PolyAI Opens Its Agentic Dialog Platform to All Builders

May 19, 2026
PolyAI has opened access to its Agentic Dialog Platform, allowing any team to build production-ready conversational agents in under ten minutes. The platform, free for the first two months, is powered by PolyAI's proprietary Raven model trained on over a billion enterprise conversations.

PolyAI announced in a press release that it has opened its Agentic Dialog Platform to all users worldwide. The platform, which powers customer service systems for enterprises such as Marriott, Foot Locker, and Caesars Entertainment, is now available to any team with an email address. Access is free for the first two months.

The Agentic Dialog Platform enables users to build and deploy conversational agents capable of handling complex enterprise interactions across 75 languages and 25 countries. It includes tools such as Poly Agent Builder, which automatically configures agents and knowledge bases from natural language descriptions, and the Agent Development Kit, which provides API keys, integrations, and CLI support for developers.

The platform is built on Raven, PolyAI's proprietary dialog model trained on more than one billion enterprise conversations. Users can deploy Raven as the default model or integrate other large language models, including GPT-5, Claude, and Gemini. PolyAI stated that the platform supports building agents that can operate at enterprise scale and handle mission-critical conversations without human intervention.

Teams can access the platform at poly.ai to begin building agents using their own workflows and tools.

We hope you enjoyed this article

Consider subscribing to one of our newsletters like Enterprise AI Brief or Daily AI Brief.

Also, consider following us on social media:

Enterprise AI AI Brief AI Brief (X)
Free newsletter

Enterprise AI Brief

Weekly report on AI business applications, enterprise software releases, automation tools, and industry implementations.

AI Token Webinar

Whitepaper

Tensordyne Napier: What If One Rack Could Do the Work of Nine?

Tensordyne

This Tensordyne whitepaper presents Napier, an inference-focused AI processor and rack-scale system based on the company’s TDN Math logarithmic number system. It examines infrastructure requirements for large mixture-of-experts and agentic models, compares major inference architecture approaches, and details the TDN AIP processor, TDN72 pod, TDN Link fabric, and Napier Ultra configuration. The paper reports simulation-based performance, cost, and accuracy-validation results, including Tensordyne’s projected comparison of one Napier rack with a nine-rack Nvidia Rubin plus Groq deployment; the chip is reported as taped out and in fabrication.

Read more

You may also like

Free, six days a week

Daily AI Brief: the AI news that matters, in your inbox.