Intelligence,
made for work.
Advancing agentic foundation models and systems
and the next generation of AI-native work.
Project Agens
Project Agens is an MSR initiative building an end-to-end-optimized foundation model and system purpose-built for long-horizon agents and the Microsoft ecosystem. It is designed to be agent-first, frontier-efficient, multimodal-native, with built-in multiagent and continuous learning capability, transforming the fundamental and frontier AI research and innovation at MSR into Microsoft advantage on AI models and systems. The initial MVP aims to build frontier work intelligence and work agents for AI-native work experiences. The first milestone is a 300B MoE model targeting 10–100× cost efficiency and 80–90% traffic replacement against frontier proprietary and open-source models, starting with work and enterprise scenarios.
Agens
- Agent-first
- Frontier-efficient
- Multimodal-native
- Multiagent-native
- Continuous learning
Purpose-built for the Microsoft ecosystem, starting with work and enterprise scenarios.
Explore the Agens ModelAgensh
- Multiagent-native harness and infrastructure
- Scaling agents and intelligence
- Reimaging AI efficiency from token efficiency to agent efficiency
Evaluated with up to 1,024 agents on pandoc in the Agensh paper.
Explore AgenshAgens Work
- AI-native work experience
- Your personal, proactive work agent
- Frontier work intelligence for Copilot, Cowork, Autopilot, and Office
The model, harness, and optimization pipeline can extend to other products.
Next: Agens 2.0Frontier efficiency.
Purpose-built intelligence.
Explore Agens Model An end-to-end-optimized agentic foundation model, starting with work and enterprise scenarios across Microsoft products.
MoE Agens model
Cost-efficiency target
Against frontier proprietary and open-source models.
Traffic-replacement target
Across Microsoft products, starting with work and enterprise.
About the first-milestone targets+
The first milestone is to build a 300B MoE Agens model, targeting 10–100× cost efficiency and 80–90% traffic replacement against frontier proprietary and open-source models across Microsoft products, starting with work and enterprise scenarios. These figures describe the project’s first-milestone targets.
Scalable agents.
Self-organized intelligence.
Scaled to 1,024 agents
Demonstrated on ProgramBench’s pandoc task. Workers claim tasks, coordinate with peers, and merge verified progress asynchronously—without a central orchestrator.
A new way to work.
Explore Agens WorkNext-generation AI-native work experience, grounded in the Office and Microsoft 365 ecosystem.
Your proactive, always-on work agent.
Illustrative workflowFind work that
needs doing.
Connect decisions, customer priorities, and work in progress to find what needs attention—before you ask.
Rollout delayed by two weeks
Data residency becomes a priority
Customer review last updated 12 days ago
Work detectedThe customer review needs an update.
Turn context into
a concrete task.
Verify what changed and what is still open. Bring the relevant context together into a clear next step.
Task verified
Update the customer
review report
- Revise the timeline
- Prioritize data residency
- Capture the decisions needed
Bring the next
draft to you.
Prepare the updated report and surface the decisions that need your input, ready for you to review.
Updated draft
Customer review
- TimelineRevised
- Data residencyMoved first
- Open questions2 flagged
Sharing waits for you.
Where work happensTeams · Outlook · Word · PowerPoint · Excel · Microsoft 365
Continuous learning AI (aka Agens 2.0)
The next horizonIntelligence that keeps learning.
Build the continuous learning loop and infrastructure to empower every organization with sovereign intelligence
01Online learning+
A new paradigm of learning: intelligence that learns how to learn as new challenges emerge.
TEST-TIME LEARNING: TRAINING AND DISTILLATION02Continual learning+
Continuous reinforcement learning, with the ambition to build new capabilities without forgetting what came before.
CONTINUOUS RL + LEARNING WITHOUT FORGETTING03Experiential learning+
Learn from experience. Consolidate knowledge. Coach and improve through the work itself.
EXPERIENCE → CONSOLIDATION → COACHING