Articles for people who
ship the stack
Rewrites on React, Node.js, TypeScript and AI. A translated body is shown when it exists. If it does not, you see the English text and a note that says so.
Tagged: azure
Microsoft Graph or legacy REST endpoints: a 2026 decision guide
Learn which Microsoft 365 REST APIs are retired or retiring in 2026, how Graph differs on auth, batching and throttling, and when SharePoint REST or EWS still fits.
8 min readTrain a Custom Model in Azure ML and Call It from a Foundry Agent
Train, register and deploy a churn model on an Azure ML managed endpoint, then expose it to a Foundry agent as a FunctionTool, with auth and production notes.
7 min readMAF 1.0, LangGraph or CrewAI? Choosing an Agent Framework in 2026
Microsoft Agent Framework 1.0 vs LangGraph vs CrewAI on state, memory, debugging, protocols, Azure paths and running cost, with a short decision path.
9 min readA Four-Layer Architecture for an Executive Briefing Agent on Azure
How a deterministic briefing agent splits work across Fabric, SQL stored procedures, FastAPI on Azure Functions and Copilot Studio to produce executive documents.
22 min readDurable AI Agents: Saving State With LangGraph, DynamoDB and Cosmos DB
Where agent checkpoints should live on AWS or Azure, how LangGraph resumes work with thread IDs and checkpointers, and what to persist versus recompute.
6 min readAPIM in front of agentic Foundry calls with least-privilege RBAC
Put Azure API Management in front of Foundry model calls from OpenAI and Anthropic, with managed identity, least-privilege custom RBAC and Function backends.
12 min readMulti-agent insurance claims triage on Microsoft Foundry
Insurance claims triage on Microsoft Foundry: a coordinator with coverage, fraud and settlement agents, checkpoints, App Insights and Container Apps hosting.
13 min readProduction RAG on Azure: chunking, hybrid search, filters, and citations
Production RAG on Azure: structure-aware chunking, hybrid search, ACL filters, reranking, grounded prompts with citations, and evaluation beyond a PDF demo.
6 min readMicrosoft Foundry turns model API calls into governed AI operations
Microsoft Foundry turns one-off model API calls into governed operations: model catalogs, agents, RBAC, tracing, observability and evaluation in one place.
7 min read
About these articles
Request a 24h estimate
Need the same stack in a production operator layer? Send the brief — estimate within 24 hours.