Voiceflow

Say goodbye to endless lists of sources. You can now organize your Knowledge Base with folders — happy sorting! 📚 📂

Can AI help you find your perfect home? Find out in #MakingBots with Peter Isaacs, happening this afternoon! Have you signed up? In our Developer Lab last week, Nicolas Arcay Bermejo demoed the example Redfin voice agent we built with the Voiceflow unified workflow — voice + chat in one project, including SMS. In this example, our user calls a phone number to share their real estate preferences in a conversational flow, and the agent serves them relevant listings from a database. Our user goes on to book an appointment to view one of the listings. A simple yet powerful example of how tailored AI agents can provide lead conversion, revenue generating and time savings benefits in any industry. ⚡ Join us at 1pm PT/4pm ET today to dig deeper into the build and learn how you could apply this template in your own projects. voiceflow .com/events

Heading to VOICE & AI next week? 👋 We're more excited than ever for this year with the recent advancements we've seen across the industry around Voice agents. Braden Ream and Tahsim Ahmed will be at Table 5 to catch up and show you some of our favorite complex agents built in Voiceflow. From unique custom front-ends to creative extensions, you'll see first-hand how the Voiceflow platform supports teams to build, launch and scale the multimodal experiences customers have come to expect. Not to mention you can now build chat and voice experiences in one unified workflow ⚡ If you'd like to set up dedicated time to chat, DM us and we'll find a time to meet! #conversationalai #conversationdesign #voiceandai #aivoice

As an agency, your biggest wins are usually your clients’ wins. For Bilal, owner of Helpline Hero, his client struggled with high demand, missing 50% of patient inquiries outside business hours due to a traditional receptionist model. Inefficient appointment booking and managing reviews were also draining staff resources. Helpline Hero built an AI agent that provided 24/7 support, instantly answering questions, booking appointments, and managing feedback—reducing staff workload and creating real business impact. 🏥 $50,000 additional monthly revenue generated 🏥 4300 conversations handled by the AI agent in the first three weeks 🏥 30 hours staff time saved in the first month 🏥 2000 additional web traffic to clinic’s site Click through Bilal’s story to learn more:

📅 Next up: Voiceflow Developer Lab with Nicolas Arcay Bermejo 🛠️ Ahead of the next #MakingBots, our Developer Lab team will show you how to build the technical aspects of an AI agent for real estate. Through transcript synthesis and a multimodal chat and voice interface, the agent captures and analyzes a buyer’s preferences, then sends them new listings that match their needs—automatically. Here’s what you’ll see: ✅ New front-end interfaces: Create a voice agent using OpenAI’s Realtime API and SMS agent via Twilio’s API ✅ Seamless multimodal experience: The buyer texts their basic requirements, and the AI agent will prompt a live call—gathering more details, after the call ends the conversation continues over chat ✅ Transcript synthesis: The call transcript will be sent back to the VF agent to synthesize and recommend real estate listings from a database This is the perfect chance to see how Voiceflow can power seamless text-and-voice interactions, creating a better customer experience for real estate companies. Want to see it in action? Join us next Wednesday, October 23: sign up at voiceflow .com/events

We’re building an AI agent that works for real estate agents: helping generate leads and letting prospective buyers book appointments to see listings that meet their needs. In consumer tech real estate apps like Redfin or Zillow, business moves fast and customers need quick responses. This puts pressure on agents or support staff to work 24/7, leaving low conversion rates and scaling support costs. What if an AI agent could be “on” for you, 24/7, getting new buyers’ requirements and proactively serving them interesting listings? That’s just what Peter Isaacs is building for Making Bots this month. You’ll see: 🏡 Buyers sign up and enter their preferences through a text message interface 🏡 When a new listing meeting their requirements comes up, the buyer receives a text notification 🏡 The buyer can then book a time over text to see that listing in person A simple-on-the-surface workflow that fills a real estate agent’s calendar without the grind. Imagine this applied to other industries - the lead conversion opportunities are endless. See you there? Join us on October 30 by registering with the link in comments, or head to voiceflow. com/events! #makingbots #aiautomation #aiagents #realestate #leadgeneration

