> ## Documentation Index
> Fetch the complete documentation index at: https://docs.praxis-ai.com/llms.txt
> Use this file to discover all available pages before exploring further.
# Create a workflow (owner and twin come from the session, never the body)
## OpenAPI
````yaml /mdx/api-reference/runtime/runtime-api.json post /api/user/agents/v2/workflows
openapi: 3.0.0
info:
title: Pria Runtime API
version: 2.0.193
description: >-
Pria API Documentation Praxis's developer platform is a core part of our
mission to empower organizations to grow better. Our APIs are designed to
enable teams of any shape or size to build robust integrations that help
them customize and get the most value out of Pria. All Pria APIs are built
using REST conventions and designed to have a predictable URL structure.
They use many standard HTTP features, including methods (POST,
GET, PUT, DELETE) and error response codes.
All API calls are
made under https://hiimpria.ai/api and all responses return standard JSON.
In these docs, you'll find lists of all available endpoints for a given API,
along with interactive code blocks for building requests. For walkthroughs
of basic usage for these APIs, check out the API guides.
servers:
- url: https://pria.praxislxp.com
description: Pria API Server
security: []
tags:
- name: Authentication
description: User authentication, registration, and password management (/api/auth)
- name: OAuth
description: OAuth authentication providers - Google, GitHub, SSO (/api/auth/oauth)
- name: User
description: User profile management and account operations (/api/user)
- name: User Institutions
description: User institution memberships and switching (/api/user/institution)
- name: User Tools
description: Available tools for authenticated users (/api/user/tools)
- name: Institutions
description: Institution settings and configuration (/api/user/institution)
- name: Conversation
description: AI conversation and Q&A endpoints (/api/ai)
- name: Realtime
description: Real-time voice AI and WebRTC sessions (/api/ai/rt)
- name: Assistant
description: AI assistant configuration and management (/api/user/assistant)
- name: History
description: Conversation history and favorites (/api/user/history)
- name: RAG
description: >-
Document upload, embedding, and retrieval-augmented generation
(/api/user/files, /api/user/rag)
- name: Setting
description: Instance variables and settings management (/api/user/setting)
- name: Branding
description: Digital twin branding and customization (/api/agent/branding)
- name: Agent
description: Agent engagement and session management (/api/agent)
- name: SDK Launch
description: >-
SDK launch token signing and verification for secure iframe embedding
(/api/auth/sdk-sign, /api/auth/sdk-verify)
- name: Testing
description: Health checks, diagnostics, and test endpoints (/api/test)
- name: Admin Accounts
description: Account management for super admins (/api/admin/account)
- name: Admin Institutions
description: Institution management for admins (/api/admin/institution)
- name: Admin Users
description: User management for admins (/api/admin/user)
- name: Admin Entitlements
description: >-
User-institution relationships and permissions
(/api/admin/userInstitution)
- name: Admin Sessions
description: Session management for admins (/api/admin/session)
- name: Admin Histories
description: Conversation history management and analytics (/api/admin/history)
- name: Admin Assistants
description: AI assistant management for admins (/api/admin/assistant)
- name: Admin Questions
description: Institution question and prompt management (/api/admin/question)
- name: Admin Tools
description: Tool configuration management (/api/admin/tool)
- name: Admin AI Models
description: AI model configuration (/api/admin/aimodel)
- name: Admin MCP Servers
description: Model Context Protocol server management (/api/admin/mcpserver)
- name: Admin Feedbacks
description: User feedback management (/api/admin/feedback)
- name: Admin Uploads
description: Upload management (/api/admin/upload)
- name: Admin Charts
description: Analytics and visualization chart management (/api/admin/chart)
- name: Audio Notes
description: Capture and ingest spoken notes into the personal vault
- name: Memory
description: User-facing memory parameters (personal + shared instance memory).
- name: My Data
description: >-
GDPR controls — personal-scope counts, async ZIP-by-email export, and
scoped soft-delete. Every endpoint pins `user = req.user._id` AND
`institution: null`; institution-scoped data is governed by the
institution's own retention policy and never reached from here.
- name: Questions
description: >-
User-facing read of the onboarding question bank used by the "create a
digital twin" wizard.
