Jupyter Notebook

interface:
  display_name: "Jupyter Notebooks"
  short_description: "Create Jupyter notebooks for experiments and tutorials"
  icon_small: "./assets/jupyter-small.svg"
  icon_large: "./assets/jupyter.png"
  default_prompt: "Create a Jupyter notebook for this task with clear sections, runnable cells, and concise takeaways."


{
  "cells": [
    {
      "cell_type": "markdown",
      "metadata": {},
      "source": [
        "# Experiment: TITLE\n",
        "\n",
        "Objective:\n",
        "- State the question you want to answer.\n",
        "- Define the success criteria.\n"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {},
      "outputs": [],
      "source": [
        "# Setup: imports and reproducibility\n",
        "from __future__ import annotations\n",
        "\n",
        "import random\n",
        "import statistics\n",
        "\n",
        "SEED = 7\n",
        "random.seed(SEED)\n",
        "SEED\n"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {},
      "source": [
        "## Plan\n",
        "\n",
        "- Hypothesis:\n",
        "- Variables to sweep:\n",
        "- Metrics to record:\n"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {},
      "outputs": [],
      "source": [
        "# Define parameters and lightweight helpers\n",
        "sample_size = 20\n",
        "values = [random.random() for _ in range(sample_size)]\n",
        "summary = {\n",
        "    \"count\": len(values),\n",
        "    \"mean\": statistics.fmean(values),\n",
        "    \"min\": min(values),\n",
        "    \"max\": max(values),\n",
        "}\n",
        "summary\n"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {},
      "source": [
        "## Results\n",
        "\n",
        "- Key observations:\n",
        "- Surprises or failure modes:\n",
        "- Decision: continue, pivot, or stop:\n"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {},
      "outputs": [],
      "source": [
        "# Record findings in a minimal, copy-pasteable structure\n",
        "result = {\n",
        "    \"seed\": SEED,\n",
        "    \"mean\": summary[\"mean\"],\n",
        "    \"range\": summary[\"max\"] - summary[\"min\"],\n",
        "}\n",
        "result\n"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {},
      "source": [
        "## Next steps\n",
        "\n",
        "- What to try next:\n",
        "- What to document elsewhere (PRD, notes, issue):\n"
      ]
    }
  ],
  "metadata": {
    "kernelspec": {
      "display_name": "Python 3",
      "language": "python",
      "name": "python3"
    },
    "language_info": {
      "name": "python",
      "version": "3.12"
    }
  },
  "nbformat": 4,
  "nbformat_minor": 5
}


<svg xmlns="http://www.w3.org/2000/svg" width="20" height="21" fill="currentColor" viewBox="0 0 20 21">
  <path fill="currentColor" d="M4.582 17.078a1.48 1.48 0 0 1 1.066.395c.29.27.463.642.48 1.038v.11a1.509 1.509 0 0 1-.858 1.315 1.476 1.476 0 0 1-1.634-.256 1.504 1.504 0 0 1-.39-1.62 1.51 1.51 0 0 1 .52-.695 1.48 1.48 0 0 1 .816-.287Zm13.167-4.733a7.802 7.802 0 0 1-2.829 3.789 7.698 7.698 0 0 1-4.48 1.44 7.7 7.7 0 0 1-4.48-1.44 7.803 7.803 0 0 1-2.829-3.79c1.424 1.704 4.168 2.854 7.308 2.854 3.14 0 5.883-1.15 7.31-2.853ZM10.436 1.743c1.605 0 3.171.504 4.48 1.44a7.804 7.804 0 0 1 2.829 3.79C16.32 5.272 13.578 4.12 10.438 4.12c-3.14 0-5.884 1.155-7.31 2.855a7.804 7.804 0 0 1 2.828-3.79 7.699 7.699 0 0 1 4.48-1.44ZM3.246 2a.865.865 0 0 1 .91.336.885.885 0 0 1-.062 1.114.869.869 0 0 1-1.433-.224.889.889 0 0 1 .148-.966.875.875 0 0 1 .437-.26ZM16.087.076c.312-.013.617.1.847.313.23.213.367.51.381.824l-.005.176a1.197 1.197 0 0 1-.675.954 1.173 1.173 0 0 1-1.296-.202A1.194 1.194 0 0 1 15.44.305c.188-.14.413-.219.647-.229Z"/>
</svg>


{
  "cells": [
    {
      "cell_type": "markdown",