The order returns process for retailers is manual and inefficient. We built an AI agent to automate this customer support workflow for New Balance. The chat experience goes beyond simple L1 tickets and can complete actions for users: 👟 When you’re looking to get a refund, you can scan a QR code, look up by your order number, or show all your recent orders. 👟 If you give a return reason in your chat messages, the agent can grab that context and input it automatically in your return form 🤯 👟 If the refund reason is determined to be a manufacturing default, the agent will generate a gift card via the Shopify API Human agents spend their time on more complex tickets, while CSAT and resolution rate jump. This type of AI automation can make level 2 customer support inquiries easier — even enjoyable — experiences for your customers. Check out Peter’s flyby demo to see it in action.

Here's how to pick your first AI agent use case ⬇️ When planning AI projects, we often see teams assess priorities based on 5 categories: ➕ Highest ROI ➕ Familiarity ➕ Technical simplicity ➕ Lowest risk ➕ Organizational simplicity Where you start with AI will depend on how your company handles these priorities. Should you build something that will yield the highest ROI but will open the team to potential risks? Or should you play it safe, building an internal automation that can be iterated upon slowly? Balancing these priorities can be challenging and will differ by organization and opportunity. Reflect on the makeup of your team, the technical capabilities available to you, the industry you work in, and the goals of the company. Once you have one AI product launched and out in the world, the path to scaling and adopting more complex use cases becomes easier. Here's an example from a team working in Voiceflow: ✅ Trilogy had an AI-first ethos as a company, making them a good candidate to start with a high-ROI use case. They started with an ambitious program to automate L1 customer support for 90 individual products. ✅ The team started by developing Atlas Core, a foundational agent integrated with Trilogy’s help center, a knowledge base, and core set of user support flows and functions. ✅ They then used Atlas Core to build the other 80% of standalone projects. This helps them scale AI agents quickly and add features to specific products while maintaining a complex core that they’re continually improving. If you need help getting started, here’s a simple flowchart to see where you might land for your first project. Then, take a look at the suggested scaling pathways to see where your team could end up after a few successful launches.

🛠️ Introducing: Secrets Manager You can now securely store and manage sensitive information within your AI agents. We know impactful agents are built on business-critical data via 3rd party integrations to resolve tickets, convert leads or drive orders. Secrets Manager makes it easy to keep these integration credentials secure with industry-standard encryption, and simpler to use by inserting secrets directly into Function and API steps. Some highlights: ⭐ When duplicating or exporting projects, secret values are excluded to maintain security across teams and projects ⭐ Utilizes AES-256 GCM encryption for top-notch security ⭐ Specify different secret values for Development and Production environments See it working in action below, and try it out for yourself (available on all plans).

🛠️ Video Recap: Everything we released in September Our releases and updates from September simplify the building process, improve response quality, and increase LLM efficiency — making it easier than ever to create amazing customer experiences. Dive into our recap video to learn more about the updates: 🗣️ Multimodal Projects (Voice + Chat) - build and test both voice or chat agents from one unified project type with Michael 📈 Better Token Efficiency - token multipliers for all models have been cut in half, making it less expensive to build complex prompts with Daniel ⚡ Updated Condition Step - visually configure enhanced logic and add custom Javascript expressions with Evgeny 🔎 Knowledge Base Search Step - build RAG pipelines for improved AI Agent response quality with Amanda You’ll also get a sneak preview from Tyler of LLM Entity Extraction, designed to bring more reliability and accuracy to user interactions by introducing rules, exit scenarios, model customization, and automatic reprompts. Happy building! 🚢 #aiagents #aiautomation #buildingwithai #generativeai #conversationdesign