NiCE launched the next generation of its Cognigy AI agent platform this week, according to a SiliconANGLE column by Zeus Kerravala, principal analyst at ZK Research. The release includes a redesigned Agentic Experience Studio, an AI Assist companion for building, testing and improving agents, reusable skills, turn-by-turn tracing and native voice-to-voice model support. Default speech-to-text, text-to-speech and language models are now included in the per-conversation price. Premium models from Deepgram, ElevenLabs and Anthropic are billed by usage.
The Simulator can now test up to 10 agent variants against synthetic customers, using an LLM as judge. Cognigy acts as both a Model Context Protocol client and server and supports agent-to-agent connections. NiCE is also co-developing the Personal Agent Protocol with Meta and Sierra, which is not live yet, Kerravala reported.
Director of Product Management Clement Boutier said hybrid setups, which mix fixed workflows with AI agents, are "where most of our customers are," while fully agentic deployments are at the "beginning of the adoption curve." Workflows can sit in front of agents to strip credit card numbers and other personal data before it reaches a model. Senior Product Marketing Manager Nhu Ho called the release "an evolution, not a replacement," saying existing deployments and integrations keep running. Boutier also said compliance remains shared: "We offer the tools and the platform, but we cannot 100% control what they put in it."
