ISE Developer Blog
Solving global tech challenges, sharing insights, and empowering developers
Latest posts
Passing Context Between Agents in Multi-Agent A2A Systems
How we solved the challenge of passing conversational context between independently deployed agents using the A2A protocol's embedded context pattern, keeping domain agents stateless and secure.
Separating Deterministic Extraction from AI Inference in Industrial Summarization
When 100% of our prototype outputs were valid JSON but 0% met the data contract, we discovered the LLM was doing work that software should own. A field classification exercise and 4-pass pipeline brought schema compliance from 0% to 100%.
Orchestration Patterns for Multi-Agent Systems: Performance and Trade-offs
Real-world lessons from evolving a production chatbot into a coordinator-based multi-agent architecture, including performance trade-offs for enterprise-scale agent reuse.
How we Decide Between Keyword and Hybrid Search: 5 Enterprise Evaluation Criteria
A data-driven framework we use in enterprise deployments to decide between vector-only keyword and hybrid search, based on five measurable evaluation criteria.
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.
