NiCE Updates Cognigy With Reusable Agent Skills and Decision Tracing

Nov 12, 2026
NiCE updates its Cognigy enterprise AI agent platform with reusable skills, decision tracing, AI assisted development and native model integrations.

NiCE launched a new version of its Cognigy enterprise AI agent platform on November 12, according to CMSWire. The release adds AI assisted development, reusable skills, decision tracing and native integrations with models from Deepgram, ElevenLabs, OpenAI and Anthropic.

The redesigned Agentic Experience Studio provides default speech recognition, speech generation and large language models for new projects. Teams can create skills, tools and personas once, reuse them across agents and coordinate specialized agents for complex tasks. AI Assist guides setup, testing and ongoing improvements.

Decision tracing records each step an agent takes, including the data, tools and decisions involved. The platform also supports speech to speech models that process audio directly. Default models are included in conversation pricing, while premium models are available with usage based billing. Existing Cognigy deployments will continue operating without changes.

We hope you enjoyed this article

Consider subscribing to one of our newsletters like Sales & Marketing AI Weekly or Daily AI Brief.

Also, consider following us on social media:

AI Brief AI Brief (X)
Free newsletter

Sales & Marketing AI Weekly

News about AI tools and innovations for Sales and Marketing professionals.

Guide
AI Writing and Copywriting

AI Writing and Copywriting

Specialist tools for drafting and revising prose.

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.