Skip to content
Changelog

Report a bug

Bolna integration: operations for AI agents

Bolna connects to Type.com as an integration. This page lists the 126 operations documented for Claude and Codex in Type.com: 53 read, 46 write, 27 destructive.

About Bolna

Create conversational voice agents using Bolna AI to enhance interactions, streamline operations and automate support.

Categories: Developer Tools & IT, Communication & Meetings

How to connect Bolna to Type.com

Access
Organization connection: one shared account for the workspace.
MCP
This integration is not available through Type’s MCP server. It remains available in Type.

To add the connection, follow the steps in Space connections.

Documented operations

126 operations. Your connection's permissions determine which operations are available. API references describe the vendor surface; they do not expand your connection's credentials or access.

126 operations listed.

Bolna

  • Read

    Retrieve voice AI agent details (deprecated)

    Deprecated v1 endpoint to retrieve a Bolna voice AI agent. New integrations should use the v2 Get agent API, which replaces this endpoint. > [!WARNING] > > These APIs have now been deprecated. > > Please use the latest **v2 APIs**. Retrieve an agent

    GET /agent/{agent_id}

  • Read

    List all voice AI agents (deprecated)

    Deprecated v1 endpoint to list all your Bolna voice AI agents. New integrations should use the v2 List all agents API, which replaces it. > [!WARNING] > > These APIs have now been deprecated. > > Please use the latest **v2 APIs**. List all agents

    GET /agent/all

  • Read

    Get all agent executions API (v1, deprecated)

    Deprecated v1 endpoint to list executions for an agent. New integrations should use the v2 agent executions API. Retrieve all executions by an agent

    GET /agent/{agent_id}/executions

  • Read

    Retrieve voice AI agent execution

    Fetch specific execution details of a Voice AI agent, including conversation times, statuses, and metrics, via Bolna APIs. Retrieve specific execution by an agent

    GET /agent/{agent_id}/execution/{execution_id}

  • Read

    List batch executions

    Learn how to retrieve all executions from a batch, providing detailed information on each call's outcome and metrics. Retrieve all executions from a batch. Returns a bare JSON array of execution objects (not wrapped in a data key).

    GET /batches/{batch_id}/executions

  • Read

    Get batch

    Find out how to retrieve details of a specific batch, including its creation time, status, call status and scheduled execution time. Retrieve a batch

    GET /batches/{batch_id}

  • Read

    List all batches

    Explore how to list all batches associated with a particular Bolna Voice AI agent, providing an overview of their statuses, schedules and other relevant details List all batches for agent

    GET /batches/{agent_id}/all

  • Read

    Get compliance application

    Retrieve a single phone number compliance application by its ID, including its review status and rejection reason. Retrieve a single phone number compliance application and its review status.

    GET /compliance/{compliance_id}

  • Read

    List compliance applications

    Retrieve all phone number compliance applications submitted by your account, along with their review status and rejection reason. List all phone number compliance applications submitted by your account, along with their review status.

    GET /compliance/list

  • Read

    Get disposition

    Retrieve a single disposition by ID via GET /dispositions/{disposition_id}, optionally scoped to a specific agent for ownership checks. Retrieve a single disposition by ID, optionally scoped to a specific agent.

    GET /dispositions/{disposition_id}

  • Read

    List dispositions

    Retrieve all dispositions accessible to your account via GET /dispositions/, optionally scoped to a specific agent with a query parameter. List dispositions accessible to your account. When agentid is provided, only dispositions linked to that agent are returned; otherwise all dispositions you own are returned.

    GET /dispositions/

  • Read

    Retrieve voice AI execution

    Fetch details of a specific phone call execution by its ID using Bolna APIs. This includes information such as conversation time, status, and telephony data. Retrieve specific execution by executionid

    GET /executions/{execution_id}

  • Read

    Retrieve voice AI execution debug bundle

    Fetch everything needed to debug one call in a single Bolna API request: the execution, per-turn latency with the structured transcript, and pipeline logs. Retrieve everything needed to debug one execution in a single response, trimmed to fit an AI assistant's tool result. Returns what the dashboard's Debugging view shows.

    GET /executions/{execution_id}/debug

  • Read

    Retrieve voice AI execution raw logs

    Fetch raw logs of a phone call execution by ID via the Bolna API, including prompts, requests, responses, and optional LLM reasoning summaries. Retrieve raw logs of specific executionid

    GET /executions/{execution_id}/log

  • Read

    List extraction categories

    Retrieve all extraction categories attached to an agent via GET /agent/{agent_id}/extraction-categories, each with the dispositions it owns. List the extraction categories attached to an agent. Each category is returned with the dispositions it owns.

    GET /agent/{agent_id}/extraction-categories

  • Read

    Get knowledge base

    Retrieve details of a specific knowledge base, including its ID, file name, creation time, and status, using Bolna APIs. Retrieve a knowledge base

    GET /knowledgebase/{rag_id}

  • Read

    List all knowledge bases

    Retrieve all knowledge bases in your Bolna account with the List all knowledge bases API, including each one's status and creation date. List all knowledge bases for your account

    GET /knowledgebase/all

  • Read

    List phone numbers API

    Retrieve all phone numbers associated with your account, including details like creation date and telephony provider like Twilio, Plivo, etc. List all phone numbers for your account

    GET /phone-numbers/all

  • Read

    Search phone numbers API

    Search available phone numbers by region, locality, or pattern, with price to use them with Bolna Voice agents. Search available phone numbers by country and pattern

    GET /phone-numbers/search

  • Read

    List providers API

    Retrieve all providers associated with your Bolna account, including their IDs, names, and creation timestamps. List all providers

    GET /providers

  • Read

    Get SIP trunk (deprecated)

    Get a single SIP trunk with full details including gateways, IP identifiers, and phone numbers. Look up any trunk by its ID. > [!WARNING] > > **Legacy SIP trunks (deprecated).** These `/sip-trunks` endpoints manage legacy SIP trunks. Existing legacy trunks keep working, but use the SIP trunks API for every new setup, and see Migrate to SIP trunks to move an existing trunk. Get a single SIP trunk with full details including gateways, IP identifiers, and phone numbers

    GET /sip-trunks/trunks/{trunk_id}

  • Read

    List SIP trunks (deprecated)

    List all SIP trunks configured in your Bolna account. Filter by active status and view trunk details including gateways and phone numbers. > [!WARNING] > > **Legacy SIP trunks (deprecated).** These `/sip-trunks` endpoints manage legacy SIP trunks. Existing legacy trunks keep working, but use the SIP trunks API for every new setup, and see Migrate to SIP trunks to move an existing trunk. List all SIP trunks for your account

    GET /sip-trunks/trunks

  • Read

    List phone numbers on trunk (deprecated)

    List all phone numbers associated with a SIP trunk. View assigned DID numbers and manage your trunk number inventory. > [!WARNING] > > **Legacy SIP trunks (deprecated).** These `/sip-trunks` endpoints manage legacy SIP trunks. Existing legacy trunks keep working, but use the SIP trunks API for every new setup, and see Migrate to SIP trunks to move an existing trunk. List all phone numbers associated with a SIP trunk

    GET /sip-trunks/trunks/{trunk_id}/numbers

  • Read

    Get all sub-accounts usage

    Retrieve aggregated usage, consumption and cost breakdowns for every sub-account in your organization. An enterprise feature of Bolna. > [!NOTE] > > This is an `enterprise` feature. > > You can read more about our enterprise offering here Bolna enterprise. Retrieve usage details for all sub-accounts under the authenticated organization for up to 32 days.

