Practical guide on structural governance for IT automation. Discusses the Model Context Protocol (MCP) as a control layer for agent-to-system interactions and hard execution constraints.
Related Articles
Reusable Evaluators and Template Library: LangSmith Eval Updates
LangSmith introduces reusable evaluators and a library of 30+ evaluator templates to standardize and scale agent evaluation across projects. Teams can define evaluation logic once and apply it across tracing workflows, ensuring consistent safety checks, response quality metrics, and trajectory validation. The templates cover safety (prompt injection, PII, toxicity), response quality, multi-step agent trajectories, user behavior analysis, and multimodal outputs. These evaluators support both online monitoring of production traffic and offline experimentation, enabling teams to detect failures, analyze agent decisions, and continuously improve performance without rebuilding evaluation logic from scratch.
AgentOps is not an engineering problem
Failures in agentic systems stem from lack of operational ownership of behavior in production—not model accuracy. This highlights gaps between governance, engineering, and customer perception, emphasizing the need for real-time behavioral oversight in deployed AI systems.
How AI Agents Will Redesign the Work Style of Cloud Architects
AI agents are transforming cloud architecture by shifting cloud architects from hands-on infrastructure management to designing intent-driven, policy-based systems. Autonomous agents now handle provisioning, scaling, anomaly detection, root cause analysis, and automated remediation, moving CloudOps toward AgentOps. Architects increasingly define SLOs, guardrails, compliance policies, and cost constraints while agents execute and optimize infrastructure in real time. The article highlights proactive incident management, automated runbooks, digital twins for simulation, embedded compliance enforcement, and human-in-the-loop governance models as core patterns. Success in this new era requires skills in intent modeling, policy design, agent escalation workflows, and telemetry-driven optimization.