Image source: wp.technologyreview.com
Introduction: Navigating AI’s Rapid Evolution
Why foundational architecture matters more than ever
As artificial intelligence capabilities accelerate and organizations pivot toward agentic systems—autonomous AI that retrieves information, makes decisions, and executes complex workflows—IT leaders face a dilemma: how to invest wisely in a landscape that can shift within months. The rapid progress introduces risk, with some projects becoming obsolete before they deliver value. According to a sponsored report from MIT Technology Review in partnership with Elastic, the solution lies not in chasing every new model but in returning to the foundational elements of AI architecture. These elements—data quality, context engineering, governance, and human expertise—form a structural framework for deploying and managing reliable, integrated AI systems at scale. They provide a stable compass, enabling leaders to make astute decisions today while preparing for a future of increasingly autonomous agents.
Data Quality: The Bedrock of Reliable AI
Poor data leads to hallucinations and bias
Models are only as reliable as the data they access. Poor data quality is a primary cause of AI hallucinations, bias, and unreliable outputs. Most enterprises grapple with legacy systems, inconsistent data structures, fragmented ownership, and incomplete datasets, making it difficult to scale AI effectively. As Adnan Adil, CIO of Elastic, explains in the report: “The data is a durable part of AI architecture because without it, these models won't run, won't provide the right context, or won't give the right level of services that we're looking to implement.” Industry surveys consistently cite data quality as a major barrier to AI success. Adil warns that if data quality is not good, “the user loses confidence in the system.” An effective AI strategy begins with connecting data across the organization, ensuring it is organized, accurate, governed, and accessible in real time. Scalable data architecture allows AI systems to evolve alongside the business. The report notes that Gartner predicts companies will abandon 60% of all AI projects through 2026 if they are not supported by AI-ready data. Avoiding that outcome requires clear data standards and ownership, clean and labeled data, and pipelines that support real-time retrieval.
Context Engineering: Shaping the Information Environment
Beyond prompt engineering to structured inputs
Context engineering ensures that AI models draw on the most pertinent information for each query, selecting and organizing data to produce accurate answers efficiently. While prompt engineering focuses on how a request is worded, context engineering designs the entire information environment around the model: retrieving the right data and presenting it in a structured, machine-readable way. Many organizations are discovering that reliable AI depends as much on context quality as on the strength of the model. Context engineering relies on a modernized, unified data foundation, as well as retrieval and memory systems such as retrieval augmented generation (RAG) and vector databases. It requires careful prioritization to determine what information matters most, what should be excluded, and when different types of information should be used. Feeding models too much context can dilute relevant details, increase costs, and slow response times. Adil emphasizes: “Minimum context, correct and current data, and machine-readable information are critical to effective context engineering.”
Governance and Observability: Control, Security, and ROI
Embedding oversight from the start
Strong governance and LLM observability help organizations maintain control over how AI systems use data, monitor performance, and identify problems before they affect operations. Without clear controls around retrieval, workflows, and model usage, AI systems often process far more information than necessary, driving up operating costs through additional computing resources, higher token consumption, and API charges. Governance works in tandem with robust security. AI expands the attack surface, introducing risks such as prompt-based data leakage, model vulnerabilities, and adversarial inputs. Protecting sensitive information requires strong access controls, monitoring, and oversight. Adil notes that essential controls—including those related to security, granular cost management, project controls, data security, and architecture—are frequently insufficient. For governance to support transparent, compliant, trustworthy, and cost-effective AI, it must be embedded into architecture, workflows, and decision-making processes from the outset. When established early, governance enables robust observability, allowing teams to assess accuracy and utility over time, monitor adoption patterns, and adjust systems as conditions change. Observability also helps organizations gain trust by increasing visibility of model performance, behavior, and failure points. Furthermore, it is essential to realize return on investment (ROI), as benefits are often indirect and depend on how systems are adopted and used. A 2026 report from Elastic found that 85% of IT decision-makers expect to enable LLM observability for their internal generative AI apps. Adil states: “Observability is actually huge. We can use observability data for cost control, decision-making, and engineering efficiency.”
Human Expertise: The Irreplaceable Component
Growing teams to harness AI’s potential
The thoughtful design, integration, and governance that maximize AI value demand specialized in-house expertise. Nearly 70% of respondents in Deloitte’s 2025 Tech Executive Survey report plan to grow teams in direct response to generative AI, a clear contrast to widely reported AI-related cuts. Adil agrees: “We think the people aspect is largely what's going to make AI impactful going forward.” As AI systems become more embedded in operations, organizations need people who can govern workflows, evaluate outputs, redesign processes, and adapt systems as conditions change. The evolution toward increasingly autonomous tools requires teams skilled in prompt engineering, orchestration, and change management. Talent adept at critical thinking and prepared to adapt with technology’s rapid advances will be in high demand. Although turnover brings fresh thinking, it also presents high costs in system continuity, institutional understanding, and innovation. The report underscores that human-centered design and expertise remain foundational, even as AI capabilities grow.
Based on reporting from technologyreview.com
