Changelog

​

Show source URLs in responses

​

Async functions and API tools

​

Tool messages

1. Start — Message delivered when the tool is initiated
2. Complete — Message delivered when the tool finishes successfully
3. Failed — Message delivered if the tool encounters an error
4. Delayed — Message delivered if the tool takes longer than a specified duration (default: 3000ms, configurable)

​

GPT 5.2

​

Voice mode in web widget

​

Native web search tool

• Toggle on the web search tool in any agent to answer questions that need live data (news, prices, schedules, etc.).
• Configure search prompts and guardrails so the agent only pulls what you want it to.
• Results are summarized and grounded back into the conversation for more accurate, up-to-date answers.

​

Telnyx telephony integration

​

Native support for keypad input (DTMF)

• Keypad input is off by default and can be turned on from Settings/Behaviour/Voice.
• When on in project settings, keypad input can be turned off at the step level via the “Listen for other triggers” toggle.
• View full documentation here

​

Knowledge base metadata

1. Adding metadata on knowledge import

2. Dynamically, or statically apply metadata at runtime

​

Built-in time variables

​

Deepgram Flux ASR model

• Smart turn detection — Knows when speakers finish talking
• Ultra-low latency — ~260ms end-of-turn detection
• Early LLM responses — EagerEndOfTurn events for faster replies
• Turn-based transcripts — Clean conversation structure
• Natural interruptions — Built-in barge-in handling
• Nova-3 accuracy — Best-in-class transcription quality

​

Sync audio and text output

​

Transcript inactivity timeout

​

Priority processing for Open AI models

​

MCP tools

• 🔌 Connect to MCP servers in just a few clicks
• 📥 Add MCP server tools to your agents
• 🔄 Sync MCP servers to stay up-to-date

​

Call forwarding tool in agents

• 📞 Seamlessly transfer callers to the right person or agent
• 🔀 Supports phone numbers, SIP addresses, and extensions
• 🛠️ Configure forwarding directly in your agent’s tools

​

Control reasoning effort for supporting GPT models

​

Shareable links now match your AI agent

• 🔗 Sharable links now mirror your actual AI agent
• 🛠️ Environment-specific links (dev, staging, production)
• 🎨 Customize the look and feel via the Interfaces tab
• 🔒 Optional password protection for secure sharing

​

Staging environment added

• New staging environment for pre-production testing
• Publish across dev → staging → production
• More control and confidence in deployment flows
• Override secrets per environment for greater flexibility

​

Duplicating projects now clones knowledge base

​

Control saving of empty transcripts

​

Save input variables in tool calls

​

GPT-5 models

​

Double-click to open agent step

​

Tool step

​

New analytics API

​

Custom query control & chunk limit for knowledge base tool

​

Better transcripts. Custom evaluations. Better AI agents.

• Transcripts, reimagined – Replay calls, debug step-by-step, filter with precision, and visualize user actions like button clicks — all in a faster, cleaner UI.
• Evaluations, your way – Define what “good” looks like with customizable evaluation templates, multiple scoring types (rating, binary, text), auto-run support, and performance tracking over time.

1. Call recordings – Replay conversations to hear how your agent performs in the real world
2. Robust debug logs – Trace agent decisions step-by-step
3. Granular filtering – Slice data by time, user ID, evaluation result, and more
4. Button click visualization – See exactly where users clicked in the conversation
5. Cleaner UI – Faster load times, more usable data

1. ⭐ Rating evals (e.g. 1–5)
2. ✅ Binary evals (Pass/Fail)
3. 📝 Text evals (open-ended notes)

• Batch or auto-run – Evaluate hundreds of transcripts in a few clicks, or automatically as they come in
• Analytics & logs – See detailed results per message or overall trends over time

• We’ve release a brand new Evaluations API
• We’ve release a new Transcripts API The legacy Transcripts API is still supported and currently has no deprecation timeline

​

Gmail tools: let your AI agents send emails

​

Call forwarding step

• ✅ Route to phone numbers
• ✅ Include optional extensions
• ✅ Support for SIP addresses

​

Hubspot tools

​

SMS messaging with Twilio tools

​

Create AI agents instantly — from just a prompt

1. Prompt-to-project generation – go from idea to working prototype in seconds
2. Prompt-to-workflow generation – describe a capability, get a complete workflow
3. Prompt-to-component generation – create specific tools and logic on the fly

​

Vonage integration for telephony

​

Smarter knowledge base building with LLM chunking strategies

​

Make.com tool

​

Airtable tools

​

Agents can now automatically use buttons, cards, and carousels to enrich conversations

​

[Deprecation] Dialog Manager API Logs

​

New Speech-to-Text Providers

• Added Cartesia’s Ink-Whisper STT model This leverages OpenAI’s whisper model, upgraded for realtime call performance Expanded language support and selection
• Added AssemblyAI Universal STT model Advanced tuning options
• Added specific model selection for Deepgram STT Nova-2, Nova-3, and Nova-3 Medical

​

Google Sheets tools

​

Cartesia voices

​

Added tool usage to project analytics

• Integration tools
• API tools
• Function tools

​

New workspace dashboard

• We’ve made updates to the workspace dashboard to make it easier to organize your projects, and manage your workspace.
• We’ve added folders, to further organize your projects. Note, if you previously used the Kanban view (deprecated), we’ve automatically converted swim-lanes into folders.
• Home tab (coming soon)
• Community tab (coming soon)
• Tutorials tab (coming soon)

​

New navigation

​

Claude Opus 4 & Sonnet 4

​

Gemini 2.5 Pro & 2.5 Flash

​

Security Settings for Widget

• Ability to whitelist domains
• Ability to have a custom privacy message before users engage with your AI agent
• Ability to not save transcripts

​

Generative No Reply

​

API Raw Content-Type select

​

Rimelabs Arcana Voices

​

Krisp Noise Cancellation

​

Salesforce tools

​

Zendesk tools

​

Voice Keywords / Multilingual Speech-to-text

​

Introducing Voiceflow Credits: A simpler way to track usage

• Simplified Measurement: One unified credit system for all actions (calls, messages, LLM responses, TTS)
• Predictable Costs: Clear pricing tiers that make budget planning straightforward
• Transparent Usage: Detailed visibility into exactly how your credits are being consumed
• Developer-Friendly: Messages only count toward credits when your agent is used in production—not when developing in-app or using shareable prototypes

• View your total available and used credits
• Track usage across all agents or drill down into specific ones
• Monitor editor and agent allocation
• Analyze usage patterns over time

• What are Voiceflow Credits? - A comprehensive guide to understanding how credits work
• Introducing Voiceflow Credits - Learn about the philosophy behind the change and how it benefits you
• Credit Calculator - Estimate your credit needs based on your specific usage patterns

• Annual plans now offer a 10% discount (previously 20%)
• Editor seats now cost $50/month with no restrictions (a price reduction)
• Business plan (formerly Teams) base tier increases from $125 to $150

​

Support for OpenAI o3 and o4 mini

• Support for OpenAI o3 and o4 mini

​

Support for GPT 4.1 models

• Support for GPT 4.1, GPT 4.1 mini and GPT 4.1 nano

​

Minor Updates / Fixes

• Voice Widget latency decreased by up to 750ms
• Voice Widget now streams with more consistent linear16@16kHz encoding

• Reset memory when a new conversation is launched (launch request)
• Global no reply not working on Agent steps
• The maximum allowed length for {userID} in the Dialog API will be set to 128 characters, effective April 18th
• Unable to remove webhook URLs
• Analytics visualization UI bug
• Voice Widget always setting userID to test on transcripts
• Chat Widget no audio output after page reload
• Export variables fails when project has large number of variables

​

Call Events Webhook

• New support added to subscribe to call events via webhook, for both twilio IVR and voice widget projects Call Events Documentation Webhook system is capable of broadcasting additional events in the future

​

Streaming Text in Chat Widget Now Optional

• Added option to disable streaming text in chat widget Stream text can now be turned off in the Modality & interface settings When disabled, the full agent response will be displayed at once instead of being streamed out. Useful for situations where streaming longer messages is not desired

​

Max Memory Turns Setting

​

Agent Step, Structured Output Improvements, Gemini 2.0 Flash

• Intelligent Prompting: Craft detailed instructions to guide your agent’s behavior and responses.
• Function Integration: Connect your agent with external services to retrieve and update data.
• Conversation Paths: Define specific flows for your agent to follow based on user intent.
• Knowledge Base Integration: Enable your agent to automatically search your knowledge base for relevant information.

