Obsy AI¶

Obsy AI is the umbrella term for the platform's AI capabilities, including Obsy Copilot, which provides immediate personal assistance, and Obsy Agent Teams, which supports continuous team workflows. These two products operate in different ways and are suited to solving different types of problems.

Product Components¶

Obsy Copilot¶

Obsy Copilot comes with the workspace and requires no additional configuration. Once opened, you can directly describe your goal; on supported pages, you can also let it work with the current object, time range, and filter conditions within your permission scope to access available data and capabilities to complete tasks.

It is suitable for the following scenarios:

• Quickly understanding current logs, traces, alerts, RUM data, dashboards, or infrastructure objects;
• Writing or checking DQL, PromQL, or filtering explorer data via natural language;
• Creating draft dashboards or Pipeline parsing rules;
• Documenting analysis processes as notes or Runbooks, or querying product documentation.

Obsy Copilot is designed for user-initiated, on-demand tasks, helping users query data, analyze, and create content within the workspace more efficiently and accurately.

Obsy Agent Teams¶

Obsy Agent Teams is used to build and run Agents with clearly defined responsibilities, enabling them to combine workspace data, external capabilities, and runtime environments to actively participate in team workflows. Each Agent can have its own responsibilities, behavior boundaries, runtime environment, and available tools.

Obsy Agent Teams is well-suited for complex tasks that require continuous context, multi-step collaboration, and actual operations, for example:

• Organizing problem analysis, solution formulation, operation execution, and result validation into a continuous task chain, maintaining context across multiple rounds of processing and cross-tool collaboration;
• Analyzing based on observable data within the workspace and, within authorized scope, invoking code repositories, clusters, and engineering tools to directly execute code fixes, scaling, configuration adjustments, and other SRE, development, or testing work;
• Connecting business systems, external services, or other AI workflows via task integration, MCP services, etc., to unify tasks from different sources into a single execution pipeline;
• Configuring Agents with clear responsibilities for different teams or business scenarios, executing tasks continuously based on schedules, workspace events, or external requests, and sending results to configured Channel sessions.

The actual capabilities of an Agent depend on the enabled configurations, authorization scope, and deployment environment. After creation, you can view the execution process and results from task sessions and run records.

Quick Start¶

For information on how to open Obsy Copilot and manage its history, see Obsy Copilot.

Plans & Credits¶

Obsy Copilot and Obsy Agent Teams share the workspace's AI service plan and credit account. For details on plan versions, credit validity periods, and deduction order, see Plans & Credits.