a designated AI employee, typically a team lead or coordinator role, the ability to operate the Sistava platform directly. It can update its own settings, assign tasks to other AI employees, adjust configurations, and manage the workforce it is part of. Self-administering AI teams without constant human input.

This is not theoretical automation. A coordinator agent can receive a request like "spin up a research assistant for the new client project," handle the configuration, assign skills and tools, and confirm when the new employee is ready. Human oversight remains in place, but the routine administrative work is handled by the agent.

## Self-Configuration Based on Context

Platform Control enables agents to self-configure when context changes. If a new project requires a skill the agent does not currently have, it can request or activate it. If a tool is no longer needed for the current sprint, the agent can remove it from its active set. Configuration that adapts to work, not the other way around.

This dynamic reconfiguration is audited. Every platform action an agent takes is logged with timestamp and justification. Managers can review and override any change. The agent operates with authority bounded by your policies.

## The Foundation for True Agent Orchestration

Multi-agent orchestration at scale requires agents that can coordinate without a human mediating every interaction. Platform Control is how Sistava enables that. A lead agent can delegate to specialist agents, monitor their progress, reassign blocked work, and compile results, all within the platform.

For enterprises running complex AI workflows, this means a meaningful reduction in the management overhead of operating a large AI workforce. The agents handle more of their own administration, freeing human managers to focus on goals and outcomes rather than configuration and coordination.

## How It Works

**Agents can update their own settings, add skills, configure tools, and manage their team directly from chat.**

Every configuration action available in the workspace UI is also available to the agent as a tool. An agent can add a skill to itself when it identifies a capability gap, update its own memory, adjust a duty, assign a task to a teammate, or reconfigure a tool connection, all triggered by a conversation or by its own initiative during a task. The agent is not just an executor. It is a participant in its own configuration.

This matters for scale. When you manage dozens of agents, having each one capable of self-management reduces the administrative overhead on your side. You can instruct an agent to prepare for a new project by acquiring the right skills and tools, and it handles that preparation itself. Oversight and approval controls ensure the agent never makes changes you have not authorized.

Questions about the platform take the same path. When you ask what your plan includes, where a limit sits, or who you could hire next, the employee looks it up against your live account, answers from that, and goes straight back to the work in front of it. The lookup is read only by design, so a question about your plan can never turn into a change to your plan, and hiring or upgrading still runs through you.

## Use Cases

### IT admin monitoring agent activity across the organization

See what every AI employee is doing in real time. Intervene, pause, or redirect without waiting for a report.

### Operations lead reviewing and approving agent actions before they execute

Set approval requirements on sensitive actions. The AI agent pauses and waits for a human decision before proceeding.

### Security team auditing all agent decisions and tool usage

Full activity logs let you trace every action an AI employee took, why it took it, and what it produced.

### Manager adjusting agent behavior without rebuilding it

Change rules, skills, or access controls on a live agent. Updates take effect immediately without downtime.

## Comparison

| Before | After |
|---|---|
| Once an AI agent runs, you have no visibility into what it's doing. | Real-time monitoring shows every action, decision, and result. |
| Sensitive actions execute automatically with no human checkpoint. | Configure approval gates that pause the agent and wait for your sign-off. |
| Debugging agent behavior means sifting through unstructured logs. | Structured activity trails make every decision traceable and reviewable. |
| Changing agent behavior requires a full reconfiguration. | Update rules and controls on a live agent without any downtime. |

## FAQ

### Which AI employees can use Platform Control?

Platform Control is a capability you assign explicitly. Typically it is given to a coordinator or lead agent role. Not every AI employee in your workforce needs or should have the ability to modify platform settings.

### Can a Platform Control agent hire new AI employees without approval?

No. Actions that affect billing, like hiring new employees or upgrading plans, always require human approval. Platform Control covers operational management like task delegation and configuration. Billing changes stay with human administrators.

### Is there an audit log for actions taken via Platform Control?

Yes. Every platform action taken by an agent is logged with a timestamp, the agent that initiated it, and the justification it provided. Managers can review and reverse any action from the audit log.

### How does Platform Control differ from just assigning tasks to multiple agents?

Task assignment is manual. Platform Control lets an agent actively manage other agents: delegating work dynamically, adjusting their configurations, and monitoring their progress, without a human facilitating every step. It is the difference between a human coordinator and an AI coordinator.

### Can my AI agent update its own settings without me doing it manually?

Yes. Self-managing agents can adjust their own skills, memory, and configuration through conversation when given the appropriate permissions. This reduces the overhead of manually maintaining each employee.