• Arrays and Nested Arrays: You can now define arrays and nested arrays in your output structure.
• Nested Objects: Structured output now supports nested objects, allowing for more complex data structures.

​

Variable Handling Update: Consistent Behavior for Undefined Values

• Updated Voiceflow variable handling for consistency in previously undefined behavior: Variables can be any JavaScript object that is JSON serializable. Any variable set to undefined will be saved as null (this conversion happens at the end of the step, so it does not affect the internal workings of JavaScript steps and functions). Functions can now return null (rather than throwing an error) and can no longer return undefined (which could cause agents to crash). Functions that attempt to return undefined will now return null (to ensure backwards compatibility).

​

New Analytics Dashboard: Gain Deeper Insights into Your Agent’s Performance

• Tokens Usage: Monitor AI token consumption over time across all models, giving you a clear picture of your agent’s token utilization.
• Total Interactions: Keep track of the total number of interactions (requests) between users and your agent over time, providing insights into engagement levels.
• Latency Monitoring: Measure the average response time of your agent to ensure optimal performance and identify any potential bottlenecks.
• Total Call Minutes: Gain visibility into the cumulative duration of voice calls in minutes, helping you understand the volume and significance of voice interactions.
• Unique Users: Identify the count of distinct users interacting with your agent over time, allowing you to track adoption and growth.
• KB Documents Usage: Analyze the frequency of knowledge base document access, with the ability to toggle between ascending and descending order to identify the most or least used documents.
• Intents Usage: Visualize the distribution of triggered intents, with sorting options to analyze intent frequency and identify popular or underutilized intents.
• Functions Usage: Monitor the frequency of function calls, their success/failure and latency, with sorting capabilities to identify the most or least used functions and optimize your agent’s functionality.
• Prompts Usage: Gain insights into the usage frequency of agent prompts, with the ability to toggle between ascending and descending order to analyze prompt utilization and effectiveness.

​

New Models, Function Editor Enhancements, and Call Recording

• Deepseek R1: Harness the potential of Deepseek’s R1 model for enhanced natural language understanding and generation.
• Llama 3.1 Instant: Experience lightning-fast responses with the Llama 3.1 Instant model.
• Llama 3.2: Leverage the advanced capabilities of Llama 3.2

• Modal View: You can now open the Function Editor as a modal directly from the canvas. This allows you to make quick updates and navigate between your functions and the canvas seamlessly.
• Snippets: We’ve introduced a new snippets feature that enables you to insert pre-written code snippets for common concepts in Voiceflow functions.

• Automatic Call Recording: All phone calls between users and your AI agent will now be automatically recorded.
• Twilio Integration: The call recordings will be accessible directly in your Twilio account for easy review and management.

​

Retrieval-Augmented Generation (RAG) for Intent Recognition

​

Expanding the Possibilities of User Interaction with Voice

• Launcher Style: Select a launcher style that complements your site’s design.
• Color Palette: Choose colors that match your brand guidelines.
• Font Family: Pick a font that aligns with your website’s typography.

• Automated Speech Recognition: Our platform uses advanced STT technology from Deepgram to accurately transcribe user speech in real-time.
• Organic Text-to-Speech: We’ve integrated with leading providers like 11 Labs and Rime to offer a variety of natural-sounding voices that bring AI agents to life.

​

AI Fallback

1. Access your agent
2. Navigate to agent settings
3. Set your preferred fallback model by provider

• Minimizes service disruptions during model outages
• Maintains consistent AI performance
• Reduces operational impact of provider issues
• Ensures business continuity

• Identifies the next available model in your sequence
• Switches ongoing operations to the backup model
• Returns to the primary model once issues are resolved

​

New Features: Structured Outputs and Variable Pathing

• In a prompt step, enable the new “JSON Output” option to specify the structure of the LLM’s response.
• Today, Structured Outputs support the following data types: String Number Boolean Integer Enum
• Support for arrays and nested objects is planned for the near future.
• Structured Outputs are available with gpt-4o-mini and gpt-4o models.

• Store an entire object in a single variable, then access its properties using dot notation (e.g. user.name, user.email).
• Capture Structured Output responses or API results as objects.
• Use object properties directly in conditions, messages, and other steps.
• Reduce the need for multiple variables to represent a single entity.

• Define precise data requirements for LLMs to provide relevant information
• Capture responses as feature-rich objects in a single step
• Access and manipulate object properties throughout your project
• Streamline your project’s design while expanding its capabilities

​

Voiceflow Telephony

• Import existing Twilio phone numbers directly into Voiceflow
• Associate phone numbers with specific agents
• Configure separate numbers for development and production environments
• Test different versions of your agent against different phone numbers

• Dramatically reduced response times
• Near real-time agent reactions
• Optimized voice processing pipeline

• High-accuracy transcription
• Low-latency processing
• Support for over 20 languages

• Programmatically initiate calls to any phone number
• Test outbound calls directly from the Voiceflow interface
• Integrate outbound calling into your existing workflows

• Premium text-to-speech voices from industry leaders, such as: ElevenLabs Rime Google
• Support for advanced telephony features through custom actions: Call forwarding DTMF handling Interruption behaviour

• Background audio customization
• Audio cue configuration

• Interruption threshold controls
• Utterance end detection
• Response timing optimization
• User input acceptance timing

• Enhanced call analytics and reporting
• Additional voice customization options

​

New AI-Native Webchat

• Streaming Text Support: Experience real-time message generation with character-by-word streaming, creating a more engaging and dynamic conversation flow. Users can see responses being crafted in real-time, similar to popular AI chat interfaces.
• AI Disclaimers: Built-in support for displaying AI disclosure messages and customizable AI usage notifications to maintain transparency with your users.

• Widget: Traditional chat window that appears in the corner of your website
• Popover: Full-screen chat experience that overlays your content
• Embed: Seamlessly integrate the chat interface directly into your webpage layout

• Color System: Expanded colour palette support with primary, secondary, and accent colour definitions
• Typography: Custom font family support
• Launcher Variations: Classic bubble launcher with customizable icons Button-style launcher with text support

• Chat Persistence: Now configured through the snippet rather than UI settings.
• Custom CSS: Maintained compatibility with most existing class names.
• Proactive Messages: Temporarily unavailable in this release, with support coming soon

​

Function libraries, starter templates and ElevenLabs support

​

Important Update: Deprecation of AI Response and AI Set Steps

• On February 4th, 2025, the AI Response and AI Set steps will be disabled from the step toolbar in the Voiceflow interface to encourage users to move away of these deprecated steps. Existing steps will remain untouched and will continue working as per normal.
• On June 3rd, 2025, these steps will no longer be supported. Any existing projects using these steps will need to be migrated to the new Prompt and Set steps. We will be sending out additional communication in advance to the sunset date.

• Centralized prompt management:The Prompt CMS serves as a hub for all your prompts, making it easy to create, edit, and reuse them across your projects.
• Advanced prompt configuration: Leverage system prompts, message pairs, conversation history, and variables to craft highly contextual and dynamic responses.
• Seamless integration: The Prompt step allows you to bring your prompts directly into your conversation flows, while the Set step lets you assign prompt outputs to variables for enhanced logic and control.
• Continued innovation: We are committed to expanding the capabilities of these new features, with exciting updates planned for the near future.