    GET /sub-accounts/all/usage

  • Read

    List all sub-accounts

    Retrieve all sub-accounts linked to your main Bolna account for centralized visibility and management. An enterprise feature. > [!NOTE] > > This is an `enterprise` feature. > > You can read more about our enterprise offering here Bolna enterprise. List all sub-accounts

    GET /sub-accounts/all

  • Read

    Track sub-account usage

    Track usage for one Bolna sub-account, with fine-grained insight into its usage, consumption and billing. An enterprise feature. > [!NOTE] > > This is an `enterprise` feature. > > You can read more about our enterprise offering here Bolna enterprise. Track usage for the sub-account upto 32 days

    GET /sub-accounts/{sub_account_id}/usage

  • Read

    Get SIP trunk connection details

    Get Bolna's SIP edge values to configure at your carrier via GET /trunk/pop: SIP domain, port, transports, signalling IPs and RTP port range. > [!NOTE] > > Allowlist every address in `ips` at your carrier, even if only one of them sends traffic today. Returns Bolna's SIP edge: the values you configure at your carrier. Point your carrier's inbound (origination) route at sipdomain on port, allowlist every address in ips for SIP signalling, and allow RTP media on rtpports. These values are the same for every trunk and every account. Read them from this endpoint rather than hard-coding them.

    GET /trunk/pop

  • Read

    Get SIP trunk

    Retrieve one SIP trunk via GET /trunk/trunks/{trunk_id}, with its gateways, carrier IPs, numbers, health and active calls. Retrieves one SIP trunk with its gateways, carrier IPs, numbers, health and activecalls.

    GET /trunk/trunks/{trunk_id}

  • Read

    List SIP trunks

    List your SIP trunks via GET /trunk/trunks, each with its gateways, carrier IPs, numbers, health and active calls. Lists your SIP trunks, oldest first. Each trunk carries its gateways, carrier IPs and numbers, plus its live health and activecalls. Deleted trunks are not returned. Trunks belong to your organisation and are shared by its members. A sub-account API key lists only the trunks created under that sub-account.

    GET /trunk/trunks

  • Read

    List SIP trunk calls

    List recent inbound and outbound calls on a SIP trunk's numbers via GET /trunk/trunks/{trunk_id}/calls, with outcome and SIP code. Lists recent calls on a trunk's numbers, newest first: inbound calls to them and outbound calls placed from them. Each entry links to its full record through executionid and the Get execution API.

    GET /trunk/trunks/{trunk_id}/calls

  • Read

    User information

    Get details like name, email, current wallet balance, concurrency limits, and account status for the authenticated user via GET /user/me. Get user information

    GET /user/me

  • Read

    List your custom LLM models

    List the custom LLMs in your account or sub-account, each with the ID needed to delete it. Sub-accounts also see the account's models. List your custom LLM models

    GET /user/model/custom

  • Read

    List your custom TTS voices

    List the custom text-to-speech voices in your account or sub-account, each with its ID. Sub-accounts also see the account's voices. List your custom TTS voices

    GET /user/tts/custom

  • Read

    List violations

    Retrieve a paginated list of violations, optionally filtered by status. Use this endpoint to monitor and manage call violations across your account. Retrieve a paginated list of violations, optionally filtered by status.

    GET /violations/list

  • Read

    List voices

    Get a paginated list of voices for a specific TTS provider and model. Requires provider_id and model_id from the List Providers endpoint. Returns a paginated list of voices available for a specific TTS provider and model. Voices include both platform-curated voices and any custom voices created by your account.

    GET /api/v1/voice-config/tts/voices

  • Read

    List TTS providers and models

    Get all supported TTS providers and their models for a given language. Returns provider IDs and model IDs needed to fetch voices. Returns all TTS providers with their supported models for a given language. Use this to discover available providers and their model IDs before fetching voices. Every provider and model is returned regardless of language; read issupported on each to see whether it covers the language you asked for.

    GET /api/v1/voice-config/tts

  • Read

    Campaign entries template

    Download the one-line CSV header naming exactly the columns required for a workflow campaign entry upload, fetched via GET with the campaign ID. Returns a one-line CSV header naming the fields the campaign's pinned version declares, in author order — the exact header an entries upload expects. Falls back to the four system fields when the version declares no schema.

    GET /workflow-campaigns/{campaign_id}/entries/template

  • Read

    Get workflow campaign

    Retrieve a Bolna workflow campaign with a per-status count of its entries and per-code counts of any upload validation failures. Retrieves a campaign with a count of entries per status and per-code counts of upload validation failures.

    GET /workflow-campaigns/{campaign_id}

  • Read

    List campaign entries

    List a workflow campaign's entries, including rows that failed upload validation together with the failure code for each one. Lists a campaign's entries, including failedvalidation rows with their failure code in validationerror.

    GET /workflow-campaigns/{campaign_id}/entries

  • Read

    List campaign executions

    List a campaign's executions, filterable by status and outcome. Poll after starting to watch contacts progress. Lists a campaign's executions. Poll after starting a campaign to watch contacts progress.

    GET /workflow-campaigns/{campaign_id}/executions

  • Read

    List workflow campaigns

    List Bolna workflow campaigns filtered by workflow, status or kind, and sorted by creation time, name or outcome counts. Lists campaigns, newest first by default.

    GET /workflow-campaigns

  • Read

    Workflow campaign report

    Aggregated campaign report: execution counts by status, termination reasons, and a per-node funnel keyed by your definition's node ids. > [!NOTE] > > For completed executions the `termination_reasons` keys are the `label` values of your end nodes, so the report maps directly onto the endings you designed. Aggregated campaign report — execution counts by status, termination reasons, and a per-node funnel keyed by the node ids in your definition.

