Skip to content
All tool news

Tool desk · Updated daily

Tool news·Voiceflow·

Voiceflow tool messages Keep Customers Informed During Lengthy Agent Actions.

Voiceflow tool messages provide contextual, multilingual status updates when an AI agent starts, completes, delays or fails a tool call.

CW

Create With tool desk

1 source checked · 3 min read · 3 sections

ShareLinkedIn
Voiceflow tool messages Keep Customers Informed During Lengthy Agent Actions

Voiceflow is giving AI agents a way to explain what they are doing while customers wait. The company’s new tool messages feature can surface contextual updates when a tool call starts, finishes, fails or takes longer than expected, replacing an awkward stretch of silence with a clearer account of the agent’s progress.

The update was announced on LinkedIn on August 12. Voiceflow argues that customers are more willing to wait when they know what is happening, drawing a comparison with the live progress indicators used by Uber and Domino’s.

That is a small interface change with potentially meaningful consequences. An agent may need time to search a database, retrieve an order, run a workflow or contact an external service. Without feedback, users cannot easily tell whether the request is being processed, the connection has stalled or the agent has stopped responding altogether.

Generated Updates With a Scripted Alternative

By default, tool messages are generated at the moment they are needed, using the current conversation as context. This should let an agent describe its work in language that fits the customer’s request, rather than displaying the same generic loading text for every action.

Builders can also choose a scripted message when tighter control is required. That option may be useful for regulated workflows, carefully defined support procedures or brands that want consistent wording around failures and delays. Voiceflow has not published detailed configuration steps in the source material, but the announcement identifies four points at which messages can appear:

  • Start: when the agent begins a tool call
  • End: when the tool call completes
  • Failure: when the requested operation does not succeed
  • Delay: when the operation is taking longer than expected

The distinction matters because each state calls for different information. A start message can confirm that the request was understood, while a delay message can reassure the customer that processing is continuing. A failure message can acknowledge the problem rather than leaving the conversation hanging.

Tool messages also respond in the language the customer is already using. Voiceflow says this multilingual behavior is automatic, which reduces the need for teams to manually write and maintain separate status messages for every supported language when they use the generative default. Scripted alternatives would still need to be planned with the intended audience in mind.

Why Visible Progress Matters for Agent Builders

Tool-using agents sit between conversational interfaces and external systems, and those systems do not always respond immediately. An inventory check might be fast, while a multistep automation involving customer records, scheduling or a third-party API could take noticeably longer. Narrating that gap makes the interface feel responsive even when the underlying operation has not finished.

For small businesses, the practical benefit is fewer ambiguous interactions. Customers who see no response may repeat a request, refresh the page or abandon the conversation. Status updates cannot make a slow integration faster, but they can set expectations and distinguish normal processing from an actual error.

The release also complements Voiceflow’s earlier work on audible agent feedback. The company previously added tool-call sounds and background audio to voice agents, offering a similar form of reassurance in voice interactions. Tool messages bring more explicit, context-sensitive feedback to the conversation itself.

Voiceflow maintains a broader product changelog covering updates across its agent builder and APIs. The supplied announcement does not specify pricing, plan requirements or a staged rollout schedule, so teams should check their workspace and current documentation before designing a production workflow around the feature.

Frequently asked questions

What is Voiceflow tool messages?

Voiceflow tool messages is a feature that lets an AI agent provide status updates while it uses a tool. Messages can appear when a tool call starts, ends, fails or is delayed, helping customers understand what is happening during the wait.

Can builders control what the status message says?

Yes. Messages are generated dynamically by default using the conversation context, but builders can opt for scripted wording when they need a consistent response.

Do tool messages support multiple languages?

Yes. According to Voiceflow, generative tool messages match the language the customer is already speaking. The announcement does not detail any language restrictions or additional configuration requirements.

Sources

1 checked

How we cover tool news: Create With's tool desk drafts these reports with AI from the sources listed above and checks them against those sources before publishing.

Worth passing on?

ShareLinkedIn

Latest tool news

What else changed this week.

All tool news
VercelDigest

What Vercel Shipped in Late October

Vercel shipped quicker static deployments, four AI Gateway models, more free domain choices and new CLI controls in late October. The changes cover developers testing sites…

Vercel

Vercel Adds Submit_feedback to Its MCP

submitfeedback is a new Vercel MCP tool that lets agents and harnesses send bug reports, friction reports and feature requests directly to the Vercel team. Feedback can include…

The Create With Briefing

Don't watch forty changelogs. Read one email.

Every Tuesday: the tool changes worth knowing, real business use cases, and what's on near you. Free, unsubscribe any time.