> ## Documentation Index > Fetch the complete documentation index at: https://docs.atako.ai/llms.txt > Use this file to discover all available pages before exploring further. # Activity > The real-time record of everything your agents do — and why it's central to trusting them. An autonomous agent that acts on your tools without you watching every step only works if you can trust what it did. The activity timeline is how: a real-time, per-agent record of every turn, tool call, and decision, always available and never something you have to ask the agent to summarize for you. ## The timeline On the **Floor**, click an agent. The **Activity** section of the agent panel is open by default. Events stream in live as the agent works — nothing to refresh. ### Anatomy of an event Each step reads like a log of a colleague's work: visiting a page, using the browser, reading or writing a file, updating memory, running code, calling an integration, managing a scheduled task, starting a sub-agent, or replying to you. Each step carries its status and how long it took, and a turn shows its number of steps and total duration. When the agent works from a plan, the timeline also shows **Agent's plan** with its progress. ### Sub-agents Delegated work shows up inline in the timeline, as start and finish events for each sub-agent. ## Company-wide view (admins) Admins get a broader lens across every agent, from the districts of the **Dashboard** storey. Every district reports on the period set in the period band — the last 24 hours by default, or live. See [The Floor](/guides/the-floor#dashboard). | District | What it shows | | - | - | | **Agent activity** | When each agent worked, how intensely, how many events failed, and what woke it up. | | **Integration log** | Every integration call, one by one — searchable, filterable by agent, integration, and status (**Succeeded**, **Denied**, **Failed**), with CSV **Export**. | | **Integrations usage** | Call volume aggregated per integration, so you can see at a glance which tools your agents actually rely on. | **Agent activity** groups events by origin, which answers "why did the agent do this?": | Origin | Meaning | | - | - | | **Human message** | Someone wrote to the agent. | | **Agent-to-agent message** | Another agent handed work over. | | **Webhook** | A webhook event arrived. | | **E-mail** | An email arrived. | | **Scheduled task** | A scheduled run fired. | | **Sub-agent** | A sub-agent did the work. | | **System event** | The platform itself. | ## Audit log Agents' integration calls are logged in the **Integration log**. Account and company events — who did what, when, from which IP address — are recorded separately in the **Audit log**, an admin-only section of **Settings**. See [Audit log](/guides/audit-log). ## Why this matters Every action an agent takes through a granted integration is logged — which agent, which action, when, and with what outcome. Because agents can act unattended across chat, email, webhooks, cron, and other agents, the activity timeline and integration log are what let you extend real autonomy to an agent without losing visibility into what it's doing. ## Related The agent panel where the Activity section lives. How grants control what an agent can call. Sub-agents and how delegation works. Account and company events, admin-only. This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.