Cohere details North 2 support for multi-agent orchestration and cross-session context

Cohere announced that North 2 allows users to create reusable agents, automations, and multi-agent orchestrations to complete tasks. In addition, agents in North 2 can maintain context across sessions rather than starting cold each time.

#cohere #north-2 #ai-agents

View original post ↗

Previous articleCoreWeave makes NVIDIA Vera Rubin NVL72 available as Cognition runs Devin in production Next articleCohere introduces North 2 with over 15 new features for enterprise agentic AI

Related AI news

Cohere introduces North 2 with over 15 new features for enterprise agentic AI

Cohere has announced North 2, describing it as its biggest upgrade to date with more than 15 new features addressing scalability, model sovereignty, and enterprise-grade security control.

CCohere•2h 39m ago•

#cohere #north-2 #ai-agents #enterprise-ai

Cohere benchmarked North Small Translate on WMT26 released after the model

Cohere says the WMT26 benchmarks used for North Small Translate were released after the model was created, so it could not be trained to those measurements.

CCohere•1d 23h 12m ago•

#cohere #north-small-translate #wmt26 #benchmarks

Cohere introduces North Small Translate, an open machine translation model

Cohere says it recently introduced North Small Translate and describes it as a new state-of-the-art open machine translation model, the best in the world under 1 trillion parameters. The company also says it wants to be open with the model’s weights and processes.

CCohere•1d 23h 13m ago•

#cohere #north-small-translate #machine-translation #open-models

Cohere Model Vault is now available in Canada

Model Vault is now available in Canada, with auto-scaled workloads, single tenancy, and completely private Cohere models. Cohere says the setup can lower total cost of ownership.

CCohere•9/23/2026, 11:19:56•

#cohere #model-vault #canada #private-ai

VeriHarness turns a base model into a verifier for long-horizon agent tasks

A Google paper, VeriHarness, uses the same base model to check both disputed and unanimous agent claims. With evidence-backed revision, it reports gains of 6.2 points with Gemini 3.5 Flash and 6.4 points with Claude Opus 4.8 over a single rollout.

eelvis•1d 2h 9m ago•

#veriharness #google #ai-agents #gemini #claude

Reset history AI News FAQ Email alerts RSS feeds API MCP Skill

News is compiled from public information. The data is for reference only, and this site has no affiliation with OpenAI.