GO TO KI

Showing 25 of 54 from the live probe.

• List Agents

  List all voice agents that belong to the authenticated user. Returns agent id, title, created date, last call date, call count, minutes used, license fee, and cost per minute.

• Get Agent

  Get full details for a single agent by its ID, including configuration, system prompt, greeting message, phone routing, advanced settings, and embed config.

• Create Agent

  Create a new voice agent. Provide at minimum a title. Agents have separate prompts and greetings for inbound and outbound calls: inbound_system_prompt / outbound_system_prompt are the instructions the agent follows, and inbound_greeting_message / outbound_greeting_message are the opening lines spoken at the start of a call. The legacy single 'system_prompt' / 'greeting_message' fields are deprecated — do not use them. If you only have one prompt/greeting, set it on both the inbound and outbound

• Update Agent

  Update an existing agent. Pass an 'updates' dict with only the fields to change. For prompts and greetings use the inbound/outbound fields — inbound_system_prompt, outbound_system_prompt, inbound_greeting_message, outbound_greeting_message. The legacy 'system_prompt' and 'greeting_message' fields are deprecated; do not write to them. Other updatable fields include title, description, voicemail_message, voicemail_detection_enabled, voicemail_detection_prompt, evaluation_prompt, timezone, phone ro

• Delete Agent

  Permanently delete an agent by its ID.

• List Prompt Versions

  List the prompt version history for an agent. Returns each version with its timestamp so you can review or restore a prior prompt.

• Get Agent Webhook

  Get the webhook configuration for an agent (the URL that Gotoki will POST call events to).

• Set Agent Webhook

  Set or update the webhook URL for an agent.

• List Agent Variables

  List all variables ({{...}} placeholders) defined on an agent. Variables are used to inject dynamic values into calls.

• Get Agent Variable

  Get a single variable by its ID for a given agent.

• Create Agent Variable

  Create a new variable ({{...}} placeholder) on an agent. Provide 'name' and optionally a 'default_value'. template_id is optional — when omitted, the default static-variable template is used (same as the dashboard's standard variable creation).

• Update Agent Variable

  Update a static variable's name and/or default value. Only static (and custom) variables are editable; Pipedrive standard variables are read-only. Provide the new 'name' and/or 'default_value' — omit a field to leave it unchanged.

• Delete Agent Variable

  Delete a variable by its ID.

• List Evaluation Labels

  List all evaluation labels for an agent. Labels classify calls (e.g. 'Interested', 'Not Interested') based on rules. Each label carries two classification fields - read them instead of guessing from the label name, which is written in the customer's own language. 'outcome_polarity' ('positive' | 'neutral' | 'negative') is what reporting counts as a conversion. 'reach_status' ('reached' | 'not_reached' | 'unknown') is whether a person was actually on the line. They are independent of each other a

• Create Evaluation Label

  Create an evaluation label for an agent. Provide label_data with keys: name, description, classification_rule, and optionally outcome_polarity ('positive' | 'neutral' | 'negative', defaults to 'neutral') and reach_status ('reached' | 'not_reached' | 'unknown', defaults to 'unknown'). Set outcome_polarity to 'positive' only for outcomes that should count as a conversion, and reach_status to 'reached' only when the label means a person was on the line - voicemail, IVR and bot pickups are 'not_reac

• Update Evaluation Label

  Update an evaluation label. Provide only the fields to change. Settable keys: name, description, classification_rule, sort_order, outcome_polarity ('positive' | 'neutral' | 'negative'), reach_status ('reached' | 'not_reached' | 'unknown'). Changing either re-scores every past call carrying this label in campaign reporting - both are read live, not stamped onto the call - and changes nothing about retries or call status.

• Delete Evaluation Label

  Delete an evaluation label by its ID.

• List Available Tools

  List all available tools on the platform that can be assigned to an agent. Includes tools like Redirect Call, Custom Function, Outlook Calendar, etc. Optionally filter by search term or category.

• List Agent Tools

  List all tools currently assigned to an agent, along with their configuration.

• Assign Tool To Agent

  Assign a tool to an agent by tool ID. Use list_available_tools to find the tool_id first.

• Unassign Tool From Agent

  Remove (unassign) a tool from an agent by tool ID.

• Get Agent Tool Config

  Get the current configuration for a specific tool assigned to an agent.

• Update Agent Tool Config

  Update the configuration for a tool assigned to an agent. config is a list of field objects, each with keys: type, required, title, api_key, value, description.

• Get Evaluation Prompt

  Get the evaluation prompt for an agent. This is the context used by the AI to evaluate and label calls.

• Set Evaluation Prompt

  Set or update the evaluation prompt for an agent. The evaluation prompt gives the AI context to classify calls with evaluation labels.