Author eval coverage for an agent in this AgentOS — map what the agent promises, mine real sessions and eval history from Postgres for scenarios, propose capabilities worth testing, then write, run, and audit Case entries in evals/cases.py. Use when the user wants evals created, coverage added, or an agent's behavior pinned down as tests. For failing suites or exploratory simulation-driven hardening, use eval-and-improve instead.
中文简介正在准备中。当前显示原文说明。
Deploy this AgentOS using its own provider instructions, configure JWT verification, and verify the public service. Use for first deployment, redeployment, or production configuration changes.
中文简介正在准备中。当前显示原文说明。
Evaluate and improve an existing AgentOS agent or team. Repair failing eval cases, or explore behavior by generating simulated user scenarios from instructions and sanitized usage, running probes, inspecting evidence and iterating within a bounded budget. Use for failing evals, autonomous hardening or simulation-driven improvement. Use create-evals for coverage authoring alone and extend-agent for a requested new capability.
中文简介正在准备中。当前显示原文说明。
User-driven loop to change an existing agent in this AgentOS — add a tool/MCP server/toolkit, add a capability (knowledge base, learning/memory, sub-agent, scheduled task), grow the safe Studio registry so components built at runtime gain a new capability, refine its instructions, or fix a specific known bug, verifying each change against the selected development runtime. Use whenever the user names a concrete change to an agent, or wants a new building block available to the platform. For autonomous hardening with no specific change in mind, use eval-and-improve.
中文简介正在准备中。当前显示原文说明。