idiap
diff --git a/‎README.md‎
Lines changed: 1 addition & 1 deletion b/‎README.md‎
Lines changed: 1 addition & 1 deletion
diff --git a/‎tutorials/demo_paper/1.agent.py‎ ‎tutorials/demo_paper/agent.py‎tutorials/demo_paper/1.agent.py renamed to tutorials/demo_paper/agent.py b/‎tutorials/demo_paper/1.agent.py‎ ‎tutorials/demo_paper/agent.py‎tutorials/demo_paper/1.agent.py renamed to tutorials/demo_paper/agent.py
diff --git a/‎…orials/demo_paper/2.dialog_generation.py‎ ‎tutorials/demo_paper/dialog_generation.py‎tutorials/demo_paper/2.dialog_generation.py renamed to tutorials/demo_paper/dialog_generation.py b/‎…orials/demo_paper/2.dialog_generation.py‎ ‎tutorials/demo_paper/dialog_generation.py‎tutorials/demo_paper/2.dialog_generation.py renamed to tutorials/demo_paper/dialog_generation.py
diff --git a/‎tutorials/demo_paper/3.evaluation.py‎ ‎tutorials/demo_paper/evaluation.py‎tutorials/demo_paper/3.evaluation.py renamed to tutorials/demo_paper/evaluation.py b/‎tutorials/demo_paper/3.evaluation.py‎ ‎tutorials/demo_paper/evaluation.py‎tutorials/demo_paper/3.evaluation.py renamed to tutorials/demo_paper/evaluation.py
@@ -9,7 +9,7 @@
 [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/idiap/sdialog/)
 
 ---
-SDialog is an MIT-licensed open-source toolkit for building, simulating, and evaluating LLM-based conversational agents end-to-end. It aims to bridge agent construction → dialog generation → evaluation → (optionally) interpretability in a single reproducible workflow, so you can generate reliable, controllable dialog systems or data at scale.
+SDialog is an MIT-licensed open-source toolkit for building, simulating, and evaluating LLM-based conversational agents end-to-end. It aims to bridge agent construction → user simulation → dialog generation → evaluation in a single reproducible workflow, so you can generate reliable, controllable dialog systems or data at scale.
 
 It standardizes a Dialog schema and offers persona‑driven multi‑agent simulation with LLMs, composable orchestration, built‑in metrics, and mechanistic interpretability.