{
  "title": "AI agents in the 2024 report",
  "report_year": 2024,
  "period": "Historical snapshot: October 2024. Dates and populations are specified per row.",
  "methodology": "These results come from different systems and tasks. The planning result is an evaluation outcome; the code figures describe a specific industrial deployment. They should not be combined into a general agent success rate.",
  "source_deck": "https://docs.google.com/presentation/d/1GmZmoWOa2O92BPrncRcTKa15xvQGhq7g4I4hJSNlC0M/edit",
  "web_edition_date": "2026-10-10",
  "rows": [
    {
      "measure": "Initial executable planning",
      "value": "12%",
      "definition": "GPT-4 result in the planning evaluation described by the report, before iterative external feedback.",
      "printed_slide": 59,
      "pdf_page": 60,
      "source_url": "https://www.stateof.ai/State-of-AI-Report-2024.pdf#page=60"
    },
    {
      "measure": "Test classes improved",
      "value": "About 10%",
      "definition": "Share of targeted test classes improved by TestGen-LLM in its deployment.",
      "printed_slide": 70,
      "pdf_page": 71,
      "source_url": "https://www.stateof.ai/State-of-AI-Report-2024.pdf#page=71"
    },
    {
      "measure": "Test recommendations accepted",
      "value": "73%",
      "definition": "Developer acceptance of TestGen-LLM recommendations.",
      "printed_slide": 70,
      "pdf_page": 71,
      "source_url": "https://www.stateof.ai/State-of-AI-Report-2024.pdf#page=71"
    }
  ]
}