Cohere Unveils North 2 AI Agent Platform with Rebuilt Orchestration and Token Spending Caps

Cohere unveils North 2 AI agent platform with rebuilt orchestration and token spending caps Artificial intelligence company Cohere Inc. today unveiled North 2, an overhaul of its platform for running AI agents inside large organizations. Alongside a redesigned system for orchestrating multistep agent work, the update gives administrators new controls for capping token spending. With North 2, Cohere is going after a tradeoff it says enterprises have accepted while deploying agents, giving up one of security, capability or cost control to get the other two. North has been generally available since August 2025, and Cohere said a year of large production deployments in industries from finance to the public sector shaped what went into the upgrade. The orchestration system works through multistep tasks on its own and pulls in a human for steps that need sign-off. Agents built from a simple prompt can now be shared across a company, which saves other teams from building the same workflow twice. Each agent keeps memory between sessions. Cohere also added a skills feature for packaging logic that agents call on repeatedly. Documents and other assets that every agent should be able to reach go into shared libraries. From a natural-language request, North 2 can produce a slide deck, dashboard or lightweight app that users prototype inside the chat window. For recurring processes there are prebuilt templates and a drag-and-drop workflow builder that reports performance in real time. The connector library now covers Slack, GitHub and Microsoft Corp.’s SharePoint and OneDrive. Cohere is also planning connectors to financial data providers, among them PitchBook Data Inc., S&P Global Inc. and FactSet Research Systems Inc. The new spending controls sit in North Admin, the platform’s management console. It now tracks token use down to the individual user and agent. Administrators can define consumption tiers for users and groups based on request and token rates and cap usage across the company. Alerts can be set to warn teams before a limit is reached. Because North 2 is model-agnostic, the models an administrator assigns to each team can include ones a customer brings from outside Cohere. Cohere is counting on its work with Nvidia Corp. to bring down what North costs to run, saying its models produce more tokens per second per node on Nvidia’s Blackwell and Hopper graphics processing units. Kari Briski, vice president of generative AI at Nvidia, said that helps North 2 “deliver more tokens for less.” Security controls also sit in North Admin, where guardrails can be applied to individual agents. The screening covers personally identifiable information in prompts and responses as well as attempted prompt injection. Autonomy policies keep each agent to the actions it is authorized to take. North still runs on-premises or in a customer’s own virtual private cloud, including fully air-gapped installations for organizations that allow no outside connection. Bell Canada’s Bell Cyber unit is using North inside its own security operations. Jawed Ahmad, Bell Cyber’s chief technology and AI officer, said North lets the unit run agentic AI with the control and sovereignty requirements Bell Cyber’s customers demand “built in from the start.” Other users include South Korean information technology services company LG CNS Co. Ltd., which runs North internally and brings it to customers across the country. Radical Ventures, an early Cohere investor, built an automation on North that prepares the briefing its team reads before a founder call. Before it existed, partner Parasvil Patel said, the team spent hours gathering basic context. North 2 arrives less than three weeks after Cohere signed a merger agreement with German AI developer Aleph Alpha GmbH in a deal that will keep the Cohere name on the combined company. Image: Cohere * * A message from John Furrier, co-founder of SiliconANGLE: Support our mission to keep content open and free by engaging with theCUBE community. Join theCUBE’s Alumni Trust Network, where technology leaders connect, share intelligence and create opportunities. 15M+ viewers of theCUBE videos, powering conversations across AI, cloud, cybersecurity and more 11.4k+ theCUBE alumni — Connect with more than 11,400 tech and business leaders shaping the future through a unique trusted-based network SiliconANGLE Media is a recognized leader in digital media innovation, uniting breakthrough technology, strategic insights and real-time audience engagement. As the parent company of SiliconANGLE, theCUBE Network, theCUBE Research, CUBE365, theCUBE AI and theCUBE SuperStudios — with flagship locations in Silicon Valley and the New York Stock Exchange — SiliconANGLE Media operates at the intersection of media, technology and AI. Founded by tech visionaries John Furrier and Dave Vellante, SiliconANGLE Media has built a dynamic ecosystem of industry-leading digital media brands that reach 15+ million elite tech professionals. Our new proprietary theCUBE AI Video Cloud is breaking ground in audience interaction, leveraging theCUBEai.com neural network to help technology companies make data-driven decisions and stay at the forefront of industry conversations.