Manager gets notified when AI agent needs a decision
When the AI employee reaches a step that requires human judgment, it sends a targeted notification with context and options, not a generic alert.
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.
Notifications keep you in the loop without checking the workspace. When an employee finishes a task, you get notified. When approval is needed, you get notified. When credits drop below 25 percent, 15 percent, or hit zero, you get notified. Every notification type maps to a real event that needs your attention, not noise.
Configure notification preferences per event type. Task completions, approval requests, choice requests, credit warnings, and credit exhaustion each have their own toggle. Notifications deliver through in-app alerts and email so you never miss something important while away from the workspace.
The community feedback board lets you request features, report bugs, or suggest improvements directly from the settings page. Every request is visible to the team, and others can vote on what matters most. The roadmap is shaped by the people actually using the product.
The bell in your workspace always fires. Everything an employee needs you for lands there whether or not you have switched anything else on, so there is one place that is guaranteed to be complete. On top of that you choose a single loud channel, and only that one delivers, which is what stops one event arriving three times in three different places while you are trying to work.
Not every update deserves to interrupt you, so several layers sit between an event and your inbox. Repeats of the same kind of alert are spaced out rather than stacked, there are ceilings on how much email can reach one person in a day and in an hour, and a delayed email is dropped entirely if you already read the item in the bell first. The point is that when something does reach you, it earned the trip.
You can answer without leaving the drawer. Hit reply on an employee update or a comment thread and the conversation opens with the context already loaded, so a two word answer does not cost you a walk across the app and back. If you belong to more than one organization, each keeps its own separate feed, so one client's work never appears while you are looking at another's.
The feedback board runs on the same principle. Post a bug, a feature request, an improvement, or a question, vote on anything already there, and comment in a thread. Each post moves through a visible status, from new to under review to planned, in progress, and finally done, and when someone comments on a post you wrote, voted for, or replied to, you hear about it in the bell like everything else.
Stay Informed Without Watching a Screen All Day
Autonomous agents work in the background, which means you need a reliable way to know when something requires your attention or has been completed. Notifications deliver the right signal at the right time: task completed, approval requested, credit threshold reached, or error encountered.
Notification rules are configurable per event type and per delivery channel. You choose whether to be notified via in-app alerts, email, Slack, or webhook. You control which events are worth a ping and which can accumulate silently in the activity feed for periodic review.
Approval Alerts That Close the Loop
Approval notifications deserve special mention because they are time-sensitive. When an AI employee reaches an Approval Gateway, it cannot proceed until a human responds. Approval alerts are delivered immediately through your highest-priority channel and include enough context to decide without opening a separate tab.
You can approve or reject directly from the notification in supported channels. This minimizes the interruption to your workflow while keeping the agent moving. If no response arrives within a configurable timeout, the notification escalates to a backup approver or cancels the action with a logged reason.
Community Feedback to Shape the Product You Use
Sistava includes a built-in community feedback and feature voting system so users can propose improvements, upvote existing requests, and see what is on the roadmap. This is not a third-party tool bolted on. It is integrated directly into the platform so you can submit feedback without leaving your workspace.
Feature votes are visible to all users so you can see what the broader community values and add your weight to requests that matter to your team. The roadmap view shows which requests are under consideration, in development, or shipped, so you always know where your feedback went.
How It Works
Your AI agents send you targeted alerts for the moments that matter: task completions, approval requests, credit warnings, and error conditions.
Configure notification rules per event type and delivery channel. Task completed goes to Slack. Approval needed goes to email and Slack. Credit balance below threshold triggers an in-app alert and an email. You decide which events are noisy enough to interrupt you and which can wait in the activity feed. Notifications are scoped per employee, per team, or organization-wide.
Approval notifications are bidirectional. When an AI agent pauses to request human input before taking a sensitive action, you receive the request with full context, the task, the proposed action, and the agent's reasoning, and you respond with a single click. The agent resumes the moment you approve. This is how you stay in control without staying in the loop for everything.
None of this is a separate product to run. Preferences live in your account settings as a short list of categories with a switch each, the bell sits in the header of every page, and the feedback board opens from the same place. There is no rules engine to build before any of it is useful, and switching a category off changes only what reaches you, never what your employees are allowed to do.
Use Cases
Team stays informed on long-running agent workflows
The AI agent sends a notification when a multi-hour task finishes, so the team knows when to pick up the next step.
Stakeholder provides feedback on AI output
After the AI employee completes a task, the notification includes an inline feedback form so the stakeholder can rate or correct the output immediately.
Support lead gets alerted on AI escalations
When the AI agent flags a ticket it cannot resolve, the support lead receives a notification with full context and the agent's reasoning.
Comparison
| Before | After |
|---|---|
| Teams check the platform constantly to see if the agent is done. | Smart notifications deliver the right alert at the right moment. |
| Feedback on agent output is collected separately, if at all. | Feedback is built into every notification, one click to respond. |
| All agent alerts look the same, signal lost in noise. | Notifications include context, so the recipient knows exactly what to do. |
| Critical escalations go unnoticed until someone checks in. | The AI employee escalates proactively and waits for a human decision. |
FAQ
Which notification channels are supported?
In-app alerts, email, Slack, and webhooks are supported. Each event type can be routed to one or more channels independently. For example, task completions go to in-app only, while approval requests go to both in-app and Slack.
Can I approve agent actions directly from Slack?
Yes. Approval request notifications sent to Slack include interactive buttons for approve and reject. Your response is sent back to the agent without you leaving Slack.
How does the community voting system work?
You can submit feature requests or upvote existing ones from within the platform. The team reviews high-voted requests when planning each cycle. You receive a notification when a request you voted for changes status.
Can I turn off notifications I do not need?
Yes. Notifications are opt-in per event type. You can turn off categories you do not want without affecting other users or system behavior. Workspace admins can set notification defaults for the team.
How does the AI agent notify me when something needs my attention?
Sistava sends smart notifications when the agent completes a task, hits a blocker, or needs your input. You can configure which events trigger alerts and how, so you stay informed without being spammed.
Will I get the same alert in the app and by email at the same time?
Sistava fires the workspace bell for everything, and beyond that only one loud channel delivers per notification. You pick which one, so an approval request reaches you in the bell and in your chosen channel, not in three inboxes at once. Email also has daily and hourly ceilings so a busy day cannot flood you.
I belong to more than one organization. Do the notifications mix together?
No. Sistava keeps a separate notification feed for each organization you belong to, scoped to the one you are currently in. Work from one client never shows up in the bell while you are looking at another, and switching organizations switches the feed with it.
What happens to a feature request after I post it?
It goes onto the community board where anyone using Sistava can read and vote on it, and it moves through visible statuses from new to under review, planned, in progress, and done. When someone comments on a post you wrote, voted for, or replied to, you get a notification, so you find out what happened to your idea without going back to check.
I get pinged on Slack when an agent finishes a deliverable or needs my approval. Everything else runs silently. It is the right level of involvement.
Where In-App Notifications fits
In-App Notifications 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: See everything. Miss nothing.
Read the guide
More in Monitoring
- 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: 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: 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: 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.
- 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.
- 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: 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: 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: 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.
- Reply to Notifications: 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: 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: 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.