RAG over FHIR Data on AWS HealthLake and Azure Health Data Services: Retrieval That Respects the Record

A FHIR record is a graph of coded, dated, status-bearing resources, not a document corpus. This article sets out a retrieval design for generative AI over FHIR data: FHIR search for exact questions, similarity search for notes, pinned allergies and medication, a hard partition by patient, and citations on every statement. Tested on synthetic data and mapped to AWS HealthLake and the Azure Health Data Services FHIR service.

Hosting Remote MCP Servers Securely on AWS and Azure: Token Validation, Gateways and Network Placement

A remote MCP server is an API that a language model can drive. This article covers the three things that decide whether it is safe: what the MCP authorization specification requires of the server, where to host it on AWS and Azure and who validates the token in each case, and where the endpoint belongs on the network. Includes a tested Python resource server and an ASP.NET Core version for Entra ID.

.NET15 min read

A2A and MCP Across Clouds: Connecting a .NET Agent Framework Agent to an Agent on Bedrock AgentCore

MCP connects an agent to its tools; A2A connects an agent to another agent. This article wires a .NET Microsoft Agent Framework coordinator on Azure to a Python agent and MCP tool server laid out for Amazon Bedrock AgentCore Runtime, and reports what broke: A2A 0.3 versus 1.0 version skew, identity across the cloud boundary, and task lifecycle handling.

.NET15 min read

Amazon S3 Vectors vs. OpenSearch Serverless vs. pgvector for RAG: Cost Floors, Query Bills and Tenant Isolation

All three AWS vector stores can now cost close to nothing at rest, but they bill and isolate tenants in very different ways. This comparison models Amazon S3 Vectors, OpenSearch Serverless (classic and next generation) and Aurora PostgreSQL with pgvector across three workload shapes, checks the S3 Vectors model against the worked examples on the AWS pricing page, and shows where the tenant boundary belongs in each.

Prompt Caching Economics on Amazon Bedrock and Azure OpenAI: Where It Pays and Where It Costs

Prompt caching cannot raise your bill on Azure OpenAI, but on Amazon Bedrock with Claude models a cache write costs more than not caching. This article derives the break-even points (one request per prefix every 20 minutes for the five-minute cache, every 80 minutes for the one-hour cache), gives a tested cost model, and shows how to measure cache read ratios on both platforms.

Taking a GenAI Assistant to Production on Amazon Bedrock: Knowledge Base, Fine-Tuning and Release Gates for Irish Healthcare

For an Irish health guidance assistant on Amazon Bedrock, published HIQA and HSE guidance goes into a Knowledge Base in eu-west-1, fine-tuning is kept for behaviour on non-personal data because Nova customisation runs in US Regions, and IHI and PPSN values are blocked by a dataset gate and a Guardrail. A Step Functions release pipeline promotes a change only after a golden-set evaluation and clinical sign-off.

AI/ML18 min read

Bedrock AgentCore Runtime vs. Lambda for Hosting Agents: Isolation, State and the Idle Bill

The same agent runs on AWS Lambda and on Amazon Bedrock AgentCore Runtime with two thin adapters. The differences are isolation, where conversation state lives and what is billed while the agent waits. AgentCore is cheaper for I/O-bound agents only if sessions are ended deliberately: left at defaults, idle memory makes it the more expensive option.

One Abstraction, Two Clouds: Microsoft.Extensions.AI over Azure OpenAI and Amazon Bedrock

Microsoft.Extensions.AI gives .NET services one interface over Azure OpenAI and Amazon Bedrock. This article builds a two-provider ASP.NET Core service with per-provider telemetry, caching, token metering, tool calling and failover, and is clear about where the abstraction stops: model identity, errors, content safety and model behaviour remain provider-specific.

.NET14 min read

Breaking the 29-Second Wall: Serverless GenAI & Agent Backends on AWS

The API Gateway 29-second timeout is now a default, not a wall: REST APIs can stream for 15 minutes, and Lambda durable functions and Bedrock AgentCore handle work that runs for hours. This article sets out the current limits, three production patterns for long-running GenAI requests with tested code, and the concurrency and cost consequences of each.

Guardrails for Amazon Bedrock: Production Audits & Jailbreak Prevention

Relying on implicit system prompts to police large language models against hostile jailbreaks is fundamentally negligent. By 2026, enterprise architectures rely strictly on decoupled interception fabrics. Explore how Amazon Bedrock Guardrails programmatically neuters adversarial prompt injections, enacts real-time PII masking, and terminates factual hallucinations automatically.

AWS6 min read

The Event-Driven GenAI Pattern: Asynchronous Bedrock Orchestration via Amazon EventBridge

Enterprise GenAI integrations are fatally exposed when treating foundation models like standard REST APIs. Integrating Claude 3.5 Sonnet directly to heavy UI components results in chronic HTTP timeouts. By early 2026, the industry standard relies on DynamoDB streams, EventBridge, and AWS Step Functions. Here is the practitioner blueprint for robust, asynchronous LLM orchestration at scale.

Model Context Protocol (MCP) on AWS: The New Architecture for Enterprise AI Agent Integrations

For years, integrating AI agents with enterprise data meant writing brittle, custom OpenAPI schemas and complex integration logic. In 2026, the open-source Model Context Protocol (MCP) acts as the ‘USB-C for AI.’ Here is the architectural retrospective on securely deploying MCP Servers via AWS Serverless to connect Amazon Bedrock and Q Developer instantly to secure proprietary data.

Amazon Nova After 15 Months: Which Model for Which Job, and How to Check

When AWS launched the Amazon Nova foundation models, the pressing question was simple: Can this replace Anthropic Claude in production? 15 months later, the enterprise architecture data is clear. Nova Micro dominates latency routing, Nova Lite owns mass multimodal extraction, but tiering up to Claude for deep frontier reasoning remains the optimal cost-performance strategy. Here is the operational reality of the Nova family in 2026.

Amazon Bedrock Flows vs Step Functions: When Visual AI Orchestration is the Right Answer

When Amazon Bedrock Flows debuted, it looked conspicuously like AWS Step Functions rebuilt for GenAI. 15 months later, the architectural divide is strictly enforced. Bedrock Flows handles ephemeral, cognitive prompt chains; Step Functions handles durable business transactions. This is the blueprint for the Hybrid Orchestration Pattern separating AI intent from Systemic persistence.

Amazon Bedrock Data Automation: Intelligent Document Processing Without the Pipeline Plumbing

Intelligent Document Processing (IDP) used to mean brittle pipelines of OCR, specific regular expressions, and custom Lambdas. Bedrock Data Automation changes the paradigm: declare a schema via a Blueprint, and let generative AI extract structured data from messy, unstructured multi-modal inputs. Here is the practitioner evaluation of migrating from Textract pipelines to BDA.

Bedrock Multi-Agent Collaboration: From re:Invent Demo to Enterprise Production

Amazon Bedrock Multi-Agent Collaboration reached GA at re:Invent 2024, enabling supervisor agents to orchestrate specialised sub-agents across enterprise domains. This is the production reality check: routing quality, token cost multiplication, failure modes that don’t surface until scale, parallel invocation patterns, and the compliance gap that catches regulated industry teams — Guardrails don’t propagate from supervisor to sub-agents.

Generative AI Services in AWS

A practitioner’s deep-dive into the complete AWS Generative AI stack: Amazon Bedrock foundation models, Knowledge Bases, Agents, Guardrails, Amazon Q Business and Q Developer, SageMaker fine-tuning with LoRA, Trainium and Inferentia custom silicon, multi-model routing patterns, and production observability. 3000+ words of enterprise-grade guidance.