    GET /workflow-campaigns/{campaign_id}/report

  • Read

    Get workflow execution

    The whole story of one contact's run: current status, every node attempt with the edge it took, and the recent timeline. Poll until terminal. > [!NOTE] > > Poll until `status` is one of `completed`, `failed`, `cancelled` or `aborted`. Each entry in `nodes` shows the attempt's status, the case that matched (`matched_case_index`) and the node it routed to (`to_node_id`), so you can replay the exact path through your graph. The whole story of one contact's run — status, every node attempt with the edge it took, and the most recent timeline events. Poll until status is terminal (completed, failed, cancelled or aborted).

    GET /workflow-executions/{execution_id}

  • Read

    Get workflow draft

    Read a workflow's stored draft definition and its current revision, the compare-and-set token you pass back when saving the draft. Reads the stored draft definition and its current revision. Use it to resync the revision before a save.

    GET /workflows/{workflow_id}/draft

  • Read

    Get workflow version

    Retrieve the frozen definition of one published workflow version via GET, identified by workflow ID and version number, for auditing or replay. Retrieves the frozen definition of a published version.

    GET /workflows/{workflow_id}/versions/{version}

  • Read

    Get workflow

    Retrieve a workflow with its draft metadata and every published version, including per-version campaign and outcome totals. Retrieves a workflow with its draft metadata and the metadata of every published version, including per-version campaign and outcome totals.

    GET /workflows/{workflow_id}

  • Read

    List workflows

    List your workflows via GET /workflows, newest first, with optional case-insensitive filtering by a substring of the workflow name. Lists your workflows, newest first.

    GET /workflows

  • Read

    Workflow node types

    Discover every node type with its configuration parameters, defaults and bounds, plus the variable namespaces available to conditions. > [!NOTE] > > The catalog is generated from the same models that publish enforces, so it never drifts from what the engine accepts. See the node reference for worked examples of each type. Lists every node type with its configuration parameters, defaults and bounds, plus the available variable namespaces and effects. Node types without an executor are returned with available set to false rather than omitted.

    GET /workflow-node-types

  • Write

    Create voice AI agent (deprecated)

    Deprecated v1 endpoint to create a Bolna voice AI agent. New integrations should use the v2 Create agent API, which replaces this endpoint. > [!WARNING] > > These APIs have now been deprecated. > > Please use the latest **v2 APIs**. Creates a new agent

    POST /agent

  • Write

    Patch update to voice AI agent (deprecated)

    Deprecated v1 endpoint to partially update an agent. New integrations should use the v2 Patch update agent API. > [!WARNING] > > These APIs have now been deprecated. > > Please use the latest **v2 APIs**. Patch update an agent

    PATCH /agent/{agent_id}

  • Write

    Create batch

    Discover how to create a batch for Bolna Voice AI agent by uploading a CSV file containing user contact numbers and prompt variable details for users. > [!NOTE] > > This is the API route. To run batches from the platform, upload your CSV under **Deploy → Batches** in the dashboard — see Batch Calling from the dashboard. > [!WARNING] > > Use a **numeric UTC offset** like `+00:00` — the `Z` suffix is rejected with a 500. The time must be at least 2 minutes in the future, and Bolna rounds the start up to the next 10-minute mark. Create batch for agent

    POST /batches

  • Write

    Schedule batch

    Learn how to schedule a batch for calling via Bolna Voice AI agent by specifying the batch ID and the desired execution time. > [!NOTE] > > **Time restrictions on `scheduled_at`** > > * Must be at most **30 days** in the future; later values return HTTP `400`. > * Batches scheduled less than 10 minutes ahead are dispatched immediately; batches scheduled 10 or more minutes ahead are marked `scheduled` and start at the requested time. > * Use a numeric UTC offset (e.g. `+00:00`); the `Z` suffix is not accepted. Schedule a batch for calling via agent

    POST /batches/{batch_id}/schedule

  • Write

    Make voice AI call

    Learn how to initiate outbound phone calls using Bolna Voice AI agents. Start making phone calls using the agent ID and recipient's phone number. > [!WARNING] > > **Wait for `completed`, not `call-disconnected`.** The `call-disconnected` event fires the instant the line drops, but `conversation_duration`, `total_cost`, `recording_url`, and `extracted_data` are not yet populated. The `completed` event (a few seconds later) has all finalized fields. See Get Execution. Initiate calls

    POST /call

  • Write

    Create compliance application

    Submit a phone number compliance application for India (DLT) with your business details, CIN certificate and GST certificate. Submit a new phone number compliance application for India (DLT) with your business details, CIN certificate and GST certificate. The application is reviewed and its status moves from submitted to accepted or rejected, usually within 24 hours.

    POST /compliance/create

  • Write

    Bulk create dispositions

    Atomically create and link multiple dispositions to an agent in one POST /dispositions/bulk request; either all succeed or none are created. > [!TIP] > > Use bulk create when setting up a new agent with a complete set of dispositions, or when importing a disposition configuration from another source. Either all dispositions are created and linked, or none are — partial results are not possible. > [!NOTE] > > Each item places its disposition in a category the same way Create Disposition does: pass `category_id` (preferred) or a `category` name, at most one of the two — an item carrying both fails the whole request with a 400 error. Items omitting both go to the agent's `General` category. See Extraction Categories. Atomically create and link multiple dispositions to an agent in a single request. Either all dispositions are created and linked, or none are.

    POST /dispositions/bulk

  • Write

    Create disposition

    Create a new disposition and link it to an agent in one POST /dispositions/ request; `agent_id` is required and at least one option type must be set. > [!NOTE] > > At least one of `is_subjective` or `is_objective` must be `true`. When `is_objective` is `true`, you must provide `objective_options`. See the ObjectiveOption schema for the full structure including nested `sub_options`. > > Place the disposition in a category by passing `category_id` (preferred) or a `category` name — at most one of the two; a payload with both fails with a 400 error. A `category` name that does not match one of the agent's categories creates a fresh category. When both are omitted, the disposition goes to the agent's `General` category. See Extraction Categories. Create a new disposition and link it to an agent. agentid is required and the disposition is automatically linked to that agent upon creation.

    POST /dispositions/

  • Write

    Create extraction category

    Create an extraction category and attach it to an agent via POST /agent/{agent_id}/extraction-categories; the category owns the model used for its LLM pass. > [!NOTE] > > The category name must be unique among the agent's attached categories. Add dispositions to the category with the Create Disposition endpoint, passing this category's `id` as `category_id`. Create an extraction category and attach it to the agent. Attaching a category gives the agent all of the category's dispositions; dispositions are added to the category via the Dispositions API using categoryid. The category name must be unique among the agent's attached categories. The model applies to the category's entire extraction pass — one category is evaluated in one LLM call.