### Can I just ask my AI employee which plan I am on and what my limits are?

Yes. Your employee reads your live account when you ask, so it can tell you your current plan, the limits attached to it, which features you already have, and which are still locked. It answers from what the account holds at that moment rather than from anything memorised earlier.

### Will my AI employee know about a feature I unlocked today?

Yes. Plan and feature answers are read fresh every single time you ask, so a change made minutes ago already shows up in the next answer. There is no cached copy to wait on and no gap between what you changed and what your employee tells you.

### Does asking my AI employee about the platform change anything in my account?

No. Answering product questions is a read only lookup, so asking about your plan, your limits, or the roles you could hire never alters any of them. Anything that affects billing, such as hiring or upgrading, stays a decision you make yourself.

> I told my agent it would be handling investor relations going forward. It added the relevant skills, updated its own persona description, and briefed the rest of the team. I did not touch a single setting.
>
> Nathan P., Founder · early-stage startup

## Where Ask Your Employee About Sistava fits

Ask Your Employee About Sistava is part of Things that control how they behave.

Skip the settings panels. Tell your AI employee what skills to learn, what rules to follow, and what personality to use, all through natural conversation. They can even browse the skill catalog and configure themselves as work evolves.

- [Things that control how they behave](/en/features/behavior): Just ask. It configures itself.

## Read the guide

- [Guide: Ask Your Employee About Sistava](/en/guide/setup/hire)

## More in Behavior

- [Shape Your Employee's Personality](/en/features/behavior/employee_persona): Write a short persona prompt to set how each AI employee talks: formal or casual, brief or detailed, warm or blunt. Every employee starts with a role-based default, and you can rewrite it any time from the Profile tab. The change applies to the employee's next message, no restart needed.
- [Customize Employee Profile](/en/features/behavior/employee_profile_customization): Every hire's Profile tab is fully editable: name, role, team, avatar, persona, language, and tone of voice, all changed in place without a rehire. Updates apply from the next message onward, across every channel the employee uses. A change history on the same tab shows who edited what and when, including edits the employee made to its own persona.
- [Credits Saver](/en/features/behavior/credits_saver): Credits Saver watches every message and quietly hands the easy ones (greetings, quick acknowledgements, 'make that shorter') to a lighter, cheaper model, while real work still runs on the model you picked. On everyday back-and-forth that often means 40 to 50% fewer credits, with no drop in quality where it counts. It is on by default and fully in your control: turn it on or off anytime, and see tracked credits saved, its router cost, and the net benefit on its own page.
- [Choose How Deeply Your Employee Thinks](/en/features/behavior/reasoning_effort_control): Set how much an employee thinks before it answers, from Off through Minimal, Light, Medium, and Deep, or leave it on Auto so the platform picks the right depth per message on its own. It applies workspace-wide from the AI Behavior settings page, with a per-employee override when one employee's work genuinely needs a different depth than the rest of the team.
- [Set a Per-Task Action Limit](/en/features/behavior/max_actions_override): Set exactly how many actions one employee can take while working on a single task, from 50 up to 1,000. Give a research-heavy employee more room to search, read, and delegate before it has to stop and report back, or cap a simple support employee tighter so it never wanders past what the task needs.
- [Skills Catalog](/en/features/behavior/skills_catalog): Give any AI employee a step-by-step playbook for a specific type of work: how you want blog posts researched, how outreach emails get structured, how a report should be formatted. The employee reads the full skill only when a task actually matches it, so you can attach as many as you want without slowing anything down.
- [Duties Catalog](/en/features/behavior/duties_catalog): Give any employee a set of standing rules they follow on every single interaction, no exceptions: respond within the hour, always CC you on sales emails, never discuss pricing without approval. Pick from the built-in catalog or write your own in plain English, and the employee carries the full text of every active duty in mind on every turn.
- [Personal Preferences Memory](/en/features/behavior/founder_personal_profile): Tell your team leader once how you want to be addressed, when you're working, and how you like answers written, and every employee on your team picks it up automatically. No settings form to fill out: just say it in chat and it sticks.
- [Skills They Can Master](/en/features/behavior/custom_skills): Teach any AI employee your own step-by-step process, from a blog-writing checklist to a lead-qualification script, and it follows those exact steps whenever a matching request comes in. Write it yourself in the Skills tab, or just describe your process in chat and the employee turns it into a skill. Skills load only when the task matches, so you can add as many as you want without slowing anything down.

## Explore

- [Every feature](/en/features)
- [Hire an AI employee](/en/market)
- [Pricing](/en/pricing)