Blog

Notes on Building Production AI

Practical field notes on AI platform operations, retrieval, agent reliability and security, and enterprise governance.

The AI Governance For Board Members

A board-level checklist for governing AI systems and agents: inventory, delegated authority, security, regulatory readiness, and accountability.

AI Coding Agents in the Enterprise: Understanding and Regulating the Risks

Coding agents are already in your codebase. Where the gains are real, which risks they concentrate, and how to govern them by autonomy tier.

The EU AI Act Deadline

The Digital Omnibus deferred high-risk obligations to December 2027, but Article 50 transparency duties took effect 2 August 2026. What applies, and to whom.

Why Most AI Agents Break in Production — And What Reliable Agents Look Like

Production agents fail on the engineering around the model. What observability, bounded tools, workload identity, memory, and runtime budgets cost.

Why Most Enterprise RAG Projects Stall at 70% Accuracy — And What Fixes It

Enterprise RAG plateaus on the corpus, the retrieval design, and the missing measurement layer. How to diagnose the real bottleneck and what moves it.

Building a Production RAG Pipeline — The Decisions Inside Each Component

A component-by-component guide to production retrieval: ingestion, contextual embeddings, hybrid retrieval, reranking, generation, and evaluation.

How AI Systems Fail — And How to Test Them for Security

AI systems fail at the seams around the model. How to test for prompt injection, data leakage, MCP compromise, memory poisoning, and identity abuse.

From Prototype to AI Platform: The Operating Model Behind Production AI

How evaluation, context, agents, tools, identity, memory, observability, and automated governance turn a successful AI prototype into a production platform.