- name: Transcription
description: >-
One-shot speech-to-text for in-place dictation. Audio blob in, transcript
out — no Upload / History / RAG embeddings are persisted. Use
`/audio-notes` for anything durable.
paths:
/api/user/agents/v2/workflows:
post:
tags:
- Agents
summary: Create a workflow (owner and twin come from the session, never the body)
requestBody:
required: true
content:
application/json:
schema:
allOf:
- $ref: '#/components/schemas/AgentsV2WorkflowInput'
- required:
- name
- instruction
responses:
'201':
description: >-
Created. `nextRunAt` is computed in the schedule's timezone (null
when manual or disabled).
content:
application/json:
schema:
type: object
properties:
success:
type: boolean
workflow:
$ref: '#/components/schemas/AgentsV2Workflow'
'400':
description: >-
INVALID_NAME, INVALID_INSTRUCTION, INVALID_ENABLED,
MODEL_NOT_AVAILABLE, INVALID_REASONING, or a schedule code
(INVALID_SCHEDULE_KIND, INVALID_TIMEZONE, INVALID_TIME,
INVALID_DATE, INVALID_DAY_OF_WEEK, INVALID_DAY_OF_MONTH,
INVALID_INTERVAL, ONCE_IN_PAST).
'403':
description: No agent access on the current twin, or a cross-site request.
'404':
description: User not found, or no current twin.
'409':
description: >-
NAME_TAKEN — the caller already has a workflow with that name
(case-insensitive) on this twin.
security:
- apiKeyAuth: []
components:
schemas:
AgentsV2WorkflowInput:
type: object
properties:
name:
type: string
maxLength: 120
instruction:
type: string
maxLength: 32000
enabled:
type: boolean
model:
type: string
maxLength: 120
description: >-
'' (Default) or an id in the caller's current GET /workflow-models
menu; anything else is 400 MODEL_NOT_AVAILABLE.
reasoning:
type: string
enum:
- ''
- 'off'
- low
- medium
- high
- xhigh
schedule:
$ref: '#/components/schemas/AgentsV2WorkflowSchedule'
AgentsV2Workflow:
type: object
description: >
An agentsv2 workflow — its own collection, nothing shared with the v1
workflows under /api/user/agents/workflows. A run starts a new session
in the owner's daemon for this twin with the instruction as its first
prompt, and ends when streaming ends.
properties:
id:
type: string
name:
type: string
maxLength: 120
instruction:
type: string
maxLength: 32000
enabled:
type: boolean
description: Off = the schedule does not fire (Run now still works).
schedule:
$ref: '#/components/schemas/AgentsV2WorkflowSchedule'
nextRunAt:
type: string
format: date-time
nullable: true
lastRunAt:
type: string
format: date-time
nullable: true
lastRunStatus:
type: string
description: The latest run's status ('' before the first run).
running:
type: boolean
description: A run of this workflow is in progress (from the run records).
waitingReason:
type: string
description: Why a due run is waiting to retry (e.g. VM_NOT_READY), else ''.
model:
type: string
maxLength: 120
example: openai-codex/gpt-5.6-sol
description: >-
The model runs use: an id from GET /workflow-models, or '' for
Default (the daemon's model). At run time an id no longer in the
menu runs on Default and the run records modelFallback.
reasoning:
type: string
enum:
- ''
- 'off'
- low
- medium
- high
- xhigh
description: >-
The reasoning level runs use, or '' for Default (the daemon's
level). A level the model doesn't support is clamped by the daemon.
createdAt:
type: string
format: date-time
updatedAt:
type: string
format: date-time
AgentsV2WorkflowSchedule:
type: object
description: >
When a workflow runs, in its own IANA timezone (wall-clock: a daily
09:00 stays 09:00 across daylight saving). Only the fields of its kind
are read; unknown fields are dropped. A time that does not exist on a
spring-forward day fires at the first valid minute after it; a repeated
time on a fall-back day fires once, at the earlier instant.
required:
- kind
- timezone
properties:
kind:
type: string
enum:
- none
- once
- daily
- weekly
- monthly
- interval
description: none = manual only (Run now).
timezone:
type: string
example: America/New_York
description: IANA zone, up to 64 characters.
date:
type: string
example: '2026-10-01'
description: 'once: YYYY-MM-DD in the timezone; must be in the future.'
time:
type: string
example: '09:00'
description: 'once, daily, weekly, monthly: HH:MM (24h) in the timezone.'
dayOfWeek:
type: integer
minimum: 0
maximum: 6
description: 'weekly: 0 = Sunday.'
dayOfMonth:
type: integer
minimum: 1
maximum: 31
description: 'monthly: clamped to the last day of short months.'
minutes:
type: integer
minimum: 15
maximum: 10080
description: 'interval: every N minutes, counted from the previous run.'
securitySchemes:
apiKeyAuth:
type: apiKey
in: header
name: x-access-token
description: JWT token passed in x-access-token header
````
This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.