TOBY AI¶

TOBY AI is the product family for the platform's AI capabilities. It includes TOBY AI Copilot for immediate, user-driven assistance and TOBY Agent Teams for persistent team workflows. The two products use different operating models and are suited to different kinds of work.

Products¶

TOBY AI Copilot¶

Copilot is provided as part of the workspace and requires no additional configuration. Open it and describe a goal directly, or let it use the current page context together with the data and capabilities available under your permissions.

Use Copilot when you need to:

• Understand a log, trace, alert, RUM object, or dashboard quickly;
• Write or review DQL and PromQL, or filter viewer data with natural language;
• Create a dashboard draft or Pipeline parsing rule;
• Turn an analysis into a note or ask a question about product documentation.

Copilot is designed for immediate tasks initiated by the user, helping them use the workspace's data query, analysis, and content creation capabilities efficiently and accurately.

TOBY Agent Teams¶

Agent Teams is used to build and run Agents with clear responsibilities, allowing them to combine workspace data, external capabilities, and runtime environments in day-to-day team operations. Each Agent can have its own responsibilities, behavioral boundaries, runtime environment, and available tools.

Agent Teams is suited to complex work that requires persistent context, multiple execution steps, and real operational actions, for example:

• Combining problem analysis, plan development, operational execution, and result verification into a continuous task while preserving context across multiple steps and tools;
• Analyzing observability data in the workspace and, within the granted permissions, using code repositories, clusters, and engineering tools to apply code fixes, scale resources, or adjust configurations for SRE, development, and testing work;
• Connecting business systems, external services, or other AI workflows through task intake, MCP services, and related integrations so tasks from different sources can enter a unified execution flow;
• Configuring Agents with clear responsibilities for different teams or business scenarios, running them on schedules, workspace events, or external requests, and delivering results to configured Channel conversations.

An Agent's actual capabilities depend on its enabled configuration, authorization scope, and deployment environment. After a run starts, its progress and result are available from task sessions and run records.

Quick Links¶

For instructions on opening Copilot and managing conversation history, see TOBY AI Copilot.

Plans and Credits¶

Copilot and Agent Teams share the workspace's AI service plan and credit balance. For plan tiers, credit validity, and deduction order, see Plans and Credits.