Tech and case studies on organizational management, team management, and engineering efficiency
The article argues that CI/CD remains essential infrastructure but must be redesigned for AI agents by exposing platform context via protocols like MCP, preserving failure scenes for root-cause analysis, and enabling self-healing pipelines, starting with the most painful pipeline as a pilot.
This article argues that CI/CD hasn't been replaced by AI but has become indispensable infrastructure like utilities, explaining why stronger AI demands stronger organizational control over quality gates, automated testing, rollback capabilities, and knowledge assetization, distinguishing personal empowerment from organizational governance.
This article summarizes Matt Pocock's four-step checklist for designing effective AI agent skills: choose between user-invoked and model-invoked triggers, structure skills with steps and references using context pointers, control agent behavior with concise guide words like 'vertical slice', and prune redundancy by eliminating duplication, sediment, and no-ops.
Meta's JiTTesting generates temporary, diff-specific test probes that run on both parent and new code versions to catch behavioral differences introduced by AI-generated changes, using dual pipelines (Dodgy Diff and Intent-Aware), noise reduction via RubFake and LLM-as-Judge, and human-in-the-loop review, while promoting stable passing tests to the permanent hardening suite.
JiTTesting introduces a dual-track testing strategy—permanent hardening tests for regression prevention and temporary catching tests generated on-demand to detect behavioral differences in AI-generated code diffs—using parallel pipelines, automated noise reduction, and human-in-the-loop validation to keep pace with rapid AI-driven development.
This article explains that Human-in-the-Loop (HITL) for AI agents is not merely a confirmation dialog but a risk-tiered governance mechanism, presenting five practical rules: risk classification, clear context for human decisions, audit logging, default deny on timeout, and feedback loops for continuous improvement.
The article argues that enterprise AI engineering is moving from fragile prompt-centric specifications to robust environment-driven verification, detailing four essential capabilities—automated validation loops, tool-call fault tolerance, hard permission isolation, and asset lifecycle management—to build governable, self-correcting AI runtime environments.
A technical management team discovers that AI code reviews approve bug fixes that violate architectural intent because AI cannot grasp unwritten team conventions, revealing that AI's limitations mirror human failures in documenting context, standardizing processes, and managing knowledge.
This article clarifies that Human-in-the-Loop (HITL) is not merely a confirmation dialog but a systematic safety framework for AI agents, detailing five production rules, three common misconceptions, and two real-world scenarios to distinguish HITL from HOTL and HOOTL.
This article analyzes ten emerging trends for AI agents in DevOps and SRE for 2026, including autonomous incident response, multi-agent collaboration, tiered autonomy, full-lifecycle Agentic DevOps, SRE for AI agents, governance frameworks, MCP protocol adoption, OpenTelemetry GenAI tracing, agent chaos engineering, and commercial product offerings from major cloud providers.
