Skip to main content
Since agents can perform tasks autonomously, it’s useful to be able to monitor what they’re doing. Click “Diary & Approvals” in the sidebar.

​
Agent diary

Each agent maintains a diary — a high-level record of activities and internal reasoning.
Agent Diary
The agent writes a diary entry when:
  • It has processed a trigger (email, scheduled task, webhook, etc).
  • It has done something significant in the chat.
In the chat, the agent decides when to write a diary entry based on the conversation content. This differs from handling triggers and events, where the agent will always write a diary entry. Writing a diary entry after every chat message would be too verbose and not useful.
The agent can also read its own diary entries. However, it normally won’t do so unless directly asked, or if it decides that it needs something specific from the diary. The diary is useful if you want to find out WHY the agent did something. For example, if the agent routed an invoice to the wrong team, the diary can help you understand why, so you can tweak the instructions.

​
Activity log

The activity log is a live-updated technical log of all triggers that the agent has processed. Triggers could be for example an email, a scheduled task, or a webhook.
Activity Log
Chat messages are not included in the activity log, since the purpose of the activity log is to show what is going on outside of the chat, when the agent does things autonomously.
When an agent processes a trigger, it goes through a sequence of steps, each shown in detail in the activity log.
  • Prefilter Decide if this trigger is relevant to the agent. For example “Do I care about this slack message, is it addressed to me?”. This is an early-out mechanism to save time and credits.
  • Interpretation The agent looks at the raw trigger data and interprets what it actually means. For example “Jim has emailed me 3 invoices to process”.
  • Plan The agent creates a plan for what to do. For example “I will review each invoice individually, validate it, potentially flag it on slack, and then forward it by email to the correct team.”.
  • Security Assessment A separate security agent assesses the plan, compares with the agent’s instructions, and decides whether it is safe to carry out the plan. For example if the agent plans to respond to an email, the security agent will check if the agent’s instructions mention that it should respond to emails. See the Security Agent page for more details.
  • Execution The agent executes the plan, and the activity log shows the specific tool calls and end result.
In addition to the AI-powered security assessment, the platform will also enforce guardrails such as email whitelists and tool call approval requirements.

​
Example

Freddy the invoice router received an email asking about invoice statistics. Let’s walk through what the activity log shows for this trigger.
To see Freddy live in action, check out the demo video.

​
The trigger

Email trigger showing Henrik asking Freddy how many invoices have been processed and what the total amount is
The trigger shows the incoming email that woke the agent. Henrik is asking for a quick summary of invoice processing statistics.

​
Pre-filter

Pre-filter step showing Proceed: Yes, with reason that pre-filter is not applicable for this event type
The pre-filter step decides whether this trigger is relevant. For direct emails to the agent, the pre-filter typically passes immediately—the agent should process emails addressed to it.

​
Plan

Plan step showing the agent's interpretation of the request and a 4-step action plan to query the database, count invoices, calculate totals, and send a reply
The plan step is where the agent shows its thinking. The Interpretation section confirms what the agent understood: Henrik wants invoice count and total amount, with a brief answer. The Action plan lists the specific steps: query the database, count invoices, calculate totals (considering currency conversions), and send a brief reply.

​
Security assessment

Security step showing Safe: Yes, with reasoning that the plan only reads data and responds to an authorized email address
A separate security agent reviews the plan before execution. Here it confirms the plan is safe: Henrik is an authorized contact, the agent is only reading data (not modifying anything), and providing aggregate statistics is within the agent’s normal scope.

​
Execution

Execution step showing successful completion with 4 invoices found: 3 legitimate totaling €33,000 and 1 rejected fraud attempt for €12,000
The execution step shows what actually happened. The agent queried the Invoice Database, calculated the statistics (distinguishing between legitimate invoices and rejected fraud attempts), and sent the reply. The Tools section shows exactly which tool calls were made and when.

​
Diary entry

Diary entry dated 2026-01-06 summarizing that Henrik emailed asking for invoice statistics, and the agent replied with the numbers
After completing the task, the agent writes a diary entry—a human-readable summary of what happened. This is useful for quickly scanning the agent’s recent activities without diving into the technical details of each trigger.

​
Additional monitoring tools

The diary and activity log are built-in tools provided by the platform. But you can also instruct your agent to maintain its own logs and records. Using agent documents:
  • “Maintain a message log document for each person you’ve been in touch with”
  • “After sending your weekly news update, also save it in the ‘News updates’ folder using the naming format <date> - <main headline>”
Using external integrations:
  • “After every processed invoice, add a line to the ‘Processed Invoices’ Google spreadsheet”
  • “Log all customer support interactions to the shared Notion database”
This gives you flexibility to create monitoring that fits your specific workflow—whether that’s a simple text log, a structured spreadsheet, or integration with your existing tools.

​
FAQ

Not directly. Each agent’s diary is private to that agent. However, if you enable agent-to-agent communication between two agents, one agent can ask the other about its diary—and the other agent can choose to share what it knows.
No. The agent can read its own diary, but the activity log is only visible to you in the UI.