Integration
Connect Carbon Voice and Openlayer
When New Action Item Created fires in Carbon Voice, your agent runs Publish Record in Openlayer, or New Project in Openlayer to Add Link Attachments to Message in Carbon Voice. Describe the whole flow and it is built, tested on every scenario and kept running.
What the catalog holds today. Ask for anything missing and your agent reads the API documentation and adds it.
Build solutions, not workarounds.
What do you want Carbon Voice and Openlayer to do together?
Ask the assistant
Connect your AI client
Give your AI client this address.
https://mcp.apiant.aiOne connection does both: ask your client to act in an app once, or have it build an automation that keeps running. Any client that takes a remote MCP server. Nothing to install. Create your free account, then sign in once in your browser.
Set it up in your client
Claude Code
Run this in the directory you want to work in.
claude mcp add --transport http -s project apiant-ai https://mcp.apiant.aiStart Claude Code there, approve the server, and sign in in the browser page it opens.
Claude Code guide (opens in a new tab)Claude, web and desktop
Open Customize, then Connectors, then Add custom connector, and paste the address. On Team and Enterprise an owner adds it first.
Setup guide (opens in a new tab)Cursor
Add the address to your MCP configuration as a server URL. Cursor signs you in in your browser.
Setup guide (opens in a new tab)Zed
Open Settings, then AI, then MCP Servers, then Add Server, then Add Remote Server.
Setup guide (opens in a new tab)Codex and the ChatGPT desktop app
Open Settings, then MCP servers, then Add server, and choose Streamable HTTP. From the terminal, Codex takes the address with its own add command and then signs you in.
Setup guide (opens in a new tab)Any other MCP client
Paste the address where the client asks for a remote MCP server URL, and name the server apiant-ai where it lets you. APIANT's skills reach the client over the same connection.
Setup guide (opens in a new tab)Example flows
What Carbon Voice and Openlayer can do together
From Carbon Voice to Openlayer
When New Action Item Created in Carbon Voice
then Publish Record in Openlayer
When New AI Prompt Response Generated in Carbon Voice
then Create Project in Openlayer
From Openlayer to Carbon Voice
When New Project in Openlayer
then Add Link Attachments to Message in Carbon Voice
When New Test Result in Openlayer
then Create Message Share Link in Carbon Voice
Starting points drawn from the triggers and actions in the catalog today. Describe the flow you need, at any depth, and your agent builds it and tests every scenario before it ships.
Everything your agent can do with Carbon Voice and Openlayer
Triggers and actions 9 triggers · 46 actions
Trigger
Action Item DeletedTriggers when an action item is deleted.
Trigger
New Action Item CreatedTriggers when an action item is created.
Trigger
New AI Prompt Response GeneratedTriggers when AI Prompt happened to a message(s).
Trigger
New AI System Prompt Response GeneratedTriggers when AI System Prompt happened to a message(s).
Trigger
New Message Posted to ConversationTriggers when a message is posted into a conversation.
Trigger
New Message ReceivedTriggers when a message is received in any conversation (Not includes your own messages).
Trigger
New Voice Memo CreatedTriggers when a voice memo is created.
Action
Add folderCreate a folder.
Action
Add Link Attachments to MessageAdd one or more link attachments to a Message.
Action
Create Action ItemCreate an Action Item.
Action
Create AI Prompt ResponseCreates a new Ai response for given prompt and message(s).
Action
Create Message Share LinkCreate a share link for a message.
Action
Create Voice MemoCreate a Voice Memo from audio file, transcript or links.
Action
Delete action itemDelete an action item.
Action
Delete folderDelete a folder and nested content.
Action
Find users by email, phone or nameSearch users by email, phone or name.
Action
Get AI Prompt ResponseReturns one AI prompt response (prompt, generated responses per language, source messages) by id.
Action
Get conversationGet a conversation by id.
Action
Get messageGet a message by id.
Action
Get Message Share LinkReturns one message share link by id.
Action
Get userGet a user by id.
Action
List AI Prompts/prompts (optional owner_type=user|workspace|system, workspace_id) — lists the AI prompts available to the account, returning each prompt's id. Read-only.
Action
List conversationsList all of the user's conversations (id and name only).
Action
List conversation usersList users in a conversation.
Action
List foldersList root folders.
Action
List messagesList messages.
Action
List workspacesList workspaces the user can access.
Action
Send Direct Message to User(s)Send a Direct Message to specific User(s).
Action
Send Message to ConversationSend a Message to specific Conversation.
Action
Update Action ItemUpdate an Action Item.
Action
Update folderRename a folder.
Trigger
New ProjectTriggers when a new project is created in your Openlayer workspace.
Trigger
New Test ResultTriggers when a new test result is available for a data source. Useful for alerting on passing or failing model tests.