    POST /agent/{agent_id}/extraction-categories

  • Write

    Update extraction category

    Rename an extraction category or change its model via PATCH /extraction-categories/{category_id}; renames update the category label on its dispositions. > [!NOTE] > > Send `name`, `model`, or both — an empty body is rejected. Renaming a category rewrites the `category` label on all of its dispositions in the same transaction. Changing `model` switches the LLM used for the category's extraction pass on subsequent calls. Update an extraction category. Both fields are individually optional, but at least one of name or model must be present — an empty body is rejected. Renaming a category rewrites the category label on all of its dispositions in the same transaction, so extraction results and disposition responses stay consistent. Changing model switches the LLM used for the category's extraction pass on subsequent calls.

    PATCH /extraction-categories/{category_id}

  • Write

    Set inbound agent

    Configure Bolna Voice AI agent to handle inbound calls automatically by associating it with a specific phone number using Bolna APIs. Add agent for inbound calls with optional IVR configuration

    POST /inbound/setup

  • Write

    Create knowledge base

    Upload a PDF document or provide a URL to create a knowledge base, enhancing your Bolna Voice AI agent's information base and response accuracy. Create knowledge base from a PDF file or URL. Provide either file or url, not both.

    POST /knowledgebase

  • Write

    Buy phone numbers API

    Buy virtual phone numbers with full purchase, pricing, and provider details to use with Bolna Voice agents for outbound and inbound calls. Buy a phone number

    POST /phone-numbers/buy

  • Write

    Move phone number

    Move a phone number between the main account and sub-accounts in your Bolna organization. An enterprise feature that needs sub-accounts. > [!NOTE] > > This is an `enterprise` feature and requires an organization account with sub-accounts. Move a phone number between the main account and sub-accounts of your organization. This changes which account owns the number. To transfer a live call to another number, see call transfer.

    POST /phone-numbers/move

  • Write

    Add a new provider

    Learn how to securely add a new provider to your Bolna account by specifying the provider's name and associated credentials. Add provider

    POST /providers

  • Write

    Add phone number to trunk (deprecated)

    Add a DID phone number to your SIP trunk using the Bolna API. Assign numbers for inbound and outbound voice calling on your trunk. > [!WARNING] > > **Legacy SIP trunks (deprecated).** These `/sip-trunks` endpoints manage legacy SIP trunks. Existing legacy trunks keep working, but use the SIP trunks API for every new setup, and see Migrate to SIP trunks to move an existing trunk. Add a DID phone number to a SIP trunk

    POST /sip-trunks/trunks/{trunk_id}/numbers

  • Write

    Create SIP trunk (deprecated)

    Create a new SIP trunk on Bolna and register it with your gateway details. Set up your trunk for inbound and outbound voice calling. > [!WARNING] > > **Legacy SIP trunks (deprecated).** These `/sip-trunks` endpoints manage legacy SIP trunks. Existing legacy trunks keep working, but use the SIP trunks API for every new setup, and see Migrate to SIP trunks to move an existing trunk. Create a new SIP trunk and register it with Bolna's media layer

    POST /sip-trunks/trunks

  • Write

    Update SIP trunk (deprecated)

    Partially update an existing SIP trunk on Bolna using a PATCH request. Only the fields you include in the request body will be changed. > [!WARNING] > > **Legacy SIP trunks (deprecated).** These `/sip-trunks` endpoints manage legacy SIP trunks. Existing legacy trunks keep working, but use the SIP trunks API for every new setup, and see Migrate to SIP trunks to move an existing trunk. Partially update an existing SIP trunk. Only included fields are changed. Gateways and ipidentifiers arrays are fully replaced when provided.

    PATCH /sip-trunks/trunks/{trunk_id}

  • Write

    Create a new sub-account

    Create a new sub-account using the Bolna API to define separate workspaces with custom configurations for enterprise-level management. > [!NOTE] > > This is an `enterprise` feature. > > You can read more about our enterprise offering here Bolna enterprise. Creates a new sub-account

    POST /sub-accounts/create

  • Write

    Patch update a sub-account

    Use this Bolna API endpoint to partially modify and update sub-account properties, including its name and concurrency limits. > [!NOTE] > > This is a partial update — send only the fields you want to change. The following can be updated: > > * `name` > * `min_concurrency` — guaranteed concurrency floor (`0` = no guarantee) > * `max_concurrency` — hard cap; omit to leave unchanged, send `null` to make the sub-account elastic, `0` to pause it > > Only **organization admins** can update sub-accounts. Omitting a concurrency field leaves it unchanged; the edit is rejected with `400` if it would break the organization's concurrency envelope. Patch update a sub-account

    PATCH /sub-accounts/{sub_account_id}

  • Write

    Add carrier IP to SIP trunk

    Allow inbound calls from your carrier by adding its signalling address or CIDR range via POST /trunk/trunks/{trunk_id}/ip-acls. > [!NOTE] > > Add every signalling address your carrier publishes for inbound calls. Bolna's SIP edge answers an INVITE from any other source with `403 Forbidden`. Adds a carrier IP: an address or CIDR range your carrier sends inbound calls from. Bolna's SIP edge refuses an INVITE from any source that is not on an active, inbound-enabled trunk's carrier IP list with 403 Forbidden, so list every signalling address your carrier publishes. A bare address is stored as a /32, and host bits are cleared (203.0.113.7/24 is stored as 203.0.113.0/24). Ranges must be public IPv4 and no broader than /16. A trunk has at most 32 carrier IPs. Bolna's SIP edge is normally reloaded with the change before the response returns.

    POST /trunk/trunks/{trunk_id}/ip-acls

  • Write

    Add gateway to SIP trunk

    Add a carrier SIP host that outbound calls are sent to via POST /trunk/trunks/{trunk_id}/gateways; gateways are tried in priority order. Adds a gateway: a carrier SIP host that outbound calls on this trunk are sent to. A trunk has at most 8 gateways. Outbound calls try gateways in ascending priority (ties in the order they were added). When the carrier fails a call in a way another gateway could fix, the next gateway is tried; a definitive answer such as busy or declined ends the call.

