A Live agent handoff step can now take its value from a project secret, not just a variable. This lets you keep values like an integration ID or a queue ID out of plain view while still populating the step.

In the handoff step's fields, choose a secret anywhere you could already choose a variable. The secret is resolved when the handoff starts.

The step's Configuration JSON stays variables-only and does not accept secrets.

The Framework page no longer has its own place in the settings rail. The initialization workflow now lives under Behaviour, alongside the rest of an agent's behaviour settings.

If a project is still on conversation flow, you can switch it to the agentic framework from the General tab. The switch only goes one way: once a project moves to agentic, it cannot move back.

This only applies to projects still on conversation flow. An agentic project has no framework switch to make.

Your agent's timezone can now be set from the global prompt editor, right next to the prompt that uses it. Your own timezone is offered first in the list, so the common choice is right there.

Open the Global Prompt tab and use the timezone selector to choose a zone, or clear it if you no longer want one set. Clearing now removes the value instead of requiring you to replace it with another.

The Search transcripts endpoint on the Analytics API can now search across several versions in one request.

Pass a list of version IDs to the versionIDs field to pull transcripts from a published version and its past releases together, instead of querying each version separately.

Messages and prompts can now be read, created, edited and deleted by ID through the API, the MCP server and Atlas. This includes a message's variants and a prompt's system text and settings, so scripted content can be managed directly rather than only through the builder.

Use the API or MCP server endpoints for messages and prompts to fetch or update them by ID, or work with them in Atlas. The /v2 environment export now nests these under messages and prompts, so exports reflect the same structure.

You can now run a function, API tool, MCP tool or integration tool on its own, from the API, the MCP server or Atlas, and read what it returned, without starting a conversation.

Call get_schema to read the inputs a tool expects, then call the tool directly to execute it once. Secrets the tool needs are passed by name rather than by value.

This runs the tool by itself, outside of any conversation flow.

Secrets have moved from the project level to the environment level, so each environment now keeps its own values.

Every secret has a Default value and can optionally have a Draft value. When you test your agent, Voiceflow uses the draft value if there is one and falls back to the default value. In production, it always uses the default value.

Live agent handoff is now available to users on all plans. Users can add the Handoff step to a chat agent and route conversations to a live agent.

Add the Handoff step from the builder and connect it to Ujet, Genesys, Kustomer, Dixa, Sunshine Conversations for Zendesk, or a custom handoff provider.

A click on a carousel or card button now appears as your turn in the transcript, and in the conversation an evaluation scores.

Nothing to configure. This applies to every transcript and to every evaluation run against it.

The chat widget can now play a notification chime when a new message arrives. A visitor who has scrolled away or switched to another tab hears when the agent has replied, instead of only seeing an unread badge on return.

Turn it on in the widget's settings. No other configuration is needed, and the chime plays automatically whenever a new message comes in while the widget isn't in focus.

Voiceflow Core 4.2 has been released as the newest agent model.

Agents running Voiceflow Core 4.1 will move to 4.2 automatically - no action needed. 4.2 is a stronger reasoning and instruction-following model. Conversation quality should improve while remaining at the same cost.

Voiceflow Core 4.1 is deprecated and no longer available for new agents.

A phone number assigned for SMS can now start a conversation instead of only receiving one. Your agent sends the first text, and the recipient's reply continues that same session.

Trigger the outbound message from the phone number API, specifying the number and the recipient. The agent's first message opens the conversation, and everything that follows, on either side, stays in that thread.

This applies to numbers already assigned for SMS, so no separate setup is needed to enable outbound sending.

You can now filter the logs returned by the transcript endpoint to just the traces you need, instead of downloading the whole log and filtering it yourself.

Pass filterConversation on a request to a transcript to return only conversation traces, or use customTraceTypes to select specific trace types to include. Both are optional parameters on the existing stable transcript endpoint.

This trims what the API returns before it reaches you, rather than requiring you to filter the full log after the fact.

Agent instructions, global prompts, and playbook instructions can now be read, searched, and patched line by line through the API. You can edit a single line in a 20,000-line prompt without re-sending the entire document, and search instructions to locate specific lines.

Use the new patch endpoints to update individual lines by their line number or search pattern. This applies to instructions at the agent level, global prompt level, and within playbooks.

Full document replacement remains available. Line-by-line patching is an alternative for large instruction sets where targeted edits are more efficient.

Atlas can now answer questions about your conversations in bulk. Ask why calls dropped last Tuesday, or which conversations scored badly on an evaluation, and it searches your transcripts, reads the ones that matter, and reports back, instead of you opening them one at a time.

Point it at a date range, an environment, or an evaluation score. It can summarize a single conversation from a link, or run named evaluations across everything it found in one batch. Batches spend your workspace's evaluation quota and write scores onto the transcripts, so Atlas tells you the cost before it starts.