Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.poolside.ai/llms.txt

Use this file to discover all available pages before exploring further.

​
Overview

Poolside lets you investigate, debug, and audit agent behavior from the Poolside Console by reviewing usage metrics, session history, and detailed trajectories. You typically review this information in sequence: from the agents list to an agent, then to a session, and finally to its trajectory. This progression lets you start with broad signals and focus in on the exact run details you need. Using this information, you can:
  • Investigate why an agent produced a specific result
  • Identify runs with errors
  • Review which tools the agent used during the run
  • Identify when and who approved tool usage
  • Trace behavior across sessions with multiple steps or turns
  • Debug and troubleshoot individual executions
For detailed instructions on opening and reading trajectories, see Trajectories.

​
Before you begin

If you belong to a team with the tenant-admin role, you can use the full auditing workflow on this page, including organization-wide usage views across all agents. If you have the View Agent Sessions or Manage Agents permission, you can review session history and trajectories for the agents those permissions cover. You can also open trajectories for sessions you started yourself, even without these permissions, by running /trajectory in the IDE. For more information, see Trajectories. To review configuration changes for an agent, including who changed what and when, see View configuration history.

​
View agent usage across the organization

Use the Agents page to review high-level usage across agents and identify activity patterns across your organization. This workflow is available to tenant admins.

​
View all agents and usage

  1. In the Poolside Console, navigate to Agents > https://mintcdn.com/poolside/Tz6xG1rOCu6JtFws/images/icons/agents-icon.svg?fit=max&auto=format&n=Tz6xG1rOCu6JtFws&q=85&s=62fd5988e22e9439aed3726927f1fcaf Agents.
  2. View the list of configured agents.
  3. Review per-agent usage metrics, including sessions, total tokens, and steps.
  4. Compare usage across agents to understand activity levels and patterns.
  5. Select an agent to view its details and associated sessions.

​
View inference metrics

Enable Inference metrics to overlay time-to-first-token latency data on the usage chart. This is available on the Agents page and on individual agent pages. These metrics can help identify early signs of GPU inference saturation. When inference nodes are under heavy load, queuing delays and resource contention can delay the start of generation. This can increase time to first token even when overall throughput appears stable. Use these metrics to determine whether agent usage patterns warrant closer monitoring of your inference deployment.
  1. In the Poolside Console, navigate to Agents > https://mintcdn.com/poolside/Tz6xG1rOCu6JtFws/images/icons/agents-icon.svg?fit=max&auto=format&n=Tz6xG1rOCu6JtFws&q=85&s=62fd5988e22e9439aed3726927f1fcaf Agents.
  2. Toggle Inference metrics on.
  3. Review the latency lines overlaid on the usage chart:
    • Avg TTFT: Average time to first token
    • P50 TTFT: Median latency
    • P95 TTFT: 95th percentile latency
  4. Hover over the chart to see exact latency values.

​
Export usage data for all agents

Export usage metrics for all agents to a CSV file for reporting or analysis.
  1. In the Poolside Console, navigate to Agents > https://mintcdn.com/poolside/Tz6xG1rOCu6JtFws/images/icons/agents-icon.svg?fit=max&auto=format&n=Tz6xG1rOCu6JtFws&q=85&s=62fd5988e22e9439aed3726927f1fcaf Agents.
  2. Select the date range for the usage data you want to export.
  3. In the Metrics table, click Export Data to download a CSV file.
The export includes per-agent session counts, token usage, step counts, and TTFT latency metrics for the selected date range.

​
Review usage for a specific agent

If you can access an agent’s session history in the Poolside Console, use the agent detail page to analyze usage patterns and inspect sessions for that agent.

​
Review agent sessions and usage

  1. In the Poolside Console, open the agent you want to inspect.
  2. Review the agent usage chart and metrics.
  3. Review the list of sessions associated with the agent.
  4. Select a session to open it in the Trajectory Viewer.

​
Export usage data for an agent

Export usage metrics for a specific agent to a CSV file.
  1. In the Poolside Console, open the agent you want to inspect.
  2. Select the date range for the usage data you want to export.
  3. In the Metrics table, click Export Data to download a CSV file.
The export includes summary session counts, token usage, step counts, and inference latency data for the selected agent and date range.

​
Open a session in the trajectory viewer

After you identify a session to inspect, open it in the Trajectory Viewer.
  1. In the Poolside Console, open the agent you want to inspect.
  2. Select a session to open it in the Trajectory Viewer.
  3. Review the session details, steps, events, and time distribution.
  4. Optional: Click Download to export the trajectory as a JSON file.
Trajectory exports can contain sensitive information, including file contents, environment variables, API keys, and personal or proprietary data.
For details on reviewing session fields, navigating multi-turn sessions, filtering steps, inspecting events, and exporting trajectory data, see Trajectories.