Action
Create Data SourceCreates a new data source in a project for streaming production data to Openlayer.
Action
Create ProjectCreates a new AI or ML project in your Openlayer workspace.
Action
Create TestCreates a data quality test in a project. Checks for duplicate rows, null values, or row counts.
Action
Delete Inference PipelineDelete an inference pipeline by its ID.
Action
Delete ProjectDelete a project by its ID.
Action
Delete TestDelete a test by its ID.
Action
Evaluate TestEvaluates a test for a specific time range. Use after publishing records to get immediate results.
Action
Find Data SourceFinds a data source (inference pipeline) by name in a project.
Action
Find ProjectFinds a project by name in your Openlayer workspace.
Action
Find Test ResultFinds test results for a data source, including whether each test passed or failed. Filter by outcome or test type to branch an automation on the result.
Action
Get Inference PipelineRetrieve the details around a specific inference pipeline.
Action
Get ProjectRetrieves one project by its id. Openlayer has no single-project endpoint, so this reads the workspace's first 100 projects and returns the one matching the id.
Action
Get TestRetrieve a test by ID.
Action
Get Test ResultRetrieves one test result by its id. Openlayer has no single-result endpoint, so this reads the data source's 100 most recent results and returns the matching one.
Action
List Inference PipelinesList the authenticated user's inference pipelines under a project.
Action
List ProjectsLists the projects in your Openlayer workspace, optionally narrowed to one kind of project. Returns up to 100 projects.
Action
List Test ResultsList all results for a test/goal under an inference pipeline.
Action
List TestsLists the tests in a project, optionally narrowed by kind, archived state or monitoring mode. Returns up to 100 tests.
Action
Publish RecordPublishes an LLM inference record to a data source for monitoring. Streams the model input, output, and metadata to Openlayer.
Action
Update Inference PipelineUpdate an inference pipeline.
Action
Update ProjectUpdate a project.
Action
Update TestUpdate a test (partial updates allowed).
No trigger or action matches that. Ask your agent to add it: it reads the API documentation and builds what you describe.
Each app on its own
Reviews
What our customers say
More from Carbon Voice
Carbon Voice to HubSpotHubSpot is your all-in-one stop for all of your marketing software needs.
Carbon Voice to SalesforceSalesforce is a leading enterprise customer relationship management (CRM) platform.
Carbon Voice to SlackSlack is a messaging platform for teams. Post messages, manage channels, users, reminders, and react to...
Carbon Voice to Google SheetsGoogle Sheets
Carbon Voice to GmailGmail is Google’s email service, featuring spam protection, search functions, and seamless integration with...
Carbon Voice to Google CalendarGoogle Calendar is a time management tool providing scheduling features, event reminders, and integration...
More into Openlayer
Google Sheets to OpenlayerGoogle Sheets
Gmail to OpenlayerGmail is Google’s email service, featuring spam protection, search functions, and seamless integration with...
Google Calendar to OpenlayerGoogle Calendar is a time management tool providing scheduling features, event reminders, and integration...
Google Drive to OpenlayerGoogle Drive is a cloud storage solution for uploading, sharing, and collaborating on files across devices...
Mailchimp to OpenlayerMailchimp marketing automation and email platform.
ActiveCampaign to OpenlayerActiveCampaign is a marketing automation, email marketing, and CRM platform.
Questions
Carbon Voice and Openlayer, answered
What can start an automation from Carbon Voice?
Any of Carbon Voice's 7 triggers in the catalog, including New Action Item Created, New AI Prompt Response Generated, New AI System Prompt Response Generated and New Message Posted to Conversation. Describe the moment in plain language and your agent picks the right one.
What can your agent do in Openlayer when something happens in Carbon Voice?
Any of Openlayer's 22 actions, including Create Data Source, Create Project, Create Test and Update Inference Pipeline. Your agent maps the data both ways and tests every scenario before it ships.
Can it also run from Openlayer to Carbon Voice?
Yes. When something happens in Openlayer, your agent can act in Carbon Voice too. This page covers both directions: Openlayer's triggers and Carbon Voice's actions are listed here as well.
Do I have to build a connector for Carbon Voice or Openlayer?
No. Both are in the catalog with their triggers and actions. You describe the automation; your agent builds it, tests every scenario and keeps it running.
Can my AI client use Carbon Voice and Openlayer without building an automation?
Yes. With your AI client connected to APIANT, ask it to do something in either app once and it runs that action on the spot. Ask for an automation and your agent builds it, tests every scenario and keeps it running. One connection covers both.
What happens when something fails?
Your agent works that out for you. It plans the failure paths along with the happy path, then tests every scenario before it ships.
Is there a free plan?
Yes. Every plan includes the agent, including free, and building from your own AI client spends no assistant credits.