{
  "schema_version": "1.0",
  "id": "A-001",
  "name": "AI Agents",
  "slug": "ai-agents-eight-hour-tasks-2028",
  "canonical_url": "https://cortist.com/forecast/ai-agents-eight-hour-tasks-2028/",
  "question": "Will AI agents reach an eight-hour task horizon at 80% reliability by the end of 2028?",
  "status": "editorial_candidate",
  "publication_date": "2026-10-23",
  "deadline_utc": "2028-12-31T23:59:59Z",
  "probability": null,
  "has_numerical_forecast": false,
  "independently_locked": false,
  "scoring_eligible": false,
  "scored": false,
  "forecast_owner": "Cortist editorial research",
  "event_definition": "At least one publicly available frontier AI agent evaluated with a preregistered, independently replicated METR-style task-completion-time-horizon benchmark reaches an 80%-success time horizon of at least eight hours, where task duration means human expert time for comparable software or research tasks. The qualifying system and task suite must be publicly described before the outcome is judged.",
  "proposed_threshold": "At least 8 human-expert hours at 80% modeled task success",
  "proposed_yes_criteria": [
    "Independent evaluators publish an 80%-reliability time horizon of at least eight human-expert hours for a qualifying publicly available agent on a comparable held-out task suite.",
    "Reproducible task sampling, success tests, baseline estimates and uncertainty intervals are disclosed; an independent reviewer validates eligibility.",
    "The eligible result is achieved and documented by 23:59:59 UTC on December 31, 2028."
  ],
  "proposed_no_criteria": [
    "An eligible independent evaluation by the deadline demonstrates no qualifying agent meeting the threshold under preregistered and comparable tests.",
    "Evidence standards are complete, but all systems tested below the threshold with the stipulated coverage."
  ],
  "unresolved_prelock_requirements": [
    "METR stopped actively updating the previous public dashboard in September 2026; a valid successor evaluator, comparable suite and sampling coverage must be formally selected.",
    "If no adequate independent evaluation exists by the deadline, label unresolved, not automatically false.",
    "Lock the software/research task-domain scope, confidence-interval rules and version-change policy before assigning a probability."
  ],
  "limitations": "An eight-hour benchmark horizon does NOT mean all jobs can be automated; tasks are mainly software engineering, machine learning and security.",
  "sources": [
    {
      "label": "METR: Task-completion time horizons",
      "url": "https://metr.org/time-horizons/",
      "note": "Defines the 50% and 80% time-horizon measures and the narrow task domain."
    },
    {
      "label": "METR: Modeling assumptions",
      "url": "https://metr.org/notes/2026-03-20-impact-of-modelling-assumptions-on-time-horizon-results/",
      "note": "Shows uncertainty from suite composition and curve-fitting, especially at 80% reliability."
    },
    {
      "label": "METR: Measuring AI Ability to Complete Long Tasks",
      "url": "https://metr.org/blog/2025-03-19-measuring-ai-ability-to-complete-long-tasks/",
      "note": "Original study explaining methodology and why time horizons are not ordinary workdays."
    }
  ]
}