​

API Step V2

type CodeText = (
  | string
  | {
      variableID: string;
    }
  | {
      entityID: string;
    }
)[];

interface MarkupSpan {
  text: Markup;
  attributes?: Record<string, unknown> | undefined;
}

type Markup = (
  | string
  | {
      variableID: string;
    }
  | {
      entityID: string;
    }
  | MarkupSpan
)[];

type ApiV2Node = {
  type: "api-v2";
  data: {
    name: string;
    url?: Markup | null | undefined;
    headers?: Array<{ id: string; key: string; value: Markup }> | undefined;
    httpMethod: "get" | "post" | "put" | "patch" | "delete";
    queryParameters?: Array<{ id: string; key: string; value: Markup }> | undefined;
    responseMappings?: Array<{ id: string; path: string; variableID: string }> | undefined;
    body?:
      | {
          type: "form-data";
          formData: Array<{ id: string; key: string; value: Markup }>;
        }
      | {
          type: "params";
          params: Array<{ id: string; key: string; value: Markup }>;
        }
      | {
          type: "raw-input";
          content: CodeText;
        }
      | null
      | undefined;
    fallback?:
      | {
          path: boolean;
          pathLabel: string;
        }
      | null
      | undefined;
    portsV2: {
      byKey: Record
        string,
        {
          type: string;
          id: string;
          target: string | null;
        }
      >;
    };
  };
  nodeID: string;
  coords?: [number, number] | undefined;
};

​

Introducing Claude Haiku 3.5 and Streamlining Model Selection

• Benefit from improved performance and enhanced conversational abilities
• Create more engaging and human-like interactions

​

Document Metadata - Update Routes

• Document Metadata Update - New PATCH endpoint /v1/knowledge-base/docs/{documentID} to update metadata for entire documents Updates metadata across all chunks simultaneously Note: Not supported for documents of type ‘table’
• Chunk Metadata Update - New PATCH endpoint /v1/knowledge-base/docs/{documentID}/chunk/{chunkID} to update metadata for specific chunks Allows targeted updates to individual chunk metadata Supports all document types, including tables Other chunks in the document remain unchanged

​

Expanded Prompt Support: Add AI Logic to Conditions and Message Variants

• Prompt Conditions: Condition steps can now evaluate prompt responses to intelligently branch conversations down different paths based on AI analysis.
• Message Variant Conditions: Message steps can now use prompt responses to select the most appropriate response text, helping your agent say the right thing at the right time.
• Seamless Prompt Integration: Choose from your existing prompts in the Prompt CMS or create new ones directly within the Condition or Message step.

1. Create or select a Condition step
2. Choose “Prompt” as your condition type
3. Select or create a prompt
4. Add paths and define evaluation criteria

1. Add variants to your Message step
2. Select a prompt to determine variant selection
3. Define your variant conditions
4. Test your dynamic messaging

​

Import and Export Variables and Entities

• Quickly populate your variables and entities by importing exported JSON files
• Easily create new versions of variables and entities by importing new files
• Export your variables and entities as JSON files for backup or sharing
• Save time by bulk importing and exporting variables and entities

​

Prompt Sharing and Improved Variable Debugging

• Import prompts into any agent with just a few clicks, including any variables or entities that are used in the prompt.
• Streamline your workflow by reusing effective prompts across projects.
• Share your best prompts with colleagues and the community.

• See and modify objects and arrays assigned to variables during prototyping.
• Quickly identify issues with variable assignments.

​

Smart Chunking - New Strategies

​

Unlock Dynamic Interactions in Your Agent with Events

• Custom Triggers: Define custom events in the new Event CMS, allowing your agent to respond to specific user actions beyond just conversational input.
• Seamless Integration: Events act as signals from the user’s interactions—like button clicks, page navigations, or in-app actions—enabling your agent to initiate specific workflows dynamically.
• Event Triggers in Workflows: Use the new Event type in the Trigger step to associate events with specific flows in your agent, giving you full control over the conversational paths.

• Expand Interaction Capabilities: Respond to a wide range of user actions within your application, making your agent more intelligent and adaptable.
• Create Contextual Experiences: Provide relevant interactions based on what the user is doing.
• Streamline User Journeys: Assist users at critical points, offering guidance, confirmations, or additional information exactly when needed.

• User Clicks a Checkout Button: Trigger an event to initiate a checkout assistance flow, confirming items or offering shipping options.
• In-App Feature Usage: Start a tutorial when a user accesses a new feature for the first time.
• User Sends a Command in a Messaging App: Provide immediate responses to specific commands, like showing recent transactions.
• User Navigates to a Specific Page: Offer assistance related to the content of the page, such as explaining pricing plans.

• Introduction to Events: Learn more about what you can do with Events.
• Using Events: Discover how to define and implement events in your agent using the Event CMS.

​

Prompt like a Pro: New Prompts CMS, Prompt Step and more

1. Prompts CMS Centralized Prompt Hub: Manage all your prompts in one place, ensuring consistency and easy access across your entire agent. Advanced Prompt Editor: Craft, edit, and test your prompts within an intuitive interface equipped with the necessary tooling to refine your AI agent’s responses. Message Pairs & Conversation Memory: Utilize message pairs to simulate interactions and inject conversation memory, allowing for more dynamic and context-aware agent behaviour. Visibility into Performance Metrics: Gain insights into latency and token consumption, now split by input and output tokens, to optimize your prompts for performance and cost-efficiency.
2. New Prompt Step Prompt Integration: Incorporate response prompts directly into your agent workflows using the new Prompt step. Reuse Across Agent: The prompts you create can be easily reused across your agent, making any updates available wherever the prompt is used.
3. Assign Prompts in Set Step Simplify Designs: This feature brings prompts to the Set step for purposes of reusability and consolidating methods of setting variable values in your agent.

• Expanded Prompt Support: Soon, you’ll be able to use prompts in more steps within your agent’s flow, unlocking new possibilities for interaction design.
• Community Sharing: We’re developing features that will allow you to share prompts across your agents and with the wider community, facilitating collaboration and collective improvement.

• Prompt CMS and Editor: Explore the central hub for creating, testing, and managing prompts within your agent.
• Prompt step: Learn how to integrate prompts directly into your agent’s flow.
• Set step: Discover how to dynamically assign prompt outputs to variables for greater control over agent behaviour.

​

Persistent Listen in Functions

• Persistent Events: Functions can now define events that persist for the entire conversation session. This means that events associated with components like carousels, choice traces, or buttons remain active even after the conversation moves past the function step.
• Delayed User Interaction: Users can interact with these persistent components at any point during the session. When they do, the agent will refer back to the original function and proceed down the relevant path defined in your function code.
• Flexible Agent Behaviour: You now have control over whether the agent waits for user input at the function step or continues execution immediately, thanks to the new listen parameter settings.

• Behavior: The agent pauses execution at the function step. It waits for immediate user input before proceeding.
• Use Case: Ideal when you require the user to make a choice or provide input before moving on.
• Implementation: Set listen: true in your function’s next command.

next: {
  listen: true,
  to: [
    {
      on: { 'event.type': 'option_selected', 'event.payload.value': '1' },
      dest: 'option_1_path',
    },
    // Additional event handlers...
  ],
  defaultTo: 'default_path',
},

• Behavior: The agent continues execution without waiting at the function step. Events defined in the function persist throughout the session and can be triggered later.
• Use Case: Perfect for non-blocking interactions where users might choose to interact with components at their convenience.
• Implementation: Set listen: false in your function’s next command.

next: {
  listen: false, // Must be explicitly set to false
  to: [
    {
      on: { 'event.type': 'item_selected', 'event.payload.label': 'Item A' },
      dest: 'item_A_path',
    },
    // Additional event handlers...
  ],
  defaultTo: 'default_path',
},

• Dynamic Conversations: Create agents that can handle delayed interactions, allowing users to make choices at any point during the conversation.
• Persistent Interactivity: Keep buttons and interactive elements active throughout the session.

export default async function main(args) {
  return {
    trace: [
      {
        type: 'carousel',
        payload: {
          cards: [
            {
              title: 'Product A',
              description: { text: 'Description of Product A' },
              imageUrl: 'https://example.com/productA.png',
              buttons: [
                {
                  name: 'Buy Now',
                  request: { type: 'purchase', payload: { productId: 'A' } },
                },
              ],
            },
            // Additional cards...
          ],
        },
      },
    ],
    next: {
      listen: false, // Agent continues without waiting
      to: [
        {
          on: { 'event.type': 'purchase', 'event.payload.productId': 'A' },
          dest: 'purchase_A_path',
        },
        // Additional event handlers...
      ],
      defaultTo: 'continue_path',
    },
  };
}

• Agent Behavior: Continues to ‘continue_path’ immediately. The purchase event remains active and can be triggered later. When the user clicks “Buy Now” for Product A, the agent navigates to ‘purchase_A_path’.

