The same agent and the same two tools built with Microsoft Agent Framework, LangGraph and Google ADK, run against a scripted model that calls missing tools, sends wrong types, repeats a refund and never stops. The defaults differ, and a few lines of configuration bring them into line.
Read more →Category: AI/ML
GPT-6 in Codex: Choosing Between Astra, Sol and Luna
GPT-6 Astra, Sol and Luna are all in Codex and differ in price by a factor of a hundred. What has been published about them, what an agent session costs under the new caching and long-context rules, and what Codex CLI actually sends when each kind of work is given its own model.
Read more →GPT-5.2-Codex: 400K Context, Image Input and Microsoft Foundry
What OpenAI, Microsoft and GitHub have published about GPT-5.2-Codex, with sources, and what the 400,000-token window means in practice: how much code fits, what a session costs, and how prompt order decides whether caching applies.
Read more →EF Core 10: Vector Search, LeftJoin/RightJoin, and Full-Text Search on Cosmos DB
Entity Framework Core 10, released alongside .NET 10, introduces features that position it as a first-class choice for AI-powered applications. The headline addition—vector search support—enables semantic similarity queries directly in LINQ, while new LeftJoin/RightJoin operators and Cosmos DB full-text search round out a release focused on modern data access patterns. This comprehensive guide explores each […]
Read more →Kubernetes 1.35: In-Place Pod Resource Updates and AI Model Image Volumes
Kubernetes 1.35, released in January 2026 and now supported on Amazon EKS and EKS Distro, marks a significant milestone in container orchestration—particularly for AI/ML workloads. This release introduces In-Place Pod Resource Updates, allowing you to resize CPU and memory without restarting pods, and Image Volumes, a game-changer for delivering large AI models using OCI container […]
Read more →From AI Pilots to Production Reality: Architecture Lessons from 2025 and What 2026 Demands
A Beginning-of-Year Reflection for Enterprise Architects and Technical Leaders As we step into 2026, it’s worth pausing to reflect on the seismic shifts that defined enterprise architecture in 2025—and the hard lessons learned when AI hype met production reality. What began as breathless excitement around generative AI and LLMs has matured into a more nuanced […]
Read more →