Execute an inline workflow

/v1/workflows/execute

Headers: every response carries x-request-id (quote it in support requests). Send x-trace-id (optional, a UUID) to correlate this call across planes; reusing an id that already ran answers 409 duplicate_execution_id. Pick the body format with format or Accept (application/json, text/yaml, text/markdown, text/plain).

Authorization: send Authorization: Bearer $PLUNGE_API_KEY; X-API-Key: <ozk_ key> is accepted as an alternative.

Authorizations

Authorizationstringheaderrequired

Bearer token: Authorization: Bearer ozk_…. ozk_ platform API key (Authorization: Bearer ozk_…)

Body

application/json
text/yaml

One of three shapes: a bare agent call (agent + the agent's own fields), a workflow object or YAML string, or top-level name/tasks (auto-nested). format, input, inputs, stream, sync, dry_run and metadata are wire keys and never reach the agent.

agentstring

bare agent call: the agent id; every other field is passed to the agent (guide 10.2)

workflowany

CNL workflow object, or a YAML string

namestring

with tasks: the workflow name

tasksany[]

with name: the task list, auto-nested under workflow

inputstring

inputsobject

formatenum<string>

Response format override (precedence: this field → Accept header → mirror of the request Content-Type). Default json. yaml = the envelope with Markdown as block scalars; markdown = the same result the MCP plane renders; text = the bare result content. An unknown value → 400 invalid_format.

Available options: json, yaml, markdown, text

Response

Engine acknowledgement Response format negotiates via the format field, an Accept header (application/json, text/yaml, text/markdown, text/plain), or the request Content-Type mirror; default JSON.

application/json
text/yaml
text/markdown
text/plain

Response headers

x-request-idstringfrom code

Server-minted request id.

X-Execution-Idstringfrom code

The execution this call opened.

successboolean

workflow_idstring

final_task_idstring

request_idstring

contentstring

the final task's stored content, present once the sync run has stored it

missing_workflow (none of workflow / agent / tasks) / ambiguous_body (agent next to workflow or tasks) / reserved_field (a field named like an engine task key) / invalid_json / invalid_yaml / invalid_body (unreadable body) / invalid_format — format must be one of json, yaml, markdown, text

application/json

errorobjectrequired

Show child attributes

codestringrequired

messagestringrequired

Missing, invalid, expired or revoked ozk_ key.

Error code: unauthorizedfrom code

agent_not_active — a named agent card is not status:active (refused pre-dispatch)

application/json

errorobjectrequired

Show child attributes

codestringrequired

messagestringrequired

unknown_agent — a named agent id does not exist in the registry (refused pre-dispatch)

application/json

errorobjectrequired

Show child attributes

codestringrequired

messagestringrequired

duplicate_execution_id — x-trace-id already used by an earlier run — send a fresh UUID

application/json

errorobjectrequired

Show child attributes

codestringrequired

messagestringrequired

payload_too_large — body over 1 MiB (MAX_REQUEST_SIZE)

application/json

errorobjectrequired

Show child attributes

codestringrequired

messagestringrequired

rate_limited — Retry-After header

application/json

errorobjectrequired

Show child attributes

codestringrequired

messagestringrequired

engine_error

application/json

errorobjectrequired

Show child attributes

codestringrequired

messagestringrequired

import os import requests workflow = { 'name': 'doc-demo', 'tasks': [{'type': 'task', 'id': 't1', 'agent': 'llm-agent', 'prompt': 'Reply with only the word: pong'}], } res = requests.post( 'https://api.plungeai.com/v1/workflows/execute', headers={'Authorization': f"Bearer {os.environ['PLUNGE_API_KEY']}"}, json={'workflow': workflow, 'input': 'go'}, ) if res.status_code != 200: raise SystemExit(res.headers.get('X-Error-Code')) run = res.json() print(run['workflow_id'], run['final_task_id'])

const workflow = { name: 'doc-demo', tasks: [{ type: 'task', id: 't1', agent: 'llm-agent', prompt: 'Reply with only the word: pong' }], } const res = await fetch('https://api.plungeai.com/v1/workflows/execute', { method: 'POST', headers: { Authorization: `Bearer ${process.env.PLUNGE_API_KEY}`, 'Content-Type': 'application/json' }, body: JSON.stringify({ workflow, input: 'go' }), }) if (!res.ok) throw new Error(res.headers.get('X-Error-Code') ?? String(res.status)) const run = await res.json() console.log(run.workflow_id, run.final_task_id)

import java.net.URI; import java.net.http.HttpClient; import java.net.http.HttpRequest; import java.net.http.HttpResponse; public class Main { public static void main(String[] args) throws Exception { String json = "{\"workflow\":{\"name\":\"doc-demo\",\"tasks\":[{\"type\":\"task\",\"id\":\"t1\",\"agent\":\"llm-agent\",\"prompt\":\"Reply with only the word: pong\"}]},\"input\":\"go\"}"; HttpRequest req = HttpRequest.newBuilder(URI.create("https://api.plungeai.com/v1/workflows/execute")) .header("Authorization", "Bearer " + System.getenv("PLUNGE_API_KEY")) .header("Content-Type", "application/json") .POST(HttpRequest.BodyPublishers.ofString(json)) .build(); HttpResponse<String> res = HttpClient.newHttpClient().send(req, HttpResponse.BodyHandlers.ofString()); System.out.println(res.statusCode() + " " + res.body()); } }

curl -s https://api.plungeai.com/v1/workflows/execute \ -H "Authorization: Bearer $PLUNGE_API_KEY" \ -H 'Content-Type: application/json' \ -d '{"workflow":{"name":"doc-demo","tasks":[{"type":"task","id":"t1","agent":"llm-agent","prompt":"Reply with only the word: pong"}]},"input":"go"}'

cat > workflow.yaml <<'YAML' workflow: name: doc-demo-yaml tasks: - type: task id: t1 agent: llm-agent prompt: "Reply with only the word: pong" YAML curl -s https://api.plungeai.com/v1/workflows/execute \ -H "Authorization: Bearer $PLUNGE_API_KEY" \ -H 'Content-Type: text/yaml' \ --data-binary @workflow.yaml

Execute an inline workflow

Authorizations

Body

Response

Response headers

Planned: TI-33

Planned: TI-34