​

New Publishing Workflow, Knowledge Base Folders and Updated Choice Step

• New Publishing Workflow: Versioned Publishing with Release Notes: Easily add release notes to each version of your agent during the publishing process, making it simpler to track changes and updates. Dedicated Publishing Tab: Access a new Publishing tab within the Agent CMS, where you can name your version, add release notes, and publish directly. The tab includes: Publish View: Name your versions and add notes before publishing. Release Notes View: Review your agent’s release history with a clean, organized display.
• Folders for the Knowledge Base CMS: We’ve added folders to the Voiceflow Knowledge Base CMS, enabling you to organize your data sources more effectively. This makes managing large datasets and sources easier, keeping everything in order.
• Enhanced Choice Step with Button Support: You can now attach buttons to a choice step, with intents being optional. This means you can add paths to a Choice step that are only triggered with a button click, offering greater flexibility in how users interact with your agents.

​

Fueling Your Creativity: We’ve Doubled Your AI Tokens!

​

Streaming API for Real-Time Interactions

• Real-Time Event Streaming: Receive immediate trace events as your Voiceflow project progresses, allowing for dynamic and responsive conversations.
• Improved User Experience: Drastically reduce latency by sending information to users as soon as it’s ready, rather than waiting for the entire turn to finish.
• Support for Long-Running Operations: Break up long-running steps (e.g., API calls, AI responses, JavaScript functions) by sending immediate feedback to the user while processing continues in the background.
• Streaming LLM Responses: With the completion_events query parameter set to true, stream large language model (LLM) responses (e.g., from Response AI or Prompt steps) as they are generated, providing instant feedback to users.

POST /v2/project/{projectID}/user/{userID}/interact/stream

• Accept: text/event-stream
• Authorization: {Your Voiceflow API Key}
• Content-Type: application/json

• completion_events (optional): Set to true to enable streaming of LLM responses as they are generated.

curl --request POST \
     --url https://general-runtime.voiceflow.com/v2/project/{projectID}/user/{userID}/interact/stream \
     --header 'Accept: text/event-stream' \
     --header 'Authorization: {Your Voiceflow API Key}' \
     --header 'Content-Type: application/json' \
     --data '{
       "action": {
         "type": "launch"
       }
     }'

event: trace
id: 1
data: {
  "type": "text",
  "payload": {
    "message": "Give me a moment...",
  },
  "time": 1725899197143
}

event: trace
id: 2
data: {
  "type": "debug",
  "payload": {
    "type": "api",
    "message": "API call successfully triggered"
  },
  "time": 1725899197146
}

event: trace
id: 3
data: {
  "type": "text",
  "payload": {
    "message": "Got it, your flight is booked for June 2nd, from London to Sydney.",
  },
  "time": 1725899197148
}

event: end
id: 4

event: trace
id: 1
data: {
  "type": "completion",
  "payload": {
    "state": "start"
  },
  "time": 1725899197143
}

event: trace
id: 2
data: {
  "type": "completion",
  "payload": {
    "state": "content",
    "content": "Welcome to our service. How can I help you today? Perh"
  },
  "time": 1725899197144
}

... [additional content events] ...

event: trace
id: 6
data: {
  "type": "completion",
  "payload": {
    "state": "end"
  },
  "time": 1725899197148
}

event: end
id: 7

• Find YourprojectID : Locate your projectID in the agent’s settings page within the Voiceflow Creator. Note that this is not the same as the ID in the URL creator.voiceflow.com/project/.../.
• Include Your API Key: Ensure you include your Voiceflow API Key in the Authorization header of your requests.

• Example Project: Check out our streaming-wizard demo project for a practical implementation using Node.js.

• Compatibility: This new streaming endpoint complements the existing interact endpoint and is designed to enhance real-time communication scenarios.
• Deterministic and Streamed Messages: When using completion_events, you may receive a mix of streamed and fully completed messages. Consider implementing logic in your client application to handle these different message types for a seamless user experience.
• Latency Reduction: By streaming events as they occur, you can significantly reduce perceived latency, keeping users engaged and informed throughout their interaction.

​

Smart Chunking Beta: Automatic HTML to Markdown Conversion

​

Secrets Manager and Updated Button Step

• Secure Storage of Sensitive Data Safely store passwords and credentials used to access essential services and functions within your software. Utilize AES-256 GCM encryption to ensure confidentiality and integrity of your secrets.
• Visibility Controls Masked Secrets: Values are hidden but can be temporarily revealed when needed. Restricted Secrets: Values remain hidden and cannot be revealed after creation, enhancing security for highly sensitive data.
• Environment Overrides Specify different secret values for Development and Production environments. Seamlessly manage environment-specific configurations without altering your agent’s logic.
• Integration with Function and API Steps Easily insert secrets into Function and API steps without hardcoding sensitive information. Access secrets directly from the canvas by typing { and selecting from the Secrets tab.
• Secure Project Sharing When duplicating or exporting projects, secret values are excluded to maintain security. Re-add secret values as needed in the new project instance.

• Enhanced Security Protects sensitive information using industry-standard encryption. Prevents unauthorized access through robust key management and encryption practices.
• Simplified Management Centralizes the handling of all your secrets within the Secrets Manager. Reduces the risk of accidental exposure by avoiding hardcoded credentials.
• Operational Flexibility Environment overrides allow for different configurations across development and production stages. Streamlines the deployment process by separating environment-specific data.

1. Access the Secrets Manager Navigate to Agent Settings in the left sidebar. Click on the Secrets tab to open the Secrets Manager interface.
2. Create a New Secret Click New Secret in the top-right corner. Enter the Name, Value, and choose the Visibility setting. Click Create Secret to add it to your Secrets Manager.
3. Use Secrets in Your Agent In a Function or API step, type { to open the variable selector. Switch to the Secrets tab and select the desired secret.
4. Set Up Environment Overrides Go to the Environments tab in Agent Settings. Click Override Secrets next to the desired environment. Enter environment-specific values for your secrets and click Save.

• Streamlined Button Creation: We’ve made it quicker and more intuitive to add buttons. Simply click the ”+” button next to the Buttons label in the editor to add a new button.
• Clean Editor Layout: The editor has been decluttered to focus on what’s important, allowing you to configure your buttons without any unnecessary distractions.

1. Replace Existing Steps: You can replace your existing Button steps with the redesigned version in your projects to benefit from the improved UI.
2. Update Your Conversation Paths: Reconnect any paths as needed using the ports associated with your buttons.
3. Review Settings: Check your No Match, No Reply, and Listen for Other Triggers settings to ensure they are configured as desired.

​

New AI-Powered Entity Collection

• Rules: You can now define specific criteria that the user’s input must meet. This helps ensure that the information collected is valid and meets your requirements.
• Exit Scenarios: These allow your agent to gracefully handle situations where the user can’t provide the necessary information. You can set up alternative paths or responses for these cases, improving the overall user experience.

1. Update Your Steps: Replace your existing Choice and Capture steps with the new AI-powered versions available in the step toolbar.
2. Configure Rules and Exit Scenarios: Use the new options within these steps to define rules and exit scenarios that suit your project’s needs.
3. Test Your Agent: After making changes, be sure to test your agent thoroughly to ensure everything works as expected.

