PolyAI opens its Agentic Dialog Platform to every enterprise builder for creating and deploying voice dialog agents that have resolved more than 1 billion customer conversations
Platform runs on proprietary Raven model for real-time calls.
#914Matt Henderson@MATTHEN2PolyAI platform is now fully open 🎉
The UI has a built in agent for creating and editing your project. And the sdk allows you to bring this into your local coding agent setup.
Have a go and share any feedback!
PolyAI@polyaivoiceStarting today, we're opening our Agentic Dialog Platform to every enterprise builder. Our dialog agents have resolved 1 billion+ customer conversations for clients like FedEx, Unicredit, PG&E, Marriott, Foot Locker, and many more. These aren't easy conversations. They solve problems like: > A patient booking medical transport who needs insurance verified on the spot. > A homeowner calling their utility company about a gas leak. > A cardholder figuring out why their must-have purchase was declined. Standard conversational AI was never built for this. It was designed for chat, adapted for voice later. It generates responses, but can't do what dialog requires: hold context under pressure, navigate ambiguity in real time, and actually resolve problems. So we built a better model. Our proprietary model Raven was built from the ground up specifically for dialog. Agent harness in the weights, not bolted on through prompts that drift under pressure. And in our platform, you can deploy Raven as your default or bring in GPT-5, Claude, Gemini, whatever model fits your use case or regulatory requirement. Now that the Agentic Dialog Platform is open, any team can create, test, and deploy dialog agents on the same model and infrastructure the world’s top brands trust on their hardest days. This opens up the pool of builders across your entire enterprise. The person who knows customers best, who runs operations, who owns the customer journey: they're all builders now. Two ways to build: > Poly Agent Builder: Describe your use case in natural language, and it configures your agent, knowledge base, and conversation flows automatically. Production-ready in ten minutes. > Agent Development Kit (ADK): Developers use this to build dialog agents the same way they build everything else. Use your own IDE, a coding assistant like Claude, version with Git, deploy from your terminal. Get started now: http://studio.poly.ai/
#1032Rohan Paul@ROHANPAUL_AIVoice AI might be the biggest productivity boost you can add to almost any office job.
And with PolyAI’s Agentic Dialog Platform now open to every enterprise builder, Voice AI has gone from a 6-figure annual contract to a free trial you can install straight from your terminal.
The hard part is not speech recognition, because the real challenge is keeping track of messy human intent while a caller changes details, adds urgency, or asks for something the system did not expect.
Their proprietary model Raven, has the agent behavior built into the model itself instead of relying on long prompts that can drift when calls get complicated.
PolyAI@polyaivoiceStarting today, we're opening our Agentic Dialog Platform to every enterprise builder. Our dialog agents have resolved 1 billion+ customer conversations for clients like FedEx, Unicredit, PG&E, Marriott, Foot Locker, and many more. These aren't easy conversations. They solve problems like: > A patient booking medical transport who needs insurance verified on the spot. > A homeowner calling their utility company about a gas leak. > A cardholder figuring out why their must-have purchase was declined. Standard conversational AI was never built for this. It was designed for chat, adapted for voice later. It generates responses, but can't do what dialog requires: hold context under pressure, navigate ambiguity in real time, and actually resolve problems. So we built a better model. Our proprietary model Raven was built from the ground up specifically for dialog. Agent harness in the weights, not bolted on through prompts that drift under pressure. And in our platform, you can deploy Raven as your default or bring in GPT-5, Claude, Gemini, whatever model fits your use case or regulatory requirement. Now that the Agentic Dialog Platform is open, any team can create, test, and deploy dialog agents on the same model and infrastructure the world’s top brands trust on their hardest days. This opens up the pool of builders across your entire enterprise. The person who knows customers best, who runs operations, who owns the customer journey: they're all builders now. Two ways to build: > Poly Agent Builder: Describe your use case in natural language, and it configures your agent, knowledge base, and conversation flows automatically. Production-ready in ten minutes. > Agent Development Kit (ADK): Developers use this to build dialog agents the same way they build everything else. Use your own IDE, a coding assistant like Claude, version with Git, deploy from your terminal. Get started now: http://studio.poly.ai/
🧵 4. PolyAI’s bet is that voice agents should be built for phone calls from day 1, not copied over from chatbot logic.
That means the agent needs to handle interruptions, messy phrasing, accents, silence, back-and-forth corrections, and the normal chaos of real customer conversations.
PolyAI says its agents are trained on hundreds of thousands of real customer service calls, which is important because support calls rarely look like clean demo scripts.
Rohan Paul@rohanpaul_ai🧵 3. Most customer support automation still breaks at the most important place: the actual phone call. Old Interactive Voice Response systems usually force people through menus, chatbots often fail when the question gets messy, and human support teams get crushed during peak demand. That creates long wait times, abandoned calls, higher staffing costs, and uneven customer experience across voice, chat, SMS, and social channels.
🧵 5. The technical split between the 2 launches is pretty clear.
ADK is for developers who want control, versioning, deployment workflows, and production-grade voice agents built from their normal coding setup.
PolyPhone is for teams that want the fastest path from “we have a website” to “customers can talk to our website.”
That second part is interesting because the website becomes more than a static page: it can answer, explain, qualify, route, and help users without making them search around.
Rohan Paul@rohanpaul_ai🧵 4. PolyAI’s bet is that voice agents should be built for phone calls from day 1, not copied over from chatbot logic. That means the agent needs to handle interruptions, messy phrasing, accents, silence, back-and-forth corrections, and the normal chaos of real customer conversations. PolyAI says its agents are trained on hundreds of thousands of real customer service calls, which is important because support calls rarely look like clean demo scripts.
🧵 6. PolyAI’s new launch is really aimed at 2 very different builders.
ADK is for developers who want to build serious voice AI agents from their normal coding setup, with more control over how the agent is built, managed, tested, and shipped.
PolyPhone is for teams that want a much faster path: give it a website, let it understand the FAQs, product details, and key pages, then turn that site into a voice agent people can actually talk to.
So instead of a website just sitting there with text, it can now answer questions, explain products, qualify leads, route users, and help customers without making them click around.
Rohan Paul@rohanpaul_ai🧵 5. The technical split between the 2 launches is pretty clear. ADK is for developers who want control, versioning, deployment workflows, and production-grade voice agents built from their normal coding setup. PolyPhone is for teams that want the fastest path from “we have a website” to “customers can talk to our website.” That second part is interesting because the website becomes more than a static page: it can answer, explain, qualify, route, and help users without making them search around.
