Conversation API

The Conversation API lets you interact with Contentrain Studio's AI agent programmatically. Instead of using the web interface, you can send messages and receive structured responses through a REST API — enabling chatbots, CI/CD pipelines, and custom integrations.

What the Conversation API Is

The Conversation API exposes the same AI agent that powers the Studio chat panel, but through a programmatic interface:

• Same tool set (create/update/delete content, manage models, etc.)
• Same permission model (scoped by API key role)
• Same branch workflow (changes go to review branches)
• Same conversation context (maintains history within a session)

API Key Management

Conversation API access requires an API key, managed in the project settings.

Creating an API Key

1. Open the project sidebar
2. Navigate to Conversation Keys settings
3. Click Create key
4. Configure the key:

Setting	Description
Name	Descriptive label for the key
Role	viewer, editor, or admin — determines what the agent can do
Specific models	Restrict access to certain models (Enterprise)
Allowed models	List of model IDs the key can access
Allowed tools	Which agent tools the key can invoke
Allowed locales	Which locales the key can read/write
Custom instructions	Additional system prompt text for this key
AI model	Which Claude model to use — Haiku or Sonnet (defaults to Sonnet)

5. The key is generated and shown once — copy it immediately

Key Format

Conversation API keys follow the format:

crn_conv_{random-base62-string}

WARNING

API keys are shown only once at creation time. Studio stores only the SHA-256 hash. If you lose the key, create a new one and delete the old one.

Editing and Deleting Keys

You can update a key's name, role, and restrictions at any time. Deleting a key immediately revokes access.

Sending Messages

Endpoint

POST /api/conversation/v1/{projectId}/message
Authorization: Bearer crn_conv_...
Content-Type: application/json

Request Body

{
  "message": "Create a blog post titled 'API-Created Post' with status published",
  "conversationId": null,
  "model": "claude-sonnet-4-5"
}

Field	Required	Description
message	Yes	The user message to send to the agent
conversationId	No	Continue an existing conversation (null for new)
model	No	Override the AI model (defaults to key's configured model)

Response

The response streams as Server-Sent Events (SSE):

data: {"type":"conversation","id":"conv-uuid"}
data: {"type":"text","content":"I'll create that blog post for you."}
data: {"type":"tool_use","id":"tool-1","name":"save_content"}
data: {"type":"tool_result","id":"tool-1","result":{"branch":"cr/content/blog-posts/en/..."}}
data: {"type":"text","content":"Done! The blog post has been created on branch cr/content/blog-posts/en/..."}
data: {"type":"done","affected":{"models":["blog-posts"],"branchesChanged":true}}

Event Types

Event	Description
conversation	Conversation ID assigned (use for follow-up messages)
text	AI response text chunk
tool_use	Agent is invoking a tool
tool_result	Tool execution completed
done	Conversation turn complete, includes affected resources
error	An error occurred

Conversation History

Listing Conversations

GET /api/conversation/v1/{projectId}/history
Authorization: Bearer crn_conv_...

Returns a list of past conversations:

[
  {
    "id": "conv-uuid",
    "title": "Create blog post",
    "created_at": "2026-04-02T10:00:00Z",
    "updated_at": "2026-04-02T10:05:00Z"
  }
]

Continuing a Conversation

Pass the conversationId in subsequent requests to maintain context:

{
  "message": "Now update the title to 'Updated Post'",
  "conversationId": "conv-uuid"
}

The agent will remember the previous context and can reference earlier operations.

Custom Instructions

Each API key can have custom instructions — additional text injected into the agent's system prompt. Use this to:

• Set content guidelines ("Always use formal English")
• Define default behaviors ("Set status to draft unless I say published")
• Restrict scope ("Only work with the blog-posts model")
• Add domain knowledge ("Our brand voice is friendly and professional")

Custom instructions are configured when creating or editing the API key.

Use Cases

Chatbot on Your Website

Embed a chat widget on your website that uses the Conversation API to let visitors ask questions about your content or submit feedback:

const response = await fetch('/api/conversation/v1/{projectId}/message', {
  method: 'POST',
  headers: {
    'Authorization': 'Bearer crn_conv_...',
    'Content-Type': 'application/json',
  },
  body: JSON.stringify({
    message: userInput,
    conversationId: sessionId,
  }),
})

const reader = response.body.getReader()
// Process SSE stream...

CI/CD Content Updates

Automate content updates from your deployment pipeline:

curl -X POST \
  -H "Authorization: Bearer crn_conv_..." \
  -H "Content-Type: application/json" \
  -d '{"message": "Set the site-settings version field to 2.1.0"}' \
  https://your-studio.com/api/conversation/v1/{projectId}/message

Bulk Content Operations

Use the API to perform bulk operations that would be tedious in the UI:

const operations = [
  'Set all blog posts with status draft to published',
  'Add the tag "featured" to entries with rating above 4',
  'Copy all English FAQ entries to Spanish',
]

for (const op of operations) {
  await sendMessage(op, conversationId)
}

Content Migration

Migrate content from external sources by instructing the agent:

"Create a team member entry with name 'Jane Smith', role 'CTO',
bio 'Leading technology strategy...', and email '[email protected]'"

Role-Based Access

Each Conversation API key has exactly one of three roles, and that role determines what the agent can do:

Role	Can Read	Can Write	Can Delete	Can Manage Models
Viewer	Yes	No	No	No
Editor	Yes	Yes	Yes	No
Admin	Yes	Yes	Yes	Yes

INFO

These three roles (viewer / editor / admin) are specific to Conversation API keys. They are not the same as the workspace and project roles used by the in-app AI Chat agent (workspace owner / admin / member combined with project editor / reviewer / viewer).

Model Restrictions

With specificModels enabled, the API key can only access the models listed in allowedModels. This is useful for creating scoped keys that can only manage specific content areas.

Tool Restrictions

The allowedTools setting lets you restrict which agent tools a key can invoke. For example, a viewer key might only allow brain_query and brain_search, while an editor key allows save_content and delete_content.

Locale Restrictions

The allowedLocales setting restricts which locales the key can read from and write to.

Plan Limits

Feature	Free	Starter	Pro	Enterprise
Conversation keys	0	0	15	Unlimited
API messages/month	0	0	3,000	Unlimited
Custom instructions (roadmap)	No	No	Yes	Yes

INFO

The Conversation API is an Enterprise-Edition feature available on Pro and above — Starter workspaces cannot create conversation keys.

Next Steps

• AI Chat — Understand the agent's capabilities
• Content Models — Define models for API-driven content
• Webhooks — Get notified when content changes via API