​

New Multimodal Projects

​

Upcoming Update to Listen Steps Data Format

• New Node Types Added: ButtonsV2 Node (buttons-v2) Description: Enhances button interactions with more dynamic features. Type Definition: TypeScripttype ButtonsV2Node = &#123; type: "buttons-v2"; data: &#123; portsV2: &#123; byKey: Record<string, &#123; id: string; type: string; target: string | null; data?: &#123; type?: "CURVED" | "STRAIGHT" | null; color?: string | null; points?: &#123; point: [number, number]; toTop?: boolean | null; locked?: boolean | null; reversed?: boolean | null; allowedToTop?: boolean | null; &#125;[] | null; caption?: &#123; value: string; width: number; height: number; &#125; | null; &#125; | null; &#125;>; &#125;; listenForOtherTriggers: boolean; items: &#123; id: string; label: Markup; &#125;[]; name?: string; noReply?: &#123; repromptID: string | null; path?: boolean | null; pathLabel?: string | null; inactivityTime?: number | null; &#125; | null; noMatch?: &#123; repromptID: string | null; path?: boolean | null; pathLabel?: string | null; &#125; | null; &#125;; nodeID: string; coords?: [number, number]; &#125;; CaptureV3 Node (capture-v3) Description: Provides advanced data capture capabilities, including entity capture and automatic reprompting. Type Definition: TypeScripttype CaptureV3Node = &#123; type: "capture-v3"; data: &#123; portsV2: &#123; byKey: Record<string, &#123; id: string; type: string; target: string | null; data?: &#123; type?: "CURVED" | "STRAIGHT" | null; color?: string | null; points?: &#123; point: [number, number]; toTop?: boolean | null; locked?: boolean | null; reversed?: boolean | null; allowedToTop?: boolean | null; &#125;[] | null; caption?: &#123; value: string; width: number; height: number; &#125; | null; &#125; | null; &#125;>; &#125;; listenForOtherTriggers: boolean; capture: | &#123; type: "entity"; items: &#123; id: string; entityID: string; path?: boolean | null; pathLabel?: string | null; repromptID?: string | null; placeholder?: string | null; &#125;[]; automaticReprompt: &#123; params: &#123; model?: | "text-davinci-003" | "gpt-3.5-turbo-1106" | "gpt-3.5-turbo" | "gpt-4" | "gpt-4-turbo" | "gpt-4o" | "gpt-4o-mini" | "claude-v1" | "claude-v2" | "claude-3-haiku" | "claude-3-sonnet" | "claude-3.5-sonnet" | "claude-3-opus" | "claude-instant-v1" | "gemini-pro-1.5"; system?: string; maxTokens?: number; temperature?: number; &#125; | null; exitScenario?: &#123; items: &#123; id: string; text: string; &#125;[]; path?: boolean | null; pathLabel?: string | null; &#125; | null; &#125; | null; rules?: &#123; id: string; text: string; &#125;[]; &#125; | &#123; type: "user-reply"; variableID?: string | null; &#125;; name?: string; noReply?: &#123; repromptID: string | null; path?: boolean | null; pathLabel?: string | null; inactivityTime?: number | null; &#125; | null; &#125;; nodeID: string; coords?: [number, number]; &#125;; ChoiceV2 Node (choice-v2) Description: Enhances user choice interactions with improved intent handling and automatic reprompt options. Type Definition: TypeScripttype ChoiceV2Node = &#123; type: "choice-v2"; data: &#123; portsV2: &#123; byKey: Record<string, &#123; id: string; type: string; target: string | null; data?: &#123; type?: "CURVED" | "STRAIGHT" | null; color?: string | null; points?: &#123; point: [number, number]; toTop?: boolean | null; locked?: boolean | null; reversed?: boolean | null; allowedToTop?: boolean | null; &#125;[] | null; caption?: &#123; value: string; width: number; height: number; &#125; | null; &#125; | null; &#125;>; &#125;; listenForOtherTriggers: boolean; items: &#123; id: string; intentID: string; rules?: &#123; id: string; text: string; &#125;[]; button?: &#123; label: Markup; &#125; | null; automaticReprompt?: &#123; exitScenario?: &#123; items: &#123; id: string; text: string; &#125;[]; path?: boolean | null; pathLabel?: string | null; &#125; | null; &#125; | null; &#125;[]; name?: string; noReply?: &#123; repromptID: string | null; path?: boolean | null; pathLabel?: string | null; inactivityTime?: number | null; &#125; | null; noMatch?: &#123; repromptID: string | null; path?: boolean | null; pathLabel?: string | null; &#125; | null; &#125;; nodeID: string; coords?: [number, number]; &#125;;

• Enhanced Capabilities: The new node types offer advanced features, allowing for more complex and dynamic conversational flows.
• Existing Nodes Remain Unchanged: Your current diagrams and nodes will continue to function as before.
• New Features Available in New Steps: Only new instances of these steps created after the update will utilize the updated formats and capabilities.

• Update Integrations: If you have custom integrations that interact with diagrams[id].nodes, plan to update them to accommodate these new node types when creating new steps.

​

Condition Step Update

• Redesigned UI: The Condition Step now features an updated interface for easier navigation and setup of conditional paths.
• Flexible Logic Configuration: Users can now choose between a Condition Builder (for non-technical users) or Expression (for custom JavaScript logic) to create paths based on variables, values, logic groups, or expressions.

​

New KB Search Step and Major Token Cost Reductions

• Native KB Querying: Easily query your Knowledge Base without the need for manual API configurations. Simply input a question or variable and retrieve relevant data chunks directly in your workflow.
• Customizable Chunk Retrieval: Use the chunk limit slider to specify the number of data chunks to be returned, ranging from 1 to 10. Fine-tune responses by adjusting this setting to suit your agent’s needs.
• No Match Handling: Set a minimum chunk score for chunk matching. If no data meets this threshold, the workflow can automatically follow a customizable Not Found path, ensuring a seamless user experience even when no exact match is found.
• Enhanced Control Over Prompts: Fetched data chunks are automatically converted into a string format, making them easy to incorporate into text-based prompts and other steps. You have the flexibility to control how this data is used, enhancing the quality and relevance of your agent’s responses.
• Testing Experience: Test your queries directly within the editor. View the returned chunks and their scores for insight into optimizing your knowledge base.

• Improved Efficiency: Eliminate the complexity of setting up manual API calls. The KB Search Step simplifies querying your Knowledge Base, saving you time and effort.
• Greater Flexibility: Control how many data chunks are returned and set minimum chunk scores to ensure the most relevant information is fetched for your agents.
• Enhanced Workflow Integration: Automatically convert and save data into variables, ready for use in subsequent steps within your workflow. This streamlines the process of integrating Knowledge Base data into your conversational designs.

• Token Multiplier Reduction: Tokens are now more affordable, with a reduction of ~50% or more on many of the supported models! Here are the new multipliers: GPT-3.5-Turbo: Reduced from 0.6x to 0.25x GPT-4 Turbo: Reduced from 12x to 5x GPT-4: Reduced from 25x to 14x GPT-4o: Reduced from 6x to 2.5x GPT-4o mini: Reduced from 0.2x to 0.08x Claude Instant 1.2: Reduced from 1x to 0.4x Claude 1: Reduced from 10x to 4x Claude 2: Reduced from 10x to 4x Claude Haiku: Reduced from 0.5x to 0.15x Claude Sonnet 3: Reduced from 5x to 1.75x Claude Sonnet 3.5: Reduced from 5x to 1.75x Claude Opus: Reduced from 20x to 8.5x Gemini: Reduced from 8x to 3.5x
• Billing Email Setting: You can now set a Billing Email on your account from the Billing page on the dashboard. This allows all billing-related emails, such as invoices and payment-related notifications, to be routed to the appropriate contact.

