Author Archives: Allen Rodriguez
A retrieval-augmented generation system can return polished prose while retrieving the wrong evidence. Good evaluation separates retrieval quality from generation quality, then measures citation support, safety, latency, and cost rather than collapsing them into one answer score. In the AWS-centered AIP-C01 objectives, RAG evaluation belongs with model/application testing and Amazon Bedrock Knowledge Bases. In Microsoft’s […]
Human-in-the-loop design is most useful when it changes who has authority to create a consequence. In a low-risk assistant, a person may simply review generated text. In an agentic system, approval can stand between a model proposal and an action that sends money, changes access, publishes content, deletes data, contacts a customer, or modifies infrastructure. […]
Retrieval systems work best when they distinguish broad candidate discovery from precise final ranking. The first stage aims not to miss good evidence; the second stage spends more effort reordering eligible candidates for the actual question. In AIP-C01, Amazon Bedrock Knowledge Bases can use a reranker model during retrieval; in AI-103, Azure AI Search can […]
Security architecture is the discipline of turning risk decisions into durable system boundaries, identities, controls, evidence, and recovery paths. It begins before a firewall rule or cloud policy is configured. The architect first has to understand what the organization is trying to protect, which failures would materially harm the business, where trust is currently assumed, […]
Cryptographic systems fail in practice when organizations focus on algorithms but neglect the keys that make those algorithms trustworthy. A strong cipher cannot protect data if private keys are copied without control, symmetric keys are never rotated, recovery copies are exposed, or compromised keys remain valid. The ISC2 CISSP blueprint treats cryptography as part of […]
Model Context Protocol (MCP) makes it easier for AI clients to discover and use external tools, resources, and prompts through a shared protocol. That interoperability is valuable precisely because it reduces custom integration work. It also creates a governance question: when connecting a new server can expose new data and actions to an AI client, […]
Indirect prompt injection occurs when an AI application ingests attacker-controlled instructions through data rather than through the user’s direct message. A poisoned web page, document, email, support ticket, code comment, calendar entry, or tool response can contain text that is ordinary content to a person but looks like an instruction to a language model. Once […]
A language-model response is generated data, not a trusted application object. Even when a prompt is carefully designed, the model can omit required fields, produce an invalid identifier, invent an unsupported value, include unsafe markup, exceed a business limit, or return a structurally valid action that the current user is not authorized to perform. Production […]
Chunking is often described as dividing text into pieces that fit an embedding model or retrieval pipeline. That description is technically true and operationally incomplete. Documents carry structure: headings define scope, tables bind values to columns, lists express grouping, captions qualify figures, and paragraphs inherit meaning from the sections around them. A retrieval system that […]
A large context window does not remove the need to manage context. It increases the amount of material an application can send to a model, but every token still has a source, cost, latency effect, and opportunity cost. System instructions, conversation history, retrieved evidence, tool definitions, tool results, examples, intermediate state, and the requested output […]
Microsoft AI-103: Tool Schemas for AI Agents A tool schema is the contract between an AI agent and the system it is allowed to call: it constrains arguments, explains what the tool does, and supports independent server-side authorization. A clear schema narrows the model’s choices and makes backend validation predictable; vague descriptions force the model […]
Red-teaming an AI application is not the same exercise as asking a model a collection of provocative prompts. A production system can retrieve documents, call tools, write records, trigger workflows, and expose different data to different users. The useful test case therefore has to describe an adversarial situation in which a model decision interacts with […]
Microsoft AI-103: Speech-Enabled AI Agents A speech-enabled AI agent is not simply a text agent with speech recognition bolted onto the front and text-to-speech added at the end. Voice creates a real-time interaction loop where latency, interruption, turn detection, audio quality, identity, tool execution, and failure recovery all affect whether the experience feels trustworthy. Within […]
Microsoft AI-103: Telemetry for Production Agents Production agents need more than application logs because one user request can become a chain of model calls, retrieval operations, tool invocations, approval steps, retries, and external side effects. Telemetry has to reconstruct that chain well enough for operators to answer what happened, why it happened, how long it […]
Vector search changes what an application can ask a relational database to do. Instead of matching only exact values, ranges, or lexical terms, the application can store an embedding beside ordinary business data and search for rows whose vectors are semantically close to a query vector. In Azure SQL, that makes semantic retrieval part of […]
