Search the practice set
126 questions, 454 terms and 400 topics in 20 areas.
60 results for “LLM Application Architecture”
Tool Calling
Giving a model a set of typed function definitions it can request to invoke, with the application executing the call and returning the result.
Application Portfolio Management
Maintaining an inventory of every application with its owner, cost, business value and technical health, and using it to decide what to invest in, replace or retire.
LLM Evaluation
A repeatable measurement of whether an AI system's outputs are good enough, on cases that reflect the actual task.
Layered Architecture
Organising code into horizontal layers — presentation, application, domain, data — where each layer may only call the one beneath it.
AI Gateway
A shared proxy in front of model providers that centralises routing, keys, quotas, caching, logging and safety policy.
Change Data Capture
Publishing a stream of a database's row-level changes by reading its replication log, without modifying the application that owns it.
Context Window
The maximum number of tokens a model can attend to in one request, holding the system prompt, history, retrieved context, tools and the answer.
Guardrail
A deterministic check applied to a model's input or output, enforcing rules that cannot be left to the model itself.
Microservices
An architectural style where an application is a set of independently deployable services, each owning its data and aligned to a business capability.
Model Router
Directing each request to a model chosen by the task's difficulty, cost and latency budget, rather than sending everything to the largest model available.
OAuth 2.0
An authorisation framework that lets an application obtain scoped, delegated access to a resource without handling the user's credentials.
OWASP Top Ten
A periodically updated consensus list of the most critical web application security risks, useful as a design-review checklist.
Prompt Injection
An attack in which text from an untrusted source is interpreted by the model as instructions rather than as