Category Archives: Technology
Microsoft AI-103: Prompt Shields for AI Apps Prompt injection is dangerous because an AI application mixes instructions and data inside the same reasoning context. A user can try to override system rules directly, while an attacker can place hidden instructions inside a document, email, web page, or tool result that the model later reads as […]
GitHub Copilot Public Code Filtering: Risks and Controls Public code filtering in GitHub Copilot is a governance control for a specific question: what should happen when a Copilot suggestion matches or closely resembles code that is publicly available on GitHub? The answer affects developer workflow, attribution review, and enterprise policy, but it does not make […]
Reusable Components for Copilot Studio Agents Reusable agent components are valuable when several Copilot Studio agents need the same capability but should not independently reinvent prompts, topics, tools, actions, and integration logic. Microsoft now provides component collections and an Agent Library experience through Copilot Agent Kit, allowing makers to install reusable packages and add them […]
Microsoft AI-103: Safety Evaluation in Microsoft Foundry Safety evaluation is the discipline of testing whether an AI application behaves acceptably before the same failure becomes a production incident. In Microsoft Foundry, this goes beyond checking a chatbot for rude language. The current evaluation stack covers content risks, agent behavior, tool use, groundedness, task completion, and […]
Microsoft AI-103: Azure AI Search Semantic Ranking Semantic ranking in Azure AI Search applies a second-stage relevance model to the candidate results returned by keyword, vector, or hybrid retrieval. It cannot recover relevant content that the first retrieval stage excluded, and it does not replace indexing, chunking, or vectorization. In Microsoft AI Agents, semantic ranking […]
Amazon AWS AIP-C01: Vector Search with OpenSearch Serverless For AWS AIP-C01 retrieval design, Amazon OpenSearch Serverless can act as a managed vector layer for semantic search, similarity matching, and retrieval-augmented generation without requiring a team to operate conventional OpenSearch clusters; index quality, filters, and permissions still require explicit design. In Generative AI on AWS, the […]
Microsoft AI-103: Model Routing in Microsoft Foundry Model routing in Microsoft Foundry determines how much model selection happens dynamically for each request, and how quality, latency, and cost are evaluated when different models can serve the same workload. Instead of binding every prompt to one fixed deployment, a model router selects from eligible models according […]
Amazon AWS AIP-C01: SageMaker AI Endpoint Autoscaling Amazon SageMaker AI endpoint autoscaling turns model serving capacity into a feedback system, making the choice of real demand signals an important AWS AIP-C01 deployment decision. A production variant can add or remove instances as demand changes instead of forcing operators to choose one fixed instance count for […]
Amazon AWS AIP-C01: SageMaker AI Model Registry For AWS AIP-C01 model governance, Amazon SageMaker AI Model Registry is a control point for deciding which trained model artifact is allowed to move toward production, and which version and approval evidence supports that decision. Training systems can generate many candidate models, but production needs a smaller set […]
Amazon AWS AIP-C01: Secrets Management for AI Apps AI applications collect credentials at nearly every boundary: model providers, vector stores, relational databases, observability platforms, SaaS APIs, webhook destinations, and custom tools. In AWS AIP-C01 security design, removing avoidable long-lived secrets matters before choosing where to store the remainder. On AWS, those credentials should not be […]
Amazon AWS AIP-C01: Step Functions for Agentic Workflows Agentic applications are often described as loops—ask a model, call a tool, inspect the result, and continue—but AWS AIP-C01 production designs also need explicit state, retries, and recovery that can survive the failure of one in-memory process. Long-running approvals, retries, timeouts, parallel branches, compensating actions, and external […]
Amazon AWS AIP-C01: Testing RAG Quality on AWS A retrieval-augmented generation system can fail even when every component is technically healthy, making separately measured retrieval quality and answer grounding essential to AWS AIP-C01 evaluations. The vector store can return results, the model can produce fluent text, and the application can stay within latency targets while […]
Amazon AWS AIP-C01: Vector Search with Aurora PostgreSQL Vector search inside Amazon Aurora PostgreSQL can be attractive to AWS AIP-C01 application designers when relational data and semantic retrieval need to share consistent permissions, filters, and an operational model without a separate vector database. Aurora PostgreSQL supports the pgvector extension, and AWS documents using an Aurora […]
Microsoft AI-103: Hallucination Test Sets Hallucination testing is more useful when it is built around concrete failure cases than when it relies on a vague instruction to “check factuality.” Microsoft Foundry supports reusable evaluation datasets, model and agent evaluators, synthetic test generation, trace-derived data, and CI/CD-oriented reruns. For Microsoft AI Agents, that makes a hallucination […]
Microsoft AI-103: Key Vault Patterns for AI Apps AI applications accumulate secrets faster than conventional web services because the model is only one dependency in a larger execution path. A production workload can call model endpoints, search services, databases, queues, observability systems, SaaS tools, and custom APIs during a single user interaction. In Microsoft AI […]