    POST /trunk/trunks/{trunk_id}/gateways

  • Write

    Add number to SIP trunk

    Add a phone number from your carrier to a SIP trunk via POST /trunk/trunks/{trunk_id}/numbers, optionally with the agent that answers it. > [!NOTE] > > `e164` must be in E.164 format with the plus. Set `destination_key` to the called number exactly as your carrier sends it in the SIP Request-URI, without a leading `+`; for most carriers that is the E.164 digits. Adds a phone number from your carrier to a trunk. The number answers inbound calls with its agent (or the trunk's defaultinboundagentid) and can be used as fromphonenumber for outbound calls from agents whose telephony provider is trunk. A number can be live on only one trunk on Bolna at a time; adding one that is already on a trunk returns 409 numbertaken.

    POST /trunk/trunks/{trunk_id}/numbers

  • Write

    Assign agent to SIP trunk number

    Set or clear the agent that answers inbound calls to a SIP trunk number via PATCH /trunk/numbers/{number_id}, with the trunk default as fallback. > [!WARNING] > > An empty body clears the number's agent, the same as `{"agent_id": null}`. Calls to a number with no agent go to the trunk's `default_inbound_agent_id`, and are refused when that is not set either. Assigns the agent that answers inbound calls to a trunk number, or clears it with "agentid": null. A number without an agent is answered by its trunk's defaultinboundagentid. When neither is set, inbound calls to the number are refused with SIP 404. agentid is the only field this endpoint changes, and omitting it clears the assignment just as null does.

    PATCH /trunk/numbers/{number_id}

  • Write

    Create SIP trunk

    Create a SIP trunk to your own carrier via POST /trunk/trunks, with gateways for outbound calls and carrier IPs for inbound calls. > [!NOTE] > > This endpoint returns `200`, not `201`. Send the carrier's credentials only if it challenges Bolna's outbound calls; a carrier that authenticates Bolna by IP needs Bolna's signalling IPs from `GET /trunk/pop` on its allowlist instead. Creates a SIP trunk to your carrier. Gateways (where outbound calls are sent) and carrier IPs (the addresses inbound calls are accepted from) can be set here or added later. Numbers are added after the trunk exists, with the Add number API. Carrier IPs are loaded into Bolna's SIP edge when the trunk is created, normally before the response returns. The carrier password is stored encrypted and is never returned.

    POST /trunk/trunks

  • Write

    Update SIP trunk

    Change a SIP trunk's settings via PATCH /trunk/trunks/{trunk_id}. Only fields you send change; gateways, carrier IPs and numbers have their own endpoints. > [!NOTE] > > To change a gateway or a carrier IP, remove it and add the new one. To change which agent answers a number, use Assign agent to number. Updates a trunk's settings. Only the fields you send change. Gateways, carrier IPs and numbers have their own endpoints and cannot be sent here. description, preset and defaultinboundagentid can be cleared with null. The carrier credentials are set or cleared as a pair: send both authusername and authpassword, or both as null. Every other field rejects null. Setting isactive or inboundenabled to false withdraws the trunk's carrier IPs from Bolna's SIP edge, so its carrier's inbound calls are refused unless another inbound trunk lists the same addresses.

    PATCH /trunk/trunks/{trunk_id}

  • Write

    Add a custom TTS voice

    Register a voice from your own OpenAI-compatible text-to-speech server so Bolna voice agents can speak with it. Add a custom TTS voice

    POST /user/tts/custom

  • Write

    Add a new custom LLM model

    Add your own custom Large Language Model to Bolna via API and select it as the LLM for your Bolna voice AI agents. Add a custom LLM Model

    POST /user/model/custom

  • Write

    Submit violation

    Submit a violation along with an evidence file (e.g., a screenshot or document). This endpoint updates the violation status and attaches the uploaded file. Submit a violation with an associated file (e.g., screenshot or evidence image).

    POST /violations/submit

  • Write

    Abort workflow campaign

    Abort a campaign. Terminal: every execution stops before its next external action and the campaign cannot be resumed. Aborts a campaign. Terminal — every execution stops before its next external action and cannot be resumed.

    POST /workflow-campaigns/{campaign_id}:abort

  • Write

    Create workflow campaign

    Create a campaign that pins one published version of a workflow. Pass version null to pin the latest published version. > [!NOTE] > > The version pin is resolved at creation time and is immutable afterwards — publishing a newer version later never changes what this campaign runs. Creates a campaign in draft status. A campaign pins one published version of one workflow at creation time — version null pins the latest published version — and the pin is immutable afterwards.

    POST /workflow-campaigns

  • Write

    Pause workflow campaign

    Pause a running campaign. No new work starts; executions waiting on timers hold at their next dispatch until you resume. Pauses a scheduled or running campaign. No new work starts; an execution already waiting on a timer holds at its next dispatch and resumes with the campaign.

    POST /workflow-campaigns/{campaign_id}:pause

  • Write

    Resume workflow campaign

    Resume a paused workflow campaign via POST; held executions continue from the step where they paused rather than restarting from the beginning. Resumes a paused campaign.

    POST /workflow-campaigns/{campaign_id}:resume

  • Write

    Start workflow campaign

    Start dialing a campaign's pending entries. Requires at least one pending entry; repeating the call is a no-op. > [!WARNING] > > If the pinned definition contains an agent node, starting the campaign places real calls to every pending entry. Starts dialing a batch campaign's pending entries. The campaign must be draft or scheduled and hold at least one pending entry. Idempotent — repeating the call is a no-op.

    POST /workflow-campaigns/{campaign_id}:start

  • Write

    Upload campaign entries

    Bulk-upload contacts as CSV rows or a JSON array. Rows are validated individually, with per-row failures reported alongside the accepted count. > [!NOTE] > > Validation happens in two stages. First a whole-upload shape check: every column must be a system field (`reference_id`, `mobile_number`, `name`, `email`) or a field the pinned version's start node declares — otherwise the entire upload is rejected with `422 unknown_field` or `missing_required_field` and nothing is persisted. Then each row is validated individually: bad rows land in `failures` with a code (`invalid_phone`, `invalid_field_type`, `missing_required_value`, ...) while good rows are accepted. > [!NOTE] > > Re-uploading a row whose earlier version failed validation replaces it in place — such rows are counted in both `accepted` and `corrected`. Fetch the expected header with the CSV template endpoint. Uploads are capped at 32 MB and 150,000 rows. Bulk-uploads contacts as CSV rows or a JSON array. Columns must be system fields (referenceid, mobilenumber, name, email) or fields the pinned version's start node declares — an undeclared column rejects the whole upload with 422 unknownfield before anything is persisted. Rows are then validated individually; per-row failures land in the response's failures array while valid rows are accepted.

