{
  "schema_version": "newruntime-agent-readable-v0.1",
  "type": "raw_signal",
  "id": "tg-2668",
  "slug": "databricks-benchmarks-real-coding-agent-economics",
  "title": "Databricks benchmarks coding agents on its own codebase",
  "description": "Databricks evaluates agents on fresh internal pull-request tasks and measures success alongside runtime, tokens, and cost.",
  "observed_at": "2026-07-12",
  "why_it_matters": "Private, current repository tasks expose integration and environment failures that public coding benchmarks cannot capture for an individual organization.",
  "novelty": "structural",
  "verification_level": "source-inspected",
  "signal_type": "field-report",
  "evidence_kind": "mixed",
  "status": "published",
  "telegram_message_id": 2668,
  "telegram_url": "https://t.me/qwgai/2668",
  "topics": [
    "coding-agents",
    "evals",
    "agent-economics"
  ],
  "entities": [
    "Databricks"
  ],
  "related_patterns": [],
  "source_urls": [
    "https://databricks.com/blog/benchmarking-coding-agents-databricks-multi-million-line-codebase"
  ],
  "import_batch": "telegram-2026-07-17-v1",
  "routes": {
    "html": "https://newruntime.com/signals/databricks-benchmarks-real-coding-agent-economics/",
    "markdown": "https://newruntime.com/signals/databricks-benchmarks-real-coding-agent-economics.md",
    "json": "https://newruntime.com/signals/databricks-benchmarks-real-coding-agent-economics.json"
  },
  "source_format": "telegram-export-normalized-json"
}