ETH Zurich · Agentic AI Platform
Build. Collaborate.
Stay at the frontier.
A professional intelligence hub for building agentic AI workflows, evaluating foundation models, and connecting with a community of industry leaders.
Workspace
Platform Activity
Quick Actions
Foundation Models
Tutorials
Your First Agentic Workflow
Build a simple agent that uses tools to answer questions. Learn agent loops, tool calling, and structured responses using LangGraph.
RAG Pipeline from Scratch
Multi-Agent Orchestration
Tool Use with MCP
Model Comparison & Evaluation
Structured Outputs for Production
Community Discussions
Which model handles regulatory text best in production?
MCP tools we've built — share yours
Paper discussion: Causal Foundation Models reliability concerns (April 2026)
Cost optimization tricks for multi-agent workflows
Active Challenges
Build an explainability agent for automated decisions
Create an agent that can explain any ML model's decision in natural language, with causal reasoning and counterfactual explanations. Must comply with EU AI Act Article 86 requirements.
RAG pipeline under CHF 0.10 per query
Design a retrieval-augmented generation pipeline that maintains quality while keeping per-query costs below CHF 0.10. Evaluate on the community benchmark dataset.
Evaluate & Govern
Model Arena
Side-by-side comparison
Compliance Sandbox
Test against regulations
Evidence Packages
Signed audit artifacts
Cost & Carbon
Sustainability metrics
Experts
Dr. Sarah Meier
Swiss Re
Marco Bernasconi
PostFinance
Lucas Tran
Zurich Insurance
Dr. Elena Rossi
UBS
Showcase
Multi-Model Regulatory Review Agent
Agentic Document Q&A with Evidence Trail
Cost-Optimized Routing Agent
Research Feed
Causal Foundation Models: Promise and Production-Readiness
Zhang et al. · ICML 2026 2026
LLM Agents as Causal Orchestrators, Not Causal Reasoners
Kiciman et al. · NeurIPS 2025 2025
Structured Outputs at Scale: Constrained Decoding in Production
OpenAI Research · arXiv 2026 2026
The MCP Standard: Universal Tool Integration for AI Agents
Anthropic · Anthropic Technical Report 2025
Guest Speakers
Dr. Ilya Sutskever
Co-founder, SSI
What AI Safety Means for Enterprise Deployment
Dr. Judea Pearl
Professor, UCLA
Causal Reasoning in the Age of Large Language Models
Amanda Askell
AI Policy Lead, Anthropic
Designing AI Systems That Know What They Don't Know
Evidence Packages
Signed, tamper-proof compliance artifacts
Methodology
Data Profile
Results
Validation
Limitations
Decision Trace
Instructor Console
Moodle LTI integration
Cohort Management
Create cohorts, assign students, set programme dates. Integrates with Moodle via LTI.
Content Management
Create and organise tutorials, scenarios, and exercises. Align with any CAS programme structure.
Budget Configuration
Set per-user and per-cohort budgets for model API usage. Monitor spending in real-time.
Scenario Configuration
Configure evaluation scenarios with custom rubrics, datasets, and scoring dimensions.
Live Monitoring
See student activity in real-time — who is working, which models they're using, where they're stuck.
Review & Assessment
Review student workflows, evidence packages, and notebook submissions. Export grades to Moodle.
Trust & Safety
Grounded · Honest · Compliant · Transparent
Grounded
Every claim backed by evidence
- Source Attribution
- Hallucination Detection
- Calibrated Uncertainty
Honest
Pushback over agreement
- Honest Disagreement
- Multi-Model Consensus
- Built-in Red Teaming
Compliant
Regulation-ready by design
- EU AI Act Readiness
- Signed Evidence Packages
- Swiss Data Sovereignty
Transparent
Nothing hidden, everything traceable
- Full Decision Trace
- Reproducibility by Design
- Cost & Carbon Accounting