# Get agent URL: https://docs.hanzo.ai/docs/openapi/agent/get-agent-by-ref > Returns one agent with its system prompt and its 20 most recent runs. `GET /v1/agent/{ref}` > [Agent →](https://docs.hanzo.ai/docs/openapi/agent) · [All API references →](https://docs.hanzo.ai/docs/openapi) · [Get started →](https://docs.hanzo.ai/docs/guides) | | | | ------------- | -------------------------------------- | | **Address** | `https://api.hanzo.ai/v1/agent/{ref}` | | **Method** | `GET` | | **Operation** | `get_agent_by_ref` | | **Auth** | `Authorization: Bearer $HANZO_API_KEY` | Returns one agent with its system prompt and its 20 most recent runs. The ref is the agent's public id or its org-unique name — a created agent is immediately gettable by whatever create handed back. ## Request 1 field. | Field | In | Type | Required | Description | | ----- | ---- | ------ | -------- | ---------------------------------------------------------------------------------------------------------------- | | `ref` | path | string | yes | Ref is the agent's public id (the agent\_… handle create and list return) or its org-unique name, from the path. | ## Response | Status | Body | Meaning | | --------- | ----------------- | ------- | | `200` | agent.agentDetail | ok | | `default` | problem-details | refused | `200` body — 38 fields. | Field | In | Type | Always | Description | | ------------------------------- | ---- | --------------------- | ------ | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | | `avatar` | body | string | — | | | `cap_micro_usd` | body | integer (int64) | — | | | `computeRef` | body | string | — | | | `consumed_micro_usd` | body | integer (int64) | — | | | `createdAt` | body | string | — | | | `description` | body | string | — | | | `emoji` | body | string | — | | | `executionMode` | body | string | — | | | `id` | body | string | — | | | `instructions` | body | string | — | Instructions is the agent's system prompt, verbatim, up to 32 KiB. | | `lineage` | body | string\[] | — | | | `max_task_micro_usd` | body | integer (int64) | — | | | `model` | body | string | — | | | `name` | body | string | — | | | `parent` | body | string | — | | | `period` | body | string | — | | | `recentRuns` | body | agent.agentRunView\[] | — | RecentRuns is the agent's 20 most recent executions, newest first. | | `recentRuns[].actor` | body | string | — | Actor is the "org/sub" identity the run was executed and billed AS. | | `recentRuns[].agent` | body | string | — | What an operator needs to answer "what ran, for whom, and what did it do" — and, through traceId, to leave this record for the waterfall of the very same run rather than a search that hopefully lands near it. | | `recentRuns[].completionTokens` | body | integer (int64) | — | CompletionTokens is the same measurement for what the model produced, on the same final completion. | | `recentRuns[].createdAt` | body | string | — | CreatedAt is when the run finished, RFC 3339 in UTC to the second — the duration above already says how long it had been going. | | `recentRuns[].durationMs` | body | integer (int64) | — | DurationMs is wall-clock milliseconds around the completion, including a failover's retries. | | `recentRuns[].error` | body | string | — | Error is why an "ok"-less run failed, as the failing call reported it. | | `recentRuns[].id` | body | string | — | ID is the run's handle, minted as "run\_" + 32 hex characters. | | `recentRuns[].input` | body | string | — | Input is the text the run was given, verbatim. | | `recentRuns[].micro_usd` | body | integer (int64) | — | MicroUSD is what the run spent, integer micro-USD. | | `recentRuns[].model` | body | string | — | Model is the model that actually SERVED this run, which is not always the one the agent is defined on — a failover records what answered. | | `recentRuns[].output` | body | string | — | Output is what the model produced. | | `recentRuns[].promptTokens` | body | integer (int64) | — | PromptTokens is what the gateway reported for the run's FINAL completion, and only that one — a tool loop's earlier rounds are the metering ledger's account, joined by this run's id. | | `recentRuns[].status` | body | string | — | Status is the run's outcome, and there are exactly two: "ok" when the model answered, "error" when it did not. | | `recentRuns[].toolCalls` | body | integer (int64) | — | ToolCalls is how many tool dispatches the run made — a count of ACTIONS, which is a different measurement from the token counts above and from the turns a build reports. | | `recentRuns[].traceId` | body | string | — | TraceID is the trace this run IS, so the record and its spans are one thing to move between: it opens the waterfall for THIS run rather than a search that lands near it. | | `runs` | body | integer (int64) | — | | | `schedule` | body | string | — | | | `serviceAccountId` | body | string | — | | | `status` | body | string | — | | | `tools` | body | string\[] | — | | | `updatedAt` | body | string | — | | Failure carries the platform error shape — see [Errors](https://docs.hanzo.ai/docs/errors). ## Examples **CLI** ```bash hanzo agent get ``` **SDK** **.ts** ```ts import { Configuration, AgentApi } from 'hanzoai'; const api = new AgentApi(new Configuration({ accessToken: process.env.HANZO_API_KEY })); const { data } = await api.getAgentByRef({ ref: 'ref' }); ``` **.py** ```python from hanzoai.cloud import ApiClient, Configuration from hanzoai.cloud.api import AgentApi client = ApiClient(Configuration(access_token=os.environ["HANZO_API_KEY"])) result = AgentApi(client).get_agent_by_ref(ref='ref') ``` **.go** ```go cfg := hanzoai.NewConfiguration() cfg.AddDefaultHeader("Authorization", "Bearer "+os.Getenv("HANZO_API_KEY")) client := hanzoai.NewAPIClient(cfg) resp, _, err := client.AgentAPI.GetAgentByRef(context.Background()).Execute() if err != nil { return err } ``` **.rs** ```rust use hanzo_client::apis::{configuration::Configuration, agent_api}; let mut cfg = Configuration::new(); cfg.bearer_access_token = std::env::var("HANZO_API_KEY").ok(); let result = agent_api::get_agent_by_ref(&cfg, Default::default()).await?; ``` **.java** ```java import ai.hanzo.cloud.ApiClient; import ai.hanzo.cloud.api.AgentApi; ApiClient client = new ApiClient(); client.setBearerToken(System.getenv("HANZO_API_KEY")); var result = new AgentApi(client).getAgentByRef(); ``` **HTTP** ```bash curl https://api.hanzo.ai/v1/agent/ \ -H "Authorization: Bearer $HANZO_API_KEY" ``` **MCP** Tool `agent`, op `get_agent_by_ref` — POST the JSON-RPC envelope to `https://api.hanzo.ai/v1/mcp`. ```bash curl -X POST https://api.hanzo.ai/v1/mcp \ -H "Authorization: Bearer $HANZO_API_KEY" \ -H "Content-Type: application/json" \ -d '{ "jsonrpc": "2.0", "id": 1, "method": "tools/call", "params": { "name": "agent", "arguments": { "op": "get_agent_by_ref", "input": { "ref": "" } } } }' ``` --- [Agent API](https://docs.hanzo.ai/docs/openapi/agent) · [All Hanzo APIs](https://docs.hanzo.ai/docs/openapi) · [Interactive reference](https://docs.hanzo.ai/docs/openapi/reference)