​

Upcoming Update to Condition Step Data Format

• A new condition-v3 node type with an updated data structure will be added for greater flexibility and expressiveness.

type CodeText = (string | { variableID: string } | { entityID: string })[];

interface MarkupSpan {
  text: Markup;
  attributes?: Record<string, unknown>;
}

type Markup = (string | { variableID: string } | { entityID: string } | MarkupSpan)[];

type ConditionV3Node = {
  type: "condition-v3";
  data: {
    portsV2: {
      byKey: Record<string, {
        type: string;
        id: string;
        target: string | null;
      }>;
    };
    condition: {
      type: "prompt";
    } | {
      type: "logic";
      items: {
        value: {
          type: "script";
          code: CodeText;
        } | {
          type: "value-variable";
          matchAll: boolean;
          assertions: {
            key: string;
            lhs: {
              variableID: string | null;
            };
            rhs: Markup;
            operation:
              | "is"
              | "is_not"
              | "greater_than"
              | "greater_or_equal"
              | "less_than"
              | "less_or_equal"
              | "contains"
              | "not_contains"
              | "starts_with"
              | "ends_with"
              | "is_empty"
              | "is_not_empty";
          }[];
        };
        id: string;
        label?: string | null;
      }[];
    };
    name?: string;
    noMatch?: {
      repromptID: string | null;
      path?: boolean | null;
      pathLabel?: string | null;
    } | null;
  };
  nodeID: string;
  coords?: [number, number];
};

• The condition-v3 node will support both script-based and variable-based conditions, allowing for more complex logic.
• Only new condition steps created after the update will utilize the condition-v3 format, unlocking additional features.

• Plan to modify any custom integrations that interact with diagrams[id].nodes to accommodate the new node type.

​

Improved Set Step

• Value Input: This new input option simplifies the process of setting variables. You can now directly assign values to variables without needing to worry about syntax like quotes or data types. This makes it easier than ever to quickly set variables to specific text (String) values or numbers.
• Expression Input: For those needing more advanced functionality, the Expression input allows you to use JavaScript to set variables dynamically. Whether you’re incrementing or decrementing values, or performing complex calculations, the Expression input gives you the power to build sophisticated logic right within the Set step.

​

Introducing Messages: Scalable AI Agent Creation

• Centralized Message Management: Manage all your responses from a single, unified interface.
• Variants and Conditions: Create flexible message variants and set conditions for tailored responses.
• Effortless Reusability: Easily reuse messages across workflows for consistency and efficiency.
• Enhanced Visibility: Track where each message is used and manage updates efficiently.

​

New Default Model: Claude 3 - Haiku

• Claude 3 - Haiku is now the default model in all new Voiceflow projects, offering enhanced performance, improved language understanding, and more nuanced conversational abilities.

​

Upcoming changes to the Set step

• Fields Added: None
• Fields Modified: diagram.nodes[type=setV2] transformed into diagram.nodes[type=set-v3]
• Fields Removed: None

{
  "diagram": {
    "nodes": {
      "642c35170660144e5e8e4042": {
        "type": "setV2",
        "data": {
          "name": "",
          "sets": [
            {
              "id": "random-id-1",
              "type": "advance",
              "variable": "set-variable1-id",
              "expression": "{{[variable1Name].variable1ID}}"
            },
            {
              "id": "random-id-2",
              "type": "advance",
              "label": "set-2-label",
              "variable": "set-variable2-id",
              "expression": "{{[variable1Name].variable1ID}} + {{[variable2Name].variable2ID}}"
            },
            {
              "id": "random-id-3",
              "type": "advance",
              "variable": "set-variable3-id",
              "expression": "\\"just text\\""
            }
          ],
          "title": "Overwrite Itinerary",
          "portsV2": {
            "byKey": {},
            "builtIn": {
              "next": {
                "type": "next",
                "target": null,
                "id": "642c35170660144e5e8e4043",
                "data": {
                  "points": [
                    {
                      "point": [171.50532091813443, 322.2586013515363],
                      "toTop": false,
                      "locked": false,
                      "reversed": false,
                      "allowedToTop": false
                    },
                    {
                      "point": [230.50532091813443, 322.2586013515363],
                      "toTop": false,
                      "locked": false,
                      "reversed": false,
                      "allowedToTop": false
                    },
                    {
                      "point": [230.50532091813443, 517.7585097988019],
                      "toTop": false,
                      "locked": false,
                      "reversed": false,
                      "allowedToTop": false
                    },
                    {
                      "point": [206.50532091813443, 517.7585097988019],
                      "toTop": false,
                      "locked": false,
                      "reversed": true,
                      "allowedToTop": false
                    }
                  ]
                }
              }
            },
            "dynamic": []
          }
        },
        "nodeID": "642c35170660144e5e8e4042"
      }
    }
  }
}

{
  "diagram": {
    "nodes": {
      "642c35170660144e5e8e4042": {
        "type": "set-v3",
        "data": {
          "name": "",
          "items": [
            {
              "id": "random-id-1",
              "type": "script",
              "value": [{ "variableID": "variable1ID" }],
              "variableID": "set-variable1-id"
            },
            {
              "id": "random-id-2",
              "type": "script",
              "label": "set-2-label",
              "value": [{ "variableID": "variable1ID" }, " + ", { "variableID": "variable2ID" }],
              "variableID": "set-variable2-id"
            },
            {
              "id": "random-id-3",
              "type": "script",
              "value": ["\\"just text\\""],
              "variableID": "set-variable3-id"
            }
          ],
          "label": "Overwrite Itinerary",
          "portsV2": {
            "byKey": {
              "next": {
                "type": "next",
                "target": null,
                "id": "642c35170660144e5e8e4043",
                "data": {
                  "points": [
                    {
                      "point": [171.50532091813443, 322.2586013515363],
                      "toTop": false,
                      "locked": false,
                      "reversed": false,
                      "allowedToTop": false
                    },
                    {
                      "point": [230.50532091813443, 322.2586013515363],
                      "toTop": false,
                      "locked": false,
                      "reversed": false,
                      "allowedToTop": false
                    },
                    {
                      "point": [230.50532091813443, 517.7585097988019],
                      "toTop": false,
                      "locked": false,
                      "reversed": false,
                      "allowedToTop": false
                    },
                    {
                      "point": [206.50532091813443, 517.7585097988019],
                      "toTop": false,
                      "locked": false,
                      "reversed": true,
                      "allowedToTop": false
                    }
                  ]
                }
              }
            },
            "builtIn": {},
            "dynamic": []
          }
        },
        "nodeID": "642c35170660144e5e8e4042"
      }
    }
  }
}

​

Changes to Javascript step behavior

// example usage of requireFromUrl
const moment = requireFromUrl("https://cdnjs.cloudflare.com/ajax/libs/moment.js/2.29.1/moment.min.js");

time = moment().add(1, 'hours');

// example of using nodeJS modules
let buff = new Buffer(token, 'base64');
name = buff.toString('ascii');

function atob(e){let r="";if((e=e.replace(/=+$/,"")).length%4==1)throw Error("Invalid base64 string");for(let t=0,n,a,o=0;a=e.charAt(o++);~a&&(n=t%4?64*n+a:a,t++%4)&&(r+=String.fromCharCode(255&n>>(-2*t&6))))a="ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789+/".indexOf(a);return r}
function btoa(t){let a="ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789+/",h="",r=0;for(;r<t.length;){let e=t.charCodeAt(r++),$=r<t.length?t.charCodeAt(r++):Number.NaN,c=r<t.length?t.charCodeAt(r++):Number.NaN;h+=a.charAt(e>>2&63),h+=a.charAt((e<<4|$>>4&15)&63),h+=isNaN($)?"=":a.charAt(($<<2|c>>6&3)&63),h+=isNaN(c)?"=":a.charAt(63&c)}return h}

// converts base64 to ascii, equivalent of Buffer.from(base64ref, 'base64')
atob(base64ref)

// converts ascii to base64
btoa("hello world")

TypeError: Converting circular structure to JSON
--> starting at object with constructor 'global'
--- property 'global' closes the circle"

​

Sunset Announcement: Alexa Hosting

• Existing Alexa skills managed and deployed on Voiceflow will no longer function.
• We strongly encourage you to migrate your skills directly to Alexa, as we will not be providing updates or support for our Alexa integration.

