# 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.

The activity feed is a live, continuously updating timeline of everything happening across your AI workforce. See which employees are active, what tasks they are working on, which tools they are using, and what they just completed. It is your control room for the entire operation.

Filter by employee to focus on one person's work. Filter by team to see how a department is performing. Filter by action type to track all email sends, all web searches, or all document creations across your entire workforce. The feed updates in real time, so you are always looking at the current state, not a stale snapshot.

Delegation chains are visible in the feed. When a leader delegates a task to a specialist, you see the handoff. When the specialist completes it, you see the result flow back to the leader. For multi-employee workflows, the feed shows the complete coordination sequence so you understand how work moves through your organization.

## A Live Timeline of Everything Your AI Workforce Is Doing

The Activity Feed is a real-time stream of every action taken by every AI employee in your workspace. Messages sent, tools called, files written, approvals requested, tasks completed. It updates live as your agents work, giving you an always-current picture of workforce activity without polling or refreshing.

This is your operational command center for managing autonomous agents at scale. When something unexpected happens, the feed shows you exactly when it occurred, which employee was involved, and what preceded it. When things are running smoothly, it gives you confidence that your AI workforce is productive and on task.

## Filter by Employee, Team, Action Type, or Time Range

A workspace with dozens of active AI employees generates a lot of activity. Powerful filtering makes the feed useful rather than overwhelming. You can narrow the view to a specific employee, an entire team, a category of action (external communications, file operations, API calls), or a custom time window.

Filters compose, so you can ask questions like "show me all external emails sent by the sales team in the last 24 hours" or "show me every approval request from any agent this week." The feed remembers your last filter configuration so returning to a specific view is instant.

Each activity entry links directly to the relevant conversation, tool call trace, or document. You do not just see that something happened. You can drill into the full context in one click.

## Real-Time Activity as an Agent Orchestration Oversight Tool

In multi-agent workflows, activities from different agents interleave as they collaborate on tasks. The Activity Feed shows the full cross-agent timeline, so you can see how orchestrator agents delegate to sub-agents and track the outcome of each delegation. This is essential for debugging complex agent orchestration pipelines.

The feed also surfaces anomalies automatically: unusually high activity rates, repeated failures, approval backlogs, and agents approaching execution limits. These signals appear inline with the activity stream so you notice them in context rather than hunting through separate alert dashboards.

## How It Works

**Every action your AI agents take is logged to a live, filterable timeline so you always know what happened, when, and why.**

The activity feed is a real-time stream of every event your AI employees generate: messages sent, tasks created, tools called, decisions made, approvals requested, files saved. Events appear the moment they occur. Filter by employee, event type, date range, or status to find exactly what you need. Each event is expandable to show the full context.

This is your accountability layer. When a customer asks why an email was sent, you find it in the feed within seconds. When an agent's behavior seems off, the feed shows you the exact sequence of events that led there. The activity feed is also the input for the execution inspector, which breaks down individual agent runs step by step.

## Use Cases

### Manager monitors all AI employee activity in real time

Every action an AI agent takes, every tool call, every file created, every message sent, appears in the activity feed the moment it happens.

### Support team tracks live agent responses to tickets

The activity feed shows every step the AI employee takes on an open ticket, so the support lead knows exactly where things stand.

### Ops team detects unexpected agent behavior immediately

Unusual actions surface in the feed in real time, letting ops catch and investigate anomalies before they become incidents.

### Founder reviews full day of AI activity in two minutes

The activity feed gives a chronological view of everything every AI agent did, so leadership stays informed without reading individual logs.

## Comparison

| Before | After |
|---|---|
| No visibility into what AI agents are doing right now. | The live activity feed shows every action as it happens. |
| Reviewing agent work requires digging through raw execution logs. | The activity feed surfaces everything in a clean, readable timeline. |
| Errors are discovered after the fact, not in real time. | The feed flags issues immediately, so teams can respond fast. |
| Teams have to query multiple sources to understand agent behavior. | One feed aggregates all AI employee activity in one place. |

## FAQ

### How far back does the activity feed go?

The activity feed retains the full history of your workspace activity, not just a rolling window. You can scroll back to day one, filter by any time range, and export activity logs for external analysis or compliance documentation.

### Does the feed update without refreshing the page?

Yes. The feed uses real-time subscriptions so new activity appears instantly without any page refresh or polling. You see activity as it happens, which is essential when monitoring autonomous agents in production.

### Can I set up alerts based on activity feed events?

Yes. You can configure notification rules that trigger on specific activity types, error conditions, or threshold breaches. Alerts can go to email, Slack, or any webhook endpoint you configure.

### Is activity data available via API?

Yes. The full activity history is accessible through the REST API, including filtering and pagination. This lets you build custom dashboards, integrate activity data into existing monitoring tools, or trigger workflows based on agent activity.

### Can I watch what my AI agent is doing in real time?

Yes, the live activity feed shows every action your AI employee takes as it happens, in a scrolling real-time timeline. No refresh needed, events stream directly into the workspace as the agent works.

> A client asked us to prove what our AI agent did on a specific task last Thursday. I pulled up the activity feed, filtered by agent and date, and had the full timeline in thirty seconds.
>
> Tunde A., Account Director · SaaS company

## Where Activity Timeline fits

Activity Timeline 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: Activity Timeline](/en/guide/monitor/activity)

## More in Monitoring

- [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.
- [Spending Limit](/en/features/observability/spend_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](/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)