How to View Agent Insightspublic
Validated on 29 Apr 2025 • Last edited on 1 May 2025
The DigitalOcean GenAI Platform lets you work with popular foundation models and build GPU-powered AI agents with fully-managed deployment, or send direct requests using serverless inference. Create agents that incorporate guardrails, functions, agent routing, and retrieval-augmented generation (RAG) pipelines with knowledge bases.
The agent Insights feature provides an overview of your agent’s token usage and performance. This can help you understand how your agent is performing and then adjust your agent’s configuration to improve its performance.
To view insights for an agent from the DigitalOcean Control Panel, click GenAI Platform in the left menu, then click the Agents tab and select the agent you want to view the insights for.
From the agent’s Overview page, scroll down to the Insights section.
The Insights section allows you to view the following information:
- Tokens In: The number of input tokens sent by users to generate responses over the selected time period.
- Tokens Out: The number of output tokens generated by the agent over the selected time period.
- All tokens: The total number of tokens used by the agent over the selected time period.
- Requests in: The number of user requests received by the agent over the selected time period.
The Token Metrics section currently displays the following the average time it takes for the agent to generate the first token of a response, in seconds.