Update domain tuning notebook to use 'plan_execute' task and improve agent optimization examples. Change model to 'github_copilot/gpt-4o-mini' for faster performance. Enhance explanations for prompt optimization and MIPROv2. Adjust markdown formatting and update kernel specifications across notebooks.

Author: abossard

notebooks/03_domain_tuning.ipynb

@@ -98,20 +98,10 @@
     "display_prompt_diff(result.prompt_before, result.prompt_after)\n"
    ]
   },
-  {
-   "cell_type": "markdown",
-   "id": "6",
-   "metadata": {},
-   "source": [
-    "## 5. Domain-Tuning → der Unterschied\n",
-    "\n",
-    "Jetzt lassen wir den Optimizer mit **deinen echten Ticket-Beispielen** trainieren. Gleiches Modell, gleiche Aufgabe — aber mit Domain-Wissen.\n"
-   ]
-  },
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "7",
+   "id": "6",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -125,7 +115,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "8",
+   "id": "7",
    "metadata": {},
    "source": [
     "## 6. Was du gerade gesehen hast\n",
@@ -147,7 +137,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "9",
+   "id": "8",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -159,7 +149,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "10",
+   "id": "9",
    "metadata": {},
    "source": [
     "## ⏭️ Weiter geht's!\n",