​

Added support for GPT-4o mini

• GPT-4o mini Integration: Our platform now supports GPT-4o mini, providing exceptional cost-efficiency and speed. This compact model is perfect for many of your agent tasks.

• Cost Efficiency: Enjoy significant cost savings with GPT-4o mini with a 0.2x token multiplier.
• Faster Performance: Experience quicker response times, ensuring your AI agents perform efficiently.

​

Sunset Announcement: FAQ API

​

Introducing the New Voiceflow Docs

• Unified documentation: The old learn.voiceflow.com and developer.voiceflow.com sites have had all their articles merged into our new domain, docs.voiceflow.com. This is now the only site you’ll need to visit to access all of Voiceflow’s documentation. No more separate designer and developer documentation splits. Using the old domains will still redirect you to docs.voiceflow.com. Links inside the Voiceflow platform have also been updated.
• New organization: We’ve reorganized our documentation into Building, Deploying, and Improving Agents, as well as new docs and guides for Getting Started and Improving agents.
• Updated documentation: Many new articles have been written to teach you more about the state of the modern Voiceflow platform.
• New API docs and guides: Our API docs have been restructured, with new conceptual articles added and a guide for Getting Started with APIs.
• Moved changelogs: We’ve also brought over our changelogs from the old website (changelog.voiceflow.com). The link will still work to reach the changelogs.

​

Sunset Announcement: Native Integrations for WhatsApp, Twilio SMS, and Microsoft Teams

​

Added support for Gemini 1.5 Pro

• Gemini 1.5 Pro Integration: Our platform now supports Gemini Pro 1.5, offering enhanced performance and a broader range of functionalities. This model brings advanced natural language understanding and generation, making it ideal for various applications.

• Enhanced Accuracy: With Gemini 1.5 Pro, you can expect improved accuracy in natural language processing tasks, leading to more precise and reliable outputs.
• Faster Response Times: Enjoy quicker response times, thanks to the optimized performance of Gemini 1.5 Pro.
• Broader Language Support: Gemini 1.5 Pro offers support for more languages, providing a better experience for multilingual users.

​

More visibility with new updates to the Agent CMS

• A new “Used By” column has been added to these tables.
• This column displays which workflows or components are utilizing each resource.
• Each item in the dropdown is a direct link.
• Easily navigate to the referenced workflow or component for quick access and management.

• Understand how all parts of your agent design come together at a glance.
• Quickly identify dependencies and interconnections between resources.

​

Set Step Redesign

• Improved Interface: A more intuitive design for easier navigation and configuration.
• New error messages: We’re revamped our error messages for the value input to make it easier to debug.
• Labels: Option to rename and label individual variable sets for better organization and clarity.
• Improved canvas visibility: More visibility on your configuration available directly on the step.

​

Upcoming Release: Migration of the Text step to Message step

• Fields Added: responseMessages
• Fields Modified: response now has a new field called type
• Fields Removed: responseVariants, responseAttachments, and nodes with type text

• Fields Added: responseMessages
• Fields Modified: response now has a new field called type
• Fields Removed: responseVariants and responseAttachments

• On webchat projects, all text steps are now messages. Text steps will have a few new features, and all text data will no longer be stored in the node itself but in a new field called response/responseMessages.
• On both webchat and voice projects, requiredEntities re-prompts will be attached toresponse/messages instead of response/variants (variants will be sunset as well).

{
  "type": "message",
  "data": {
    "name": "",
    "draft": false,
    "portsV2": {
      "byKey": {
        "next": {
          "type": "next",
          "target": null,
          "id": "unique-port-id"
        }
      },
      "builtIn": {},
      "dynamic": []
    },
    "messageID": "unique-message-id"
  },
  "nodeID": "unique-node-id"
}

{
  "responses": [
    {
      "id": "unique-response-id",
      "name": "Required entity reprompt",
      "createdByID": 22,
      "folderID": null,
      "type": "message",
      "draft": false,
      "createdAt": "2024-07-03T02:29:25.000Z",
      "updatedAt": "2024-07-03T02:29:25.000Z",
      "updatedByID": 22
    }
  ],
  "responseMessages": [
    {
      "id": "unique-message-id-1",
      "discriminatorID": "unique-discriminator-id-1",
      "text": [
        {
          "text": [
            "my reprompt"
          ]
        }
      ],
      "condition": null,
      "delay": null,
      "createdAt": "2024-07-03T01:30:53.000Z"
    },
    {
      "id": "unique-message-id-2",
      "discriminatorID": "unique-discriminator-id-2",
      "text": [
        {
          "text": [""]
        }
      ],
      "condition": {
        "type": "expression",
        "assertions": [...]
      },
      "delay": 10000,
      "createdAt": "2024-07-03T01:19:22.000Z"
    }
  ],
  "responseDiscriminators": [
    {
      "id": "unique-discriminator-id-1",
      "channel": "default",
      "language": "en-us",
      "responseID": "unique-response-id",
      "variantOrder": [
        "unique-variant-id"
      ],
      "createdAt": "2024-07-03T02:29:25.000Z"
    }
  ]
}

{
  "type": "text",
  "data": {
    "name": "Text",
    "texts": [
      {
        "id": "text-id-1",
        "content": [{ "children": [{ "text": "My root message " }] }],
        "messageDelayMilliseconds": 10000
      },
      {
        "id": "text-id-2",
        "content": [{ "children": [{ "text": "My first variant" }] }]
      }
    ],
    "canvasVisibility": "preview",
    "portsV2": {
      "byKey": {},
      "builtIn": {
        "next": {
          "type": "next",
          "target": null,
          "id": "unique-port-id"
        }
      },
      "dynamic": []
    }
  },
  "nodeID": "unique-node-id"
}

{
  "type": "message",
  "data": {
    "name": "",
    "draft": false,
    "portsV2": {
      "byKey": {
        "next": {
          "type": "next",
          "target": null,
          "id": "unique-port-id"
        }
      },
      "builtIn": {},
      "dynamic": []
    },
    "messageID": "unique-message-id"
  },
  "nodeID": "unique-node-id"
}

1. All text data will be saved into responses (responses/discriminator/messages) instead of node data. In message node data, there will only be messageID which references response.id.
2. repromptID in required entities is a reference to response.id, and its text data is now saved under responseMessages instead of responseVariants.
3. draft in the message node data means that your message step has no content and will not display the response on the CMS until you have content, so draft is false.

