ISE Developer Blog
Solving global tech challenges, sharing insights, and empowering developers
Latest posts
Verification-driven tooling prompts for fast-moving codebases
A practical pattern for using GenAI research agents to produce reliable internal tooling by verifying assumptions with detection classes and a final checklist.
Coordinating AI-Assisted Development with AGENTS.md and Skills
How to move AI-assisted development from ad-hoc experimentation to a coordinated team-wide capability using AGENTS.md and reusable skills with GitHub Copilot CLI
WebAssembly Data Processing at the Edge with Azure IoT Operations
Safe, composable dataflow operators for Azure IoT Operations, built as WASM modules using the Component Model, WIT interfaces, and WASI Preview 2.
SQL query generation from natural language
Evaluating AI agents for NL-to-SQL generation across Azure Databricks AI/BI Genie, GitHub Copilot CLI, and Microsoft Agent Framework. We achieved ~75% accuracy with schema documentation and runtime validation, while discovering that business logic errors represent a fundamental limitation requiring domain expertise.
Propagating SharePoint Document Permissions to AI Search and RAG Pipelines
A security-first architecture that propagates SharePoint document permissions into downstream AI systems, using Microsoft Entra ID object IDs (GUIDs) for safe, query-time filtering in Azure AI Search, RAG pipelines, and Copilot extensions.
Lessons Learned from Building a Well-Matching Intelligence Layer
Key insights from the EDA and Ground Truth journey for solving well identity resolution in the Energy industry—challenges that extend to any entity matching problem across distributed systems.
Discoverable – Observable MCP Server
How to build an observable MCP Server with discoverable tools and agents.
Building Search-Enabled Agents with Azure AI Foundry and Semantic Kernel and A2A
A step-by-step guide to enable search in the semantic kernel agents using bing grounding in Azure Foundry AI Agent using A2A.
From Azure IoT Operations Data Processor Pipelines to Dataflows
In this post we explore the evolution from Azure IoT Operations Data Processor Pipelines to Dataflows, why we adopted a hybrid strategy with custom Rust pods, and the architectural lessons we learned building event detection systems at the edge.
