ceven

Vapi

Syncs voice call transcripts and analytics into your CRM, updates assistant prompts based on customer feedback, and monitors call quality through automated scorecards.

Try Vapi in Ceven

Ask Ceven anything
Standard

Why use Ceven?

  1. AI native Vapi integration

    • Describe the outcome and Ceven picks the right Vapi calls, fills the parameters, and checks the result.
    • Structured, agent friendly tool schemas so each call runs reliably instead of by guesswork.
    • Rich coverage for reading, writing, and querying your Vapi data, across all 38 of its actions.

  2. Managed auth

    • Built in OAuth with automatic token refresh and rotation.
    • One place to manage, scope, and revoke Vapi access.
    • Per user and per environment credentials instead of shared keys.

  3. Agent optimized design

    • Actions are tuned from real success and error rates so reliability climbs over time.
    • Full execution logs so you always know what ran in Vapi, when, and on whose behalf.
    • The agent pauses and asks when Vapi is unclear instead of plowing ahead.

  4. Enterprise grade security

    • Fine grained access so you control which agents and people can reach Vapi.
    • Least privilege by default, read scopes first and only the writes a workflow needs.
    • A full audit trail of every Vapi action to support review and sign off.

Supported tools

Every action Ceven's agents can run on Vapi, and when to use it.

Create assistant
Use this when you need to deploy a new voice agent with specific voice, model, and transcriber settings.
Update assistant
Modify an existing assistant configuration to tweak the system prompt or change the voice provider.
List calls
Pull a list of recent calls filtered by assistant ID or date range to analyze traffic patterns.
Get call
Retrieve full details for a single call including the transcript, recording URL, and total cost.
Create phone number
Provision a new phone number through Vapi or a BYO provider to route calls to your agent.
Delete phone number
Remove a phone number from the organization when it is no longer needed for a campaign.
Create analytics query
Run aggregations on call data to find average duration or total cost across a specific cohort.
Create scorecard
Set up structured metrics to evaluate if an assistant is meeting specific conversation goals.
Get insights
Pull processed insights and patterns from call data to identify common customer pain points.
Create eval
Build a test scenario to validate that an assistant responds correctly to a specific user input.
Create session
Establish a persistent conversation context that allows a user to move between different chats.
List assistants
Retrieve all configured voice agents in the organization to audit their current settings.
Delete Chat
Tool to delete a chat by its ID from Vapi. Use when you need to permanently remove a chat conversation.
Get Chat
Tool to fetch chat details by ID. Use when you have a chat ID and need full chat information including messages, costs, and configuration.
Create Analytics Queries
Tool to create and execute analytics queries on VAPI data. Use when you need to analyze call or subscription metrics with aggregations like count, sum, average, min, or max. Supports grouping by various dimensions and time based analysis wi
Create OpenAI Chat
Tool to create an OpenAI compatible chat using the Vapi API. Use when you need to send a chat message to an assistant or squad and receive a response. Supports both streaming and non streaming modes.
Create Monitoring Policy
Tool to create a monitoring policy in VAPI. Use when you need to set up automated monitoring rules based on thresholds and time windows. Policies can trigger alerts based on event counts or percentages over a specified lookback window.
Create Provider Resource
Tool to create an 11Labs pronunciation dictionary resource. Use when you need to define custom pronunciations for specific terms or acronyms in voice synthesis.
Delete Call
Tool to delete a call by its unique identifier. Use when you need to remove call data from the system. Returns the deleted call object with all its associated data.
Delete Eval
Tool to delete an eval by ID. Use when you need to permanently remove an eval from the system.
Get Eval
Tool to retrieve an eval by its ID. Use when you need to fetch details about a specific eval including its mock conversation messages and metadata.
Delete Eval Run
Tool to delete an eval run by its ID from Vapi. Use when you need to permanently remove an evaluation run.
Update Eval
Tool to update an existing eval in Vapi. Use when you need to modify eval properties like name, description, type, or mock conversation messages.
Get Assistant
Tool to retrieve a specific assistant by ID from Vapi. Use when you need to fetch details about an existing assistant.
Get File
Tool to retrieve a file by its ID from Vapi. Use when you need to get details about a specific file including its status, metadata, storage location, and timestamps.
List Monitoring Policies
Tool to retrieve monitoring policies from Vapi. Use when you need to list, filter, or search for monitoring policies configured in the organization. Supports filtering by policy ID, severity level, monitor ID, and date ranges for creation/u
Get Observability Scorecard
Tool to list observability scorecards with optional filtering and pagination. Use when you need to retrieve scorecards for monitoring or analysis.
List Provider Resources
Tool to list provider resources from Vapi. Use when you need to retrieve pronunciation dictionaries or other resources from providers like 11labs or Cartesia.
List Structured Outputs
Tool to list structured outputs with optional filtering. Use when you need to retrieve structured output configurations with pagination support. Supports filtering by ID, name, timestamps, and includes pagination controls.
List Chats
Tool to retrieve a list of chat conversations from VAPI. Use when you need to view existing chats, optionally filtered by assistant, squad, session, or time range. Supports pagination and sorting for efficient retrieval of large chat histor

30 actions · scroll to see them all

Frequently asked questions

Ceven connects to Vapi via webhooks and API calls to pull the full transcript the moment a call ends. The agent then processes the text to extract structured data like names, dates, and intent. This data is mapped to your downstream tools, such as Salesforce or HubSpot, so the conversation history is available to your team without manual entry. You can configure the workflow to only trigger for calls that lasted longer than a certain duration or those that reached a specific state, ensuring your CRM stays clean and only contains high value interaction data.
Yes. Vapi supports a Bring Your Own phone number model via providers like Twilio or Vonage. When you provision these in Vapi, Ceven can manage them using the Create Phone Number action. The workflow can automate the assignment of these numbers to different assistants based on the geographic region of the incoming lead or the specific marketing campaign they are responding to. This allows for a personalized caller ID experience while keeping all the orchestration logic within the Ceven workflow layer for easy adjustments.
Scorecards in Vapi allow you to define specific conditions that determine if a call was successful. Ceven uses these scorecards to trigger conditional logic. For example, if a Vapi scorecard marks a call as failed because the agent did not mention a discount code, Ceven can automatically flag that call for a human supervisor. It can also aggregate these scores over time to create a quality report, notifying you via Slack when the average success rate for a specific assistant drops below a predefined threshold.
Sessions in Vapi create a persistent context for a user across multiple interactions. Ceven manages these sessions to ensure that if a customer calls back, the assistant remembers the previous conversation. This is achieved by storing the session ID in your database and passing it back to Vapi during the call initiation. Ceven can also update session metadata based on external events, such as a customer updating their profile on your website, so the voice agent has the most current information the second the call connects.
While Vapi allows for many assistants, you should be aware that API rate limits apply to the management endpoints. If you attempt to update hundreds of assistants simultaneously through a Ceven loop, you may encounter 429 rate limit errors. To handle this, Ceven implements an exponential backoff strategy and queues requests to ensure your updates are processed without crashing the workflow. It is generally better to use a few versatile assistants with dynamic prompts rather than creating a unique assistant for every single minor variation in your use case.
Yes, Ceven leverages the Create Eval tool to run automated tests against your assistants. You can define a set of mock conversations and expected outcomes. Ceven then runs these evals and compares the actual Vapi response to your expected result. If the agent deviates from the script or fails to extract a key piece of information, Ceven can alert you and even suggest a prompt modification. This ensures that changes to your AI model do not introduce regressions in how the agent handles critical customer paths.
Vapi charges based on the duration of the call and the models used for transcription and synthesis. Ceven can run a daily Create Analytics Query to sum up the costs across all assistants. If the spending exceeds your daily budget, Ceven can trigger an emergency action to switch assistants to a cheaper model or notify the administrator. You can also use Ceven to identify which specific assistants are the most expensive per lead, allowing you to optimize the prompt length or the voice provider to reduce overhead.
Ceven primarily operates on the orchestration layer around the call. While it cannot change the prompt in the middle of a spoken sentence, it can update the assistant configuration or session metadata between calls. For real time interactivity during a call, you should use Vapi tools. Ceven can be the backend that those Vapi tools call. When the Vapi agent triggers a tool, it sends a request to a Ceven workflow, which then fetches the data from your SaaS tools and returns it to the agent to speak to the customer.

Alternatives to Vapi

Other tools that solve a similar problem. Ceven supports these too, so you can switch or run more than one at once.

Retell AI logoRetell AIBland AI logoBland AIAir AI logoAir AI

Try Ceven on your stack

Plug Ceven on top of the tools you already run. Connect Vapi and the rest of your stack, describe the outcome, and its agents handle the work end to end, days of it in minutes.

Get started for free