Personal Preferences Memory

Every workspace has a founder, and every founder has small preferences that make working with a team smoother: what to call you, when you're actually online, whether you want short bullet answers or full paragraphs. Sistava lets your team leader capture these facts directly from conversation and hold onto them, the same way a real assistant would after working with you for a week.

You don't fill out a form. You just say it: "call me Mo", "I only work weekdays, don't ping me on weekends", "keep replies short and to the point, bullets over paragraphs". The leader picks that up, saves it to your profile, and every reply from then on reflects it.

This is a different thing from your workspace's general Memory, which extracts facts, decisions, and project context from every conversation without anyone asking. Personal Preferences Memory is narrower and more deliberate: three named fields, written only when the team leader saves them, either because you said so in chat or because you typed them directly into your account settings. Nothing here is inferred; it only holds what you actually stated.

The same three fields are also visible and editable from your account settings page, so you can set them directly if you'd rather type them once than mention them in chat. Either path writes to the same place, so there's no conflict between the two.

What it stores

Nickname: how you want to be called instead of your full account name, capped at 80 characters. Work schedule: a plain description of when you work, capped at 200 characters. Output preference: a free-text description of how you like replies written, for example short and direct, or fully spelled out with headers, capped at 1,000 characters.

Each cap is read directly off the underlying database column, not hardcoded in the tool, so it can never drift out of sync if the column is widened later. Go over it and you get a clear message telling you exactly how many characters over the limit you are, rather than a raw database error. That message-instead-of-crash exists because the first paying account hit the raw error twice in their first hour, trying to set a nickname.

Who can change it

Only the team leader employee can write to your profile. If you tell a non-leader employee a preference, that employee is expected to relay it to the leader rather than saving it directly, so your profile never ends up with conflicting versions written by different employees.

You can also view or edit your nickname, work schedule, and output preference directly on your account settings page at any time. Updating it there and updating it through chat both write to the exact same record, so whichever you use last is what takes effect.

If you set a nickname, employees use it instead of your account name; if you never set one, they fall back to your first name, then your full name, then a neutral "your boss" once none of those exist. If you never state an output preference, the reply-style guidance is left out of the conversation entirely rather than shown as an empty instruction.

What actually changes because of each field

Nickname and output preference are injected into every employee's reply automatically. There is nothing to trigger, and nothing further to configure: once saved, the next message from any employee already reflects them.

Work schedule works differently today. It is stored, and both you and your team leader can see it, so the leader can check it before proposing a time for something recurring, like when to run a standing daily brief you never gave a time for. It is not currently enforced as a hard constraint by the scheduler itself the way nickname and output preference are enforced on every reply, so treat it as information your leader can consult, not a guarantee that nothing will ever run outside those hours.

Where Personal Preferences Memory fits

Personal Preferences Memory 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: Just ask. It configures itself.

Read the guide

• Guide: Personal Preferences Memory

More in Behavior

• Shape Your Employee's Personality: 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: 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: 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.
• 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.
• Choose How Deeply Your Employee Thinks: 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: 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: 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: 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.
• Skills They Can Master: 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
• Hire an AI employee
• Pricing