    POST /workflow-campaigns/{campaign_id}/entries

  • Write

    Resend execution webhook

    Send a finished execution's webhook again, to the workflow's current webhook URL, with the payload it originally carried. Sends a finished execution's webhook again, to the workflow's current webhook URL and headers. Use it to recover a webhook your server missed, or to redeliver after fixing the destination. The payload is the one originally sent, occurredat included, so a handler that keys on executionid treats it as a redelivery. The request is queued and delivered the same way as the original; the response confirms it was queued, not that your server accepted it.

    POST /workflow-executions/{execution_id}/webhook:resend

  • Write

    Test workflow webhook

    Send one sample execution webhook to the workflow's configured destination and see exactly what your server did with it. Sends one sample execution webhook to the workflow's configured settings.webhook.url, with its headers, and reports what your server did with it, so you can verify the destination before running real contacts. The sample is built from this workflow's own latest published graph — it walks the first branch of each node from the start node to an end node — so it carries your node ids and your extraction field names, in exactly the shape a real execution sends. Nothing is queued, no execution is created, and redirects are not followed.

    POST /workflows/{workflow_id}/webhook:test

  • Write

    Create workflow

    Create a new workflow via POST /workflows, starting an empty draft at revision 0 ready to receive a saved, validated, and published definition. > [!NOTE] > > The new workflow's draft starts at revision `0`. Save a definition with the Save Draft API, then validate and publish it before running contacts. Creates a new workflow with an empty draft at revision 0. Save a definition with the Save Draft API, then validate and publish it.

    POST /workflows

  • Write

    Publish workflow

    Validate the current draft and freeze it via POST as an immutable published version that campaigns and run requests execute against. > [!NOTE] > > Publishing freezes the current draft as a new version and opens a fresh draft at revision `0`. Campaigns pin a specific published version, so publishing again never changes a campaign already running. > [!NOTE] > > For `extraction` nodes, the field types are filled server-side from the linked agent's dispositions at publish time — whatever `fields` you saved in the draft is ignored. Validates the draft and freezes it as an immutable published version, then opens a fresh draft at revision 0. Campaigns and single runs always execute published versions, never drafts.

    POST /workflows/{workflow_id}/publish

  • Write

    Run workflow

    Run a single contact through the latest published version of a workflow via POST, returning an execution ID you can poll for status and results. > [!NOTE] > > `reference_id` is the contact's identity within the workflow version: repeating it returns `409 duplicate_run` with the existing `execution_id`, which makes the call safely retryable. When omitted, an identity is derived from the row's content. > [!NOTE] > > Fields declared by the start node can be passed flat at the top level — exactly like CSV columns — or nested under `custom_fields`. On a name collision the flat key wins. Undeclared keys are rejected with `422 unknown_field`. Runs one contact through the workflow's latest published version. Returns an execution you can poll with the Get Execution API. Fields declared by the start node may be passed flat at the top level or nested under customfields; a flat key wins on collision.

    POST /workflows/{workflow_id}/run

  • Write

    Update workflow

    Rename a workflow or update its settings, such as the execution webhook. Settings are merged, so each change is applied on its own. Renames a workflow and/or updates its settings, such as the execution webhook. settings is a JSON merge patch (RFC 7396) onto the stored settings: keys you omit are left unchanged and null removes one. So a rename never touches the webhook, {"settings": {"webhook": {"headers": {"X-Old": null}}}} drops one header while keeping the others, and {"settings": {"webhook": null}} stops sending webhooks. The definition itself is edited through the draft endpoints.

    PATCH /workflows/{workflow_id}

  • Write

    Validate workflow

    Check the saved draft against every graph and node rule without mutating anything. Errors block publish; warnings do not. > [!NOTE] > > Validation reads the stored draft, so save your definition with the Save Draft API first. Common error codes include `unbounded_cycle` (a loop not closed through a `retry` node), `dangling_target` (a case routes to a missing node id), `unknown_agent` and `empty_cases` on the start node. Validates the saved draft without mutating anything. Issues with severity error block publish; warnings do not.

    POST /workflows/{workflow_id}/validate

  • Destructive

    Update voice AI agent (deprecated)

    Deprecated v1 endpoint to replace an agent configuration. New integrations should use the v2 Update agent API. > [!WARNING] > > These APIs have now been deprecated. > > Please use the latest **v2 APIs**. Update an agent

    PUT /agent/{agent_id}

  • Destructive

    Delete batch

    Understand how to delete a specific batch using its ID, effectively removing it from your scheduled or active batches. Delete a batch

    DELETE /batches/{batch_id}

  • Destructive

    Stop batch

    Stop a running Bolna batch by its batch ID with the Stop batch API, halting the ongoing calls in that batch calling campaign. Stop a running batch

    POST /batches/{batch_id}/stop

  • Destructive

    Stop a previously initiated voice AI call

    Learn how to stop a call when its status is `queued` or `scheduled` This API allows you to cancel pending calls before they are executed. Stop a queued or scheduled call

    POST /call/{execution_id}/stop

  • Destructive

    Delete compliance application

    Delete a phone number compliance application and its uploaded documents. Use this to resubmit an application with corrected details. Delete a phone number compliance application along with its uploaded documents.

    DELETE /compliance/{compliance_id}

  • Destructive

    Delete disposition

    Delete a disposition from your account via DELETE /dispositions/{disposition_id}. Only the owning user or an admin can delete it; the action is permanent. > [!WARNING] > > Deletion is permanent and cannot be undone. Historical call execution results that already contain this disposition's output are not affected — only future calls will stop evaluating it. Deleting a category's last disposition also deletes the category itself. Permanently delete a disposition and remove its link to any associated agents. Regular users can only delete dispositions they own (createdby matches their user ID). Admins can delete any disposition. Historical call execution results already containing this disposition's output are not affected — only future calls will stop evaluating it. Deleting a category's last disposition also deletes the category itself.

    DELETE /dispositions/{disposition_id}

  • Destructive

    Update disposition

    Update a disposition. When scoped to an agent, shared dispositions are copied before editing to protect other agents. > [!WARNING] > > A `201` response means a **new disposition ID was created**. If you're storing the disposition ID (e.g., in your own database), update your reference to the new ID returned in the response. The original `disposition_id` now belongs to other agents; your agent uses the new copy. Update an existing disposition. All fields in the request body are optional — only fields you include are changed. When agentid is provided (scoped mode), the API checks whether the disposition is exclusive to that agent: - If exclusive, it is edited in place and 200 OK is returned. - If shared, a new private copy is created for this agent and the agent is re-linked to the copy; the original disposition is unchanged and 201 Created is returned with the new ID. When agentid is not provided (unscoped mode), admins can update any disposition; non-admin users can only update dispositions they own. To move a disposition between categories, send the new categoryid (or a category name). When a move empties a category, the emptied category is deleted automatically.

