ETH Agentic AI Platform/Dashboard

$ echo $PLATFORM

ETH Agentic AI Platform

Build agentic workflows · Compare foundation models · Connect with the community

Workspace Modes

// choose your interface
guided

Step-by-step wizard for structured workflows. Choose a goal, select data, configure methods — the platform handles the orchestration. No code required.

Goal-driven workflowTemplate library
copilot

Natural language interface backed by specialized agents. Ask questions, get grounded answers with citations. Agents route to the right tools and models.

Multi-agent routingSource attribution
notebook

Interactive code environment for full control. Write Python, build pipelines, run experiments. Jupyter-compatible with integrated model access and MCP tools.

Python executionJupyter-compatible cells

members

127

workflows

342

avg_cost

CHF 0.03

challenges

2

Foundation Models

(7)
statusmodel_idprovidercontextlatencycostopen_source
gemini-flashGoogle1M tokens180ms$false
gemini-proGoogle1M tokens1200ms$$$false
claude-sonnetAnthropic200K tokens450ms$$false
claude-haikuAnthropic200K tokens120ms$false
llama-maverickMeta128K tokens350ms$true
mistral-largeMistral AI128K tokens400ms$$false
qwen3Alibaba128K tokens500ms$true

Evaluate & Govern

model_arena// Side-by-side comparison
compliance_sandbox// Regulatory testing
evidence_packages// Signed audit artifacts
cost_carbon_tracker// Sustainability metrics

Community

Which model handles regulatory text best in production?

Dr. Sarah Meier · 24 replies

MCP tools we've built — share yours

Marco Bernasconi · 18 replies

Paper discussion: Causal Foundation Models reliability concerns (April 2026)

Prof. Anna Kovács · 31 replies

CHALLENGE34 joined

Build an explainability agent for automated decisions

Evidence Packages

// signed artifacts

Methodology

Data Profile

Results

Validation

Limitations

Decision Trace

export:PDFJupyter Notebook (.ipynb)JSON MetadataLaTeX

Instructor Console

// moodle LTI
Cohort Management// Create cohorts, assign students, set programme dates
Content Management// Create and organise tutorials, scenarios, and exercises
Budget Configuration// Set per-user and per-cohort budgets for model API usage
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

Trust & Safety

// grounded · honest · compliant · transparent

grounding

Every claim backed by evidence

  • Source Attribution
  • Hallucination Detection
  • Calibrated Uncertainty

honesty

Pushback over agreement

  • Honest Disagreement
  • Multi-Model Consensus
  • Built-in Red Teaming

compliance

Regulation-ready by design

  • EU AI Act Readiness
  • Signed Evidence Packages
  • Swiss Data Sovereignty

transparency

Nothing hidden, everything traceable

  • Full Decision Trace
  • Reproducibility by Design
  • Cost & Carbon Accounting

Research

Causal Foundation Models: Promise and Production-Readiness

ICML 2026 2026

LLM Agents as Causal Orchestrators, Not Causal Reasoners

NeurIPS 2025 2025

Structured Outputs at Scale: Constrained Decoding in Production

arXiv 2026 2026

Experts

SM

Dr. Sarah Meier

Swiss Re

MB

Marco Bernasconi

PostFinance

LT

Lucas Tran

Zurich Insurance

Showcase

Multi-Model Regulatory Review Agent

47 12

Agentic Document Q&A with Evidence Trail

38 9

Cost-Optimized Routing Agent

62 18

[14:32:01] router → model_compare(gemini-flash, mistral-large) ✓ 1.2s

[14:31:45] eval → benchmark(multilingual_rag, 4 models) ✓ 3.8s

[14:30:12] workflow → create(multilingual-rag-pipeline) ✓ 0.3s

[14:28:55] rag → ingest(sample_regulatory.pdf, 47 chunks) ✓ 2.1s

[14:27:30] system → session_start(user=alaa.hammam) ✓

[14:25:00] evidence → generate_ep(compliance_review, SHA-256) ✓ 4.5s