{
	...
  "requiredEntities": [
    {
      "id": "6684b7854986c834e67ee772",
      "entityID": "6642a6fee94258e65e603fdd",
      "intentID": "6642aa05e94258e65e603fe0",
      "repromptID": "6684b7854986c834e67ee76f",
      "createdAt": "2024-07-03T02:29:25.000Z"
    }
  ],
  "responses": [
    {
      "id": "6684b7854986c834e67ee76f",
      "name": "Required entity reprompt",
      "createdByID": 22,
      "folderID": null,
      "type": "message",
      "draft": false,
      "createdAt": "2024-07-03T02:29:25.000Z",
      "updatedAt": "2024-07-03T02:29:25.000Z",
      "updatedByID": 22
    }
  ],
  "responseDiscriminators": [
    {
      "id": "6684b7854986c834e67ee770",
      "channel": "default",
      "language": "en-us",
      "responseID": "6684b7854986c834e67ee76f",
      "variantOrder": [
        "6684b7854986c834e67ee771"
      ],
      "createdAt": "2024-07-03T02:29:25.000Z"
    }
  ],
  "responseVariants": [
    {
      "id": "6684b7854986c834e67ee771",
      "conditionID": null,
      "discriminatorID": "6684b7854986c834e67ee770",
      "attachmentOrder": [],
      "text": [
        {
          "text": [
            "my reprompt"
          ]
        }
      ],
      "speed": null,
      "cardLayout": "carousel",
      "createdAt": "2024-07-03T02:29:25.000Z",
      "type": "text"
    }
  ],
  "responseAttachments": [...],
}

{
	...
  "requiredEntities": [
    {
      "id": "6684b7854986c834e67ee772",
      "entityID": "6642a6fee94258e65e603fdd",
      "intentID": "6642aa05e94258e65e603fe0",
      "repromptID": "6684b7854986c834e67ee76f",
      "createdAt": "2024-07-03T02:29:25.000Z"
    }
  ],
  "responses": [
    {
      "id": "6684b7854986c834e67ee76f",
      "name": "Required entity reprompt",
      "createdByID": 22,
      "folderID": null,
      "type": "message",
      "draft": false,
      "createdAt": "2024-07-03T02:29:25.000Z",
      "updatedAt": "2024-07-03T02:29:25.000Z",
      "updatedByID": 22
    }
  ],
  "responseMessages": [
    {
      "id": "6684a9cc3ad70f045227d820",
      "discriminatorID": "6684a9cc3ad70f045227d81f",
      "text": [
        {
          "text": [
            "my reprompt"
          ]
        }
      ],
      "condition": null,
      "delay": null,
      "createdAt": "2024-07-03T01:30:53.000Z"
    },
     {
      "id": "6684a71a3ad70f045227d810",
      "discriminatorID": "6684a7173ad70f045227d807",
      "text": [
        {
          "text": [
            ""
          ]
        }
      ],
      "condition": {
	      "type": "expression",
	      "assertions": [...]
      },
      "delay": 10000,
      "createdAt": "2024-07-03T01:19:22.000Z"
    },
  ],
  "responseDiscriminators": [
    {
      "id": "6684a9cc3ad70f045227d81f",
      "channel": "default",
      "language": "en-us",
      "responseID": "6684b7854986c834e67ee76f",
      "variantOrder": [
        "6684b7854986c834e67ee771"
      ],
      "createdAt": "2024-07-03T02:29:25.000Z"
    }
  ],
}

1. repromptID in required entities is a reference to response.id, and its text data is now saved under responseMessages instead of responseVariants.
2. draft in the message node data means that your message step has no content and will not display the response on the CMS until you have content, so draft is false.

​

Knowledge Base: Tabular Data, Metadata, and Query Filtering

• Equality and Comparison: $eq, $ne, $gt, $gte, $lt, $lte
• Array Operations: $in, $nin, $all
• Logical Operators: $and, $or

1. FILE Upload

curl --request POST \ 
--url 'https://api.voiceflow.com/v1/knowledge-base/docs/upload?overwrite=true' \ 
--header 'Authorization: YOUR_DM_API_KEY' \
--header 'Content-Type: multipart/form-data' \ 
--header 'User-Agent: insomnia/8.0.0' \  
--form 'file=@/path/to/your/file.pdf' \  
--form 'metadata={"inner": {"text": "some test value", "price": 5, "tags": ["t1", "t2", "t3", "t4"]}}'

1. URL Upload

curl --request POST  
  --url '<https://api.voiceflow.com/v1/knowledge-base/docs/upload>  
  --header 'Authorization: YOUR_DM_API_KEY'  
  --header 'Content-Type: application/json'  
  --data '{  
    "data": {  
        "type": "url",  
        "url": "<https://example.com/">,  
        "metadata": {"test": 5}  
    }  
}'

1. TABLE Upload

curl --request POST \
  --url 'https://api.voiceflow.com/v1/knowledge-base/docs/upload/table' \
  --header 'Authorization: YOUR_DM_API_KEY' \
  --header 'Content-Type: application/json' \
  --data '{
    "data": {
        "name": "products",
        "schema": {
            "searchableFields": ["name", "description"],
            "metadataFields": ["developer", "project"]
        },
        "items": [
            {
                "name": "example_name",
                "description": "example_description",
                "developer": {
                    "name": "Jane Doe",
                    "level": "senior",
                    "skills": ["Python", "JavaScript"],
                    "languages": [
                        {
                            "name": "Russian"
                        },
                        {
                            "name": "German"
                        }
                    ]
                },
                "project": {
                    "name": "AI Development",
                    "deadline": "2024-12-31"
                }
            }
        ]
    }
}'

• Match All Specific Tags: Identify chunks that include every specified tag in the list.

{  
    "filters": {  
        "inner.tags": {  
            "$all": ["t1", "t2"]  
        }  
    }  
}

• Match Any of the Specified Tags: Find chunks containing any of the tags listed.

{  
    "filters": {  
        "inner.tags": {  
            "$in": ["t1", "t2"]  
        }  
    }  
}

• Exclude Chunks With Certain Tags: Filter out chunks that include any of the tags specified.

{
    "filters": {
        "developer.tags": {
            "$nin": ["t1", "t2"]
        }
    }
}

• Combination of Conditions: Search for chunks that either contain a specific tag or match a text value exactly.

{
    "filters": {
        "$or": [
            {
                "developer.tags": {
                    "$in": ["t1"]
                }
            },
            {
                "developer.name": {
                    "$eq": "Jane Doe"
                }
            }
        ]
    }
}

​

Introducing the Triggers Step: Elevate Your Workflow Designs

• Enhance Clarity: Users will have a better understanding of how to build efficient Workflows that address user intents effectively.
• Improving Scalability: These best practices will help users build more complex agents that can scale and adapt to new use cases and collaborations.

• Single Entry Point per Workflow: One entry point ensures clarity and simplicity in Workflow design. Commands: We are deprecating Commands so they will no longer be an option on new projects.
• Right-Click to Add Triggers step: Users can still add multiple entry points if necessary, but the default UX encourages a single entry point.
• Updated Start Chip: Users can add additional triggers directly on the start chip, offering more flexibility in design.
• The Event section from the step toolbar has been removed as we . There is still an option to add additional triggers to the canvas available through the right-click on canvas menu.

​

Update: Improved Navigation and Export Options 🧭

• Simplified Navigation: We have removed the Share button from the CMS to streamline your navigation. You can now find all export, share prototype, or invite members options under the Agent menu.
• Enhanced Export Functionality: You now have more control over what you export. We’ve added options to specify the workflow or component you want to export when selecting PNG and PDF formats. This allows for more precise and tailored exports.

​

We’ve added support for GPT 4o!

​

Introducing Workflows: Organize and Scale Your AI Agents

• Removed Intent Steps from Components: To promote best practices in agent design, we have removed the ability to add intent steps directly within Components.
• Cleaner Canvas View: The share button and agent navigation menu have been relocated to the Agent CMS, reducing clutter on the canvas and keeping your focus on designing agent workflows.

1. Newworkflows field:

{  
    workflows: [  
        {  
            status: "to_do" | "complete" | "in_progress" | null,  
            id: string,  
            createdAt: string,  
            updatedAt: string,  
            updatedByID: number,  
            name: string,  
            folderID: string | null,  
            createdByID: number,  
            description: string | null,  
            diagramID: string,  
            isStart: boolean,  
            assigneeID: number | null,  
            assistantID?: string | undefined,  
            environmentID?: string | undefined  
        }  
    ];  
}

1. Node Reference Modifications:

• Replacing goToDomain Nodes: The existing goToDomain nodes within the diagram.nodes will be replaced with goToNode. The goToNode.nodeID will reference the workflow that corresponds to what the domain’s start step previously pointed to.
• Updating goToNode References: All goToNode nodes that previously referenced a domain’s start block (with the exception of the root/home domain) will be updated to reference the new workflow steps accordingly.
• Removal of Start Steps: All start steps, except for those in the root/home diagram, will be removed. This simplification is part of our broader effort to streamline navigation and reduce redundancy within the agent design environment.