    PUT /dispositions/{disposition_id}

  • Destructive

    Delete extraction category

    Delete an extraction category and all of its dispositions via DELETE /extraction-categories/{category_id}. Deletion is permanent. > [!WARNING] > > Deleting a category **deletes all of its dispositions** — the category owns them. Deletion is permanent and cannot be undone. Historical call execution results that already contain output from this category's dispositions are not affected; only future calls stop evaluating them. To keep a disposition, move it to another category first by updating it with a different `category_id`. Delete an extraction category. The category owns its dispositions, so this deletes the category and all of its dispositions, and detaches the category from the agent. Historical call execution results that already contain output from this category's dispositions are not affected — only future calls stop evaluating them.

    DELETE /extraction-categories/{category_id}

  • Destructive

    Delete knowledge base

    Remove and delete an existing knowledge base from your Bolna account maintaining your Bolna Voice AI agents up to date. Delete a knowledge base

    DELETE /knowledgebase/{rag_id}

  • Destructive

    Delete phone numbers API

    Delete a purchased phone number from your Bolna account to stop billing for it and remove it permanently from your active inventory. Delete a batch

    DELETE /phone-numbers/{phone_number_id}

  • Destructive

    Remove a provider

    Delete a previously added provider from your Bolna account with the Remove provider API, keeping your connected integrations current. Remove provider

    DELETE /providers/{provider_key_name}

  • Destructive

    Delete SIP trunk (deprecated)

    Permanently delete a SIP trunk and all associated resources including gateways, IP identifiers, and phone numbers. > [!WARNING] > > **Legacy SIP trunks (deprecated).** These `/sip-trunks` endpoints manage legacy SIP trunks. Existing legacy trunks keep working, but use the SIP trunks API for every new setup, and see Migrate to SIP trunks to move an existing trunk. Permanently delete a SIP trunk and all associated resources (gateways, IP identifiers, phone numbers)

    DELETE /sip-trunks/trunks/{trunk_id}

  • Destructive

    Remove phone number from trunk (deprecated)

    Remove a phone number from a legacy SIP trunk. If the number was mapped to an agent, that mapping is removed too. New setups use the SIP trunks API. > [!WARNING] > > **Legacy SIP trunks (deprecated).** These `/sip-trunks` endpoints manage legacy SIP trunks. Existing legacy trunks keep working, but use the SIP trunks API for every new setup, and see Migrate to SIP trunks to move an existing trunk. Remove a phone number from a SIP trunk. If the number was mapped to an agent, the mapping is also removed.

    DELETE /sip-trunks/trunks/{trunk_id}/numbers/{phone_number_id}

  • Destructive

    Deleting a sub-account

    Use Bolna APIs to delete a sub-account and their related data, ensuring proper cleanup of agents, batches, executions, and configurations. > [!WARNING] > > This deletes **ALL** the data for that sub-account's batches, executions and agents. Delete a sub-account

    DELETE /sub-accounts/{sub_account_id}

  • Destructive

    Delete SIP trunk

    Delete a SIP trunk with its gateways, carrier IPs and numbers via DELETE /trunk/trunks/{trunk_id}; inbound and outbound calls on it stop. > [!WARNING] > > Deleting a trunk removes its gateways, carrier IPs and numbers with it. Inbound calls to its numbers are refused, and agents can no longer place calls from them. Add the numbers to another trunk to keep using them. Deletes a trunk together with its gateways, carrier IPs and numbers. Its carrier IPs are withdrawn from Bolna's SIP edge, so inbound calls from that carrier are refused unless another trunk lists the same addresses, and outbound calls from its numbers fail. The response is the deleted trunk's settings with isdeleted: true. It carries no gateways, ipacls, numbers, health or activecalls.

    DELETE /trunk/trunks/{trunk_id}

  • Destructive

    Remove carrier IP from SIP trunk

    Stop accepting inbound calls from a carrier address on a SIP trunk via DELETE /trunk/trunks/{trunk_id}/ip-acls/{acl_id}. Removes a carrier IP from a trunk. Bolna's SIP edge stops accepting this trunk's inbound calls from it, normally before the response returns.

    DELETE /trunk/trunks/{trunk_id}/ip-acls/{acl_id}

  • Destructive

    Remove gateway from SIP trunk

    Remove a gateway from a SIP trunk via DELETE /trunk/trunks/{trunk_id}/gateways/{gateway_id}; outbound calls stop using it. Removes a gateway from a trunk. Outbound calls stop using it immediately; a trunk with no gateways cannot place outbound calls.

    DELETE /trunk/trunks/{trunk_id}/gateways/{gateway_id}

  • Destructive

    Remove number from SIP trunk

    Remove a phone number from a SIP trunk via DELETE /trunk/trunks/{trunk_id}/numbers/{number_id}; inbound calls to it are refused. Removes a number from a trunk. Inbound calls to it are refused and it can no longer be used as a caller ID. The number can be added to a trunk again afterwards.

    DELETE /trunk/trunks/{trunk_id}/numbers/{number_id}

  • Destructive

    Delete a custom TTS voice

    Delete a custom text-to-speech voice and its stored endpoint key from Bolna. A voice still selected on an agent cannot be deleted. Delete a custom TTS voice along with its stored key

    DELETE /user/tts/custom/{custom_tts_id}

  • Destructive

    Delete a custom LLM model

    Delete a custom LLM and its stored endpoint key from your Bolna account. A model still selected on an agent cannot be deleted. Delete a custom LLM Model along with its stored key

    DELETE /user/model/custom/{model_id}

  • Destructive

    Delete workflow campaign

    Delete a workflow campaign via DELETE; only allowed while the campaign is still a draft with no uploaded entries and no executions. Deletes a campaign. Only legal on a draft campaign with no entries and no executions.

    DELETE /workflow-campaigns/{campaign_id}

  • Destructive

    Cancel workflow execution

    Stop one contact's execution before its next external action. Canceling an already-terminal execution is a no-op. Stops one execution before its next external action. Cancelling an already-terminal execution is a no-op that returns its current status.

    POST /workflow-executions/{execution_id}:cancel

  • Destructive

    Delete workflow

    Soft-delete a workflow via DELETE /workflows/{workflow_id}; existing campaigns and past executions are preserved for reporting purposes. Soft-deletes a workflow. Existing campaigns and executions are preserved for reporting.

