| Term | Definition |
|---|---|
| Advisor | A roster entry that gives a second opinion without doing the work. A roster can have at most one. See Multi-agent. |
| Agent | A reusable definition of a model, system prompt, tools, skills, MCP servers, granted apps, and default credential grants. See Agent setup. |
| Agent version | An immutable snapshot of an agent. Every update publishes a new one, and a session runs the version it started with. |
| Analytics | Organization-wide figures for usage, cost, completions, environment startup, and quality, by agent, tool, and model. See Analytics. |
| API key | A personal rma_ secret that authenticates API requests as you. Scoped to a tenant or one organization. See API keys. |
| Artifact | An output the agent produces, such as a saved file or an image, recorded in the event log. See Artifacts. |
| Automation | A saved agent version, environment, prompt, and run defaults that starts a session when a trigger fires or you click Run now. See Automations. |
| Automation run | The record of one automation start: its trigger, the frozen inputs, the opening message, and the session it created. |
| Built-in integration | An integration with one of the 164+ apps in the catalog, such as Salesforce or Zendesk. An admin connects it once and chooses its tools. See Integrations. |
| Child session | A session a parent session starts to delegate work. It shares its root session’s sandbox. Also called a subagent. |
| Console | The web interface for Managed Agents. See Build in the console. |
| Credential | One secret inside a vault: an MCP bearer token, an environment-variable secret, a webhook signing secret, or a native integration grant. See Vaults. |
| Curated memory store | A memory store you write through the API and attach to an automation’s sessions. See Memory. |
credential_refs | A list that narrows a session to specific credentials inside its granted vaults. |
| Criterion | One checkable line in a rubric. The grader gives each one pass, fail, or not_applicable. |
| Default organization | The organization every tenant has, named Default. Every member can reach it, and the console works in it. |
| Deliverable | A file the agent saves as the result of its work. Deliverables are collected at the end of every turn, before grading. See Artifacts. |
| Environment | The configuration a session’s sandbox runs with: runtime, compute, workspace disk, setup script, internet access, and idle policy. See Environments. |
| Evaluation | An evaluator agent’s immutable verdict on one finished session, overall and per criterion, with evidence. See Evaluations. |
| Evaluator | An agent with the evaluation toolset and a keyed rubric, used to judge sessions. |
| Event | One recorded step in a session, such as a message, tool call, or grading pass. See Events. |
| Event source | An endpoint that receives Slack, GitHub, or custom webhook events and verifies them, for automation triggers. See Receive events. |
| Execution state | execution_state: what the agent loop is doing now, such as running or idle. See Event types and states. |
| File | A file in your organization’s library: an upload you can attach to sessions, or a deliverable a session saved. See Files. |
| Grader | The separate model pass that scores the agent’s work against an outcome’s rubric. |
| Grading pass | One run of the grader. Its result is satisfied, needs_revision, or a terminal failure. |
| Hard stop | Cancelling a session: its work stops and its sandbox is torn down. See Session operations. |
| Idempotency key | A value sent in Idempotency-Key so a retried create can’t happen twice. See API conventions. |
| Integration | An organization’s connection to an outside app or service, which you grant to agents. See Integrations. |
| Interrupt | Stopping the current turn without ending the session. The session stays resumable. |
| Learned memory | The memory store Recursion maintains for each agent from its finished sessions, attached to every session of that agent. See Memory. |
| Learning run | One update of an agent’s learned memory from its session reports. It runs as an ordinary session you can read. |
| MCP server | A server that offers tools over the Model Context Protocol. Agents can use MCP servers you configure. See MCP servers. |
| Model cost | What a session’s model calls cost, for one session or a whole tree. See Usage and cost. |
| Memory | A short text document at a path in a memory store, which agents browse, search, and read when it helps. See Memory. |
| Native integration | An integration connected by signing in to the service directly, such as GitHub, Slack, or Jira, granted per agent or through a vault. See Native integrations. |
| Network policy | The rules for what a sandbox can reach on the internet. New environments have no internet access unless you allow it. See Environment reference. |
| Organization | A separate space in a tenant. Every resource belongs to exactly one organization. See Organizations and roles. |
| Outcome | A definition of done for a session: an objective plus a rubric. See Outcomes. |
| Primary owner | The person a tenant was created for. There’s exactly one, and they can’t be removed or demoted. |
| Referenced session | An earlier session a new session may read. See Referenced sessions. |
| Role | What a member may do. Each member has a tenant role, which gives them roles in organizations. See Organizations and roles. |
| Root session | The session you started, at the top of a session tree. |
| Roster | The list of agents a coordinating agent may delegate to. Up to 20 entries. |
| Rubric | Markdown criteria the grader checks. See Outcomes. |
| Sandbox | The isolated workspace where a session tree runs commands and tools. |
| Session | One run of an agent version in an environment. See Sessions. |
| Session analyst | A conversation that answers your questions about a session. Open it with Ask in the console. |
| Session tree | A root session and all the child sessions under it. They share one sandbox, and cost rolls up to the root. |
| Setup run | A test of an environment’s setup script on real compute. Sessions can’t use a script until a run passes. See Environments. |
| Setup script | A shell script that prepares an environment’s software before the agent starts. |
| Skill | A reusable procedure, in the Agent Skills format, that an agent loads when it needs it. See Skills. |
| Skill group | A named set of skills you attach together. |
| Stop reason | stop_reason: why the agent loop isn’t running, such as end_turn or outcome_satisfied. See Event types and states. |
| Session resource | A file attached to a session, read-only in its sandbox under /workspace/.managed-agents/files. See Files. |
| Tag | A label on an agent, used to filter agents and sessions. |
| Task board | A team’s shared list of tasks, owners, notes, and decisions. See Teams. |
| Team | Copies of an agent that claim tasks from a shared board and work in parallel. See Teams. |
| Tenant | The top level of an account. It holds members and organizations. |
| Thread | One agent’s line of work in a multi-agent session. |
| Trigger | What starts an automation run: a schedule, a Slack message, a GitHub event, or a custom webhook delivery. |
| Tool | An action the agent can take, such as running a command, searching the web, or calling an MCP server. See Tools. |
| Tool allow-list | The tools every agent granted a built-in integration may call in that app. Set on the Integrations page. See Choose which tools agents may use. |
| Turn | One stretch of agent work, from a message until the agent stops. Deliverables are collected and grading runs at the end of each turn. |
| Vault | A named group of credentials that agents and sessions receive by grant. See Vaults. |
| Workspace | The agent’s working directory in the sandbox, /workspace. |
API reference
Glossary
Short definitions of every term used in the Managed Agents docs, with a link to where each is explained.
Terms are in alphabetical order. Field names appear in code format.