Technical depth on AI, Azure, Next.js, and the engineering decisions behind them.
Browser-based AI agents moved from labs to early production in 2025 and 2026. Anthropic Computer Use, Microsoft Magentic, and OpenAI Operator each take a distinct architectural bet. This is the working comparison for engineers deciding which to deploy and which workloads they actually fit.
A production-shaped guide to designing AI agent tools that the model can actually use without breaking things. Schema choices, idempotency keys, error responses the model can act on, granularity tradeoffs, versioning, and the patterns that separate demo-quality tools from ones that hold up in real workloads.
A technical review of Claude Design, Anthropic's April 2026 launch that turns Claude into a visual work tool. Coverage includes the Opus 4.7 multimodal foundation, the design-system learning feature, workflow integration patterns, enterprise considerations, and where Claude Design sits alongside Figma rather than replacing it.
European industrial organisations hiring a TypeScript consultancy for manufacturing, automotive, or energy software face a market where framework familiarity is common but domain depth is rare. This buyer guide covers the evaluation criteria that matter — including the ones most consultancy pitches quietly skip.
A working-engineer walk-through of the EU AI Act beyond the risk-tier summary. Covers legal structure, Annex III classification decisions, GPAI rules, the full timeline to 2027, Article 12 logging, Article 50 transparency, conformity assessment artifacts, CE marking, penalties, and the Swedish implementation.
A deep dive into Microsoft Entra Agent ID, the control plane for AI agent identity in 2026. Covers identity blueprints, attended and unattended authentication, tool-level RBAC, conditional access, OBO flows across multi-agent systems, and the audit logging that satisfies DORA, NIS2, and AI Act obligations.
Industrial software written in Java, C#, or older languages accumulates over decades. TypeScript is increasingly the modernisation target for the customer-facing and operator-facing layers. This post walks the migration patterns that work in manufacturing, automotive, and energy contexts, and the cases where switching languages is the wrong answer.
The capability spectrum from stateless LLM to multi-agent orchestration is one of the most conflated concepts in the 2026 AI market. The distinctions matter. They change architecture, they change cost by an order of magnitude, and under the EU AI Act they change compliance posture.
A complete working pattern for type-safe Server Actions in Next.js 15 using Zod v4 — auth-aware wrappers, shared client/server schemas, file uploads, discriminated error shapes, useActionState wiring, and tests that exercise the validation boundary.
Industrial documents arrive as scanned paper, multilingual procedures, and proprietary CAD exports. Azure AI Search skillsets turn them into queryable text with structured metadata. This post walks the OCR, entity, language, and custom skill patterns that make the difference between a searchable index and one that actually answers technical queries.
A concrete playbook for reducing Azure OpenAI bills in 2026. Break-even math for Provisioned Throughput Units, prompt-cache economics, the Batch API 50 percent discount, Foundry IQ for retrieval, tiered model routing, and the telemetry that keeps the wins honest.
A practical pattern for rotating Azure secrets with zero downtime using Managed Identity, Key Vault rotation policies, and versioned references — including the common mistakes that cause rotation-induced outages.