{
  "id": 9591044,
  "title": "Context-driven AI seen essential for complex building management in Qatar",
  "url": "https://urgent.news/2026/09/24/context-driven-ai-seen-essential-for-complex-building-management-in",
  "topic": "ai",
  "section": "AI",
  "published": "2026-09-24T16:51:00.000Z",
  "source": {
    "name": "Gulf Times Business",
    "slug": "gulf-times-business",
    "url": "https://www.gulf-times.com/article/734061/business/context-driven-ai-seen-essential-for-complex-building-management-in-qatar"
  },
  "original_language": "en",
  "account": "Artificial intelligence (AI) deployment in built environments necessitates tailoring operational logic to unique asset class priorities, rather than adhering to a one-size-fits-all approach, asserts Arfaz Khan, founder and chief technology officer of ARVIS. Khan, co-founder Afnaz Khan, and Muhammed Naseef founded the startup, leveraging a team of engineers and product designers from India. Backed by Qatar Science & Technology Park (QSTP), ARVIS developed Adaptive Building Intelligence, an operational advisor for large-scale facilities, integrating with existing Building Management Systems, HVAC systems, and environmental sensors to gather performance data.\n\nKhan highlighted that building management systems interpret environmental data differently based on operational context. \"A hospital and a commercial tower may have distinct priorities, but fundamentally, they manage buildings generating information and people seeking to understand that data,\" explained Khan. He emphasized that an office with low occupancy could prioritize energy efficiency, while healthcare facilities must maintain continuous operations irrespective of energy demands. \"Low office occupancy might allow efficiency prioritization. Healthcare facilities may require operational continuity. Critical facilities might prioritize reliability,\" Khan noted.\n\nThe challenge lies in teaching algorithms the significance of specific events within a given setting, rather than merely detecting anomalies. \"The difficulty isn't teaching a system to recognize what's happening. It's teaching it why that particular situation matters in that specific building,\" Khan stated. He stressed the importance of local testing in active commercial properties, as isolated laboratory settings or synthetic datasets cannot replicate real-world feedback.\n\nKhan explained that interactions with facility operators shaped ARVIS's technology development, shifting focus from data aggregation to decision-making clarity. \"We initially assumed the main challenge was consolidating building data. However, speaking with seasoned building operators revealed a more critical question: once all information is available, what should someone focus on to make better decisions?\" Khan recalled.",
  "summary": "Deploying artificial intelligence (AI) across built environments requires adapting operational logic to the specific priorities of individual asset classes rather than applying uniform automation rule...",
  "key_points": [],
  "editors_take": null,
  "illustration": null,
  "coverage": {
    "outlets": 1,
    "also_reported_by": []
  },
  "ai_generated": true,
  "disclaimer": "Summaries, key points and the editor’s take are written by software from other outlets’ reporting and may contain errors — always check the linked original."
}