{
  "id": "document-extraction-desk",
  "title": "Document Extraction Review Desk",
  "level": 2,
  "levelName": "Builder",
  "tagline": "Extract structured fields from a text document, inspect exact source spans, and approve ambiguous values before export.",
  "summary": "Extract structured fields from a text document, inspect exact source spans, and approve ambiguous values before export.",
  "youWillBuild": "A local HTML review desk that downloads source-bound approval decisions and an approved JSON value map.",
  "usefulFor": [
    "Use your own input to produce a reviewable artifact another application can consume."
  ],
  "hours": 8,
  "languages": [
    "Python"
  ],
  "languageWhy": {
    "Python": "Standard-library parsing, explicit contracts and portable artifacts keep the mechanism visible."
  },
  "status": "ready",
  "source": "core",
  "author": {
    "name": "AI Engineering from Scratch",
    "github": "rohitg00"
  },
  "skills": [
    "Define the fields before extracting values",
    "Extract candidates without losing their evidence",
    "Bind approval to one document version",
    "Show evidence and export reviewed values"
  ],
  "prerequisites": [
    {
      "title": "Development environment",
      "path": "phases/00-setup-and-tooling/01-dev-environment"
    },
    {
      "title": "Data management",
      "path": "phases/00-setup-and-tooling/09-data-management"
    }
  ],
  "figures": true,
  "overviewFigure": "pj-document-extraction-desk-1",
  "demo": {
    "command": [
      "python3",
      "cli.py",
      "sample.txt",
      "--schema",
      "schema.json",
      "--output",
      "output/review.html"
    ],
    "cwd": "solution"
  },
  "stages": [
    {
      "id": "01-define-fields",
      "title": "Define the fields before extracting values",
      "summary": "validate_schema(schema)",
      "hours": 2,
      "difficulty": "starter",
      "language": "python",
      "concepts": [
        "Define the fields before extracting values"
      ],
      "figure": "pj-document-extraction-desk-1"
    },
    {
      "id": "02-retain-source-spans",
      "title": "Extract candidates without losing their evidence",
      "summary": "extract_candidates(text, schema)",
      "hours": 2,
      "difficulty": "core",
      "language": "python",
      "concepts": [
        "Extract candidates without losing their evidence"
      ],
      "figure": "pj-document-extraction-desk-2"
    },
    {
      "id": "03-review-and-approve",
      "title": "Bind approval to one document version",
      "summary": "typed_value(quote, kind); review_document(text, schema, candidates, decisions=None)",
      "hours": 2,
      "difficulty": "core",
      "language": "python",
      "concepts": [
        "Bind approval to one document version"
      ],
      "figure": "pj-document-extraction-desk-3"
    },
    {
      "id": "04-export-review-desk",
      "title": "Show evidence and export reviewed values",
      "summary": "render_review(report)",
      "hours": 2,
      "difficulty": "stretch",
      "language": "python",
      "concepts": [
        "Show evidence and export reviewed values"
      ],
      "figure": "pj-document-extraction-desk-4"
    }
  ],
  "demos": [
    {
      "gif": "media/run.gif",
      "poster": "media/run.png",
      "title": "Build and verify",
      "caption": "Actual starter failure and reference grader output; reference passes do not earn a learner certificate."
    },
    {
      "gif": "media/output.gif",
      "poster": "media/output.png",
      "title": "Use the finished artifact",
      "caption": "Recorded real input, computed output and the resulting portable report."
    }
  ]
}