    DELETE /workflows/{workflow_id}

  • Destructive

    Save workflow draft

    Save the draft definition using an optimistic-concurrency revision token, so concurrent editors never silently overwrite each other. > [!NOTE] > > `expected_revision` is a compare-and-set token. A fresh workflow's draft is at revision `0`, each save returns the next revision, and publishing resets the new draft to `0`. If your value is stale the save fails with `409 revision_conflict` carrying `current_revision` — re-read the draft and retry. > [!NOTE] > > Draft saves accept any well-formed JSON object up to 512 KB. Graph rules (reachability, cycles, node configs) are checked by Validate and enforced at Publish. See Nodes and Conditions and variables for the definition schema. Saves the draft definition. expectedrevision is a compare-and-set token — send the revision you last read; a stale value returns 409 revisionconflict with the currentrevision. Drafts store any well-formed JSON object; graph validation happens at validate and publish.

    PUT /workflows/{workflow_id}/draft

Bolna v2

  • Read

    Retrieve voice AI agent details

    Retrieve a Bolna voice AI agent's details with the v2 API, including its configuration, status and tasks, using the agent ID. Retrieve an agent

    GET /v2/agent/{agent_id}

  • Read

    List all voice AI agents

    List all Voice AI agents under your account, along with their names, statuses, and creation dates, using Bolna APIs. List all agents

    GET /v2/agent/all

  • Read

    Get pronunciation status

    Check whether a Bolna voice agent's pronunciation word lists are applied to calls: active, pending or failed. Check whether an agent's pronunciation word lists are applied to calls. After you save a list it is pending for a few seconds, then active.

    GET /v2/agent/{agent_id}/pronunciation-dictionary-status

  • Read

    List batch executions API (v2)

    Retrieve executions from a batch with pagination support, providing detailed information on each call's outcome and metrics. Retrieve all executions from a batch with pagination support

    GET /v2/batches/{batch_id}/executions

  • Read

    Get all voice AI agent executions

    Retrieve all executions performed by a specific agent using Bolna APIs. This endpoint provides a comprehensive history of the agent's calls and conversations. > [!WARNING] > > The `from` and `to` query parameters are **required** to filter executions by date. Retrieve all executions by an agent

    GET /v2/agent/{agent_id}/executions

  • Write

    Create voice AI agent

    Learn how to create new agents with Bolna APIs, enabling customized tasks, prompts, and configurations for Bolna voice AI agents. > [!TIP] > > The quickest path is creating an agent in the dashboard (Auto Build) and copying its ID. Use the API when you need to programmatically provision agents at scale or integrate agent creation into your deployment pipeline. > [!NOTE] > > The LLM `provider` is not checked against a fixed list at creation time, unlike the transcriber and > synthesizer. An unroutable provider or model is accepted by `POST /v2/agent` and only fails once a > call runs, so verify it against the table above. > [!WARNING] > > `language` takes a plain ISO 639-1 code for every provider, including Sarvam: send `"language": "hi"`. > `"hi-IN"` is rejected, even though Sarvam's own API uses locale codes, because Bolna resolves them for you. > [!WARNING] > > **Keyword weights are not carried through.** `keywords` accepts the dashboard's `word:boost` form, but > the boost is stripped before storage: `"Bolna:100,Acme:50,Zeta"` is persisted as `"Bolna,Acme,Zeta"`. > The terms themselves still apply. Deepgram sends them as `keyterm` on `nova-3` and Flux and as > `keywords` on `nova-2` and earlier, and Sarvam reads them on `saaras:v4` only. See > provider support for every provider > that reads this field and its limits. > [!WARNING] > > **`language` inside `provider_config` is required for most providers:** `cartesia`, `sarvam`, > `smallest`, `rime`, `azuretts`, `gemini`, `soniox` and `polly`. Leaving it out fails with > `400 Tools Config > Voice > Language: This field is required`, even though the agent already has a > transcriber language. `elevenlabs`, `deepgram` and `openai` do not take it at all, and it is optional > on `maya` (defaults to `en`) and `kalpa`. > [!TIP] > > To mix providers per language in one agent, for example Deepgram plus Cartesia for English and > ElevenLabs plus Sarvam for Hindi, use `multilingual_config`. See the > Multilingual Config Reference. > [!NOTE] > > To replace the transcriber, LLM and synthesizer with a single realtime model, set `tools_config.s2s` > and leave the other three `null`. See Speech-to-Speech. Creates a new agent

    POST /v2/agent

  • Write

    Patch update to voice AI agent

    Partially update a Bolna voice AI agent: name, welcome message, webhook URL, voice, pronunciation words, calling guardrails, telephony provider and prompts. > [!TIP] > > Use `PATCH` for small, targeted edits (renaming an agent, swapping a voice, updating a webhook URL). Use `PUT` when you need to rewrite tasks, toolchains, or the full prompt structure. > [!NOTE] > > All agent-config attributes go inside the `agent_config` object. `agent_prompts` is a top-level key, a sibling of `agent_config`. > [!NOTE] > > Hours use 24-hour format: `0` = midnight, `9` = 9 AM, `17` = 5 PM, `21` = 9 PM. See the Calling Guardrails guide for rescheduling behavior and regional calling regulations. > [!NOTE] > > An agent on `trunk` places outbound calls from your trunk's numbers. To answer inbound calls, assign the agent to a trunk number with `PATCH /trunk/numbers/{number_id}`. See Receive calls on a SIP trunk. > **Full update (PUT)** > > Replace the entire agent configuration, tasks, and prompts. > **Calling guardrails** > > Control outbound call timing and rescheduling. > **Set inbound agent** > > Map a phone number to an agent for inbound calls. > **Webhooks** > > Receive call results without polling. Patch update an agent

    PATCH /v2/agent/{agent_id}

  • Write

    Test dispositions

    Run every disposition linked to an agent against a sample transcript via POST to preview grouped extraction results before making live calls. Run all dispositions linked to the specified agent against a provided transcript and return the grouped results. Useful for validating your disposition setup before going live.

    POST /v2/agent/{agent_id}/dispositions/test

  • Destructive

    Delete voice AI agent

    Use Bolna APIs to delete agents and their related data, ensuring proper cleanup of batches, executions, and configurations. > [!WARNING] > > This deletes **ALL** agent data including all batches, all executions, etc. Delete an agent

    DELETE /v2/agent/{agent_id}

  • Destructive

    Stop agent queued calls

    Use Bolna APIs to stop all queued calls for a specific agent, preventing any pending calls from being executed. > [!WARNING] > > This stops **ALL** the queued calls for a given agent. Stop all queued calls for a given agentid

    POST /v2/agent/{agent_id}/stop

  • Destructive

    Update voice AI agent

    Update agent configurations, tasks, and prompts to refine behavior and capabilities using Bolna Voice AI agent APIs. Update an agent

    PUT /v2/agent/{agent_id}

See How connections work for access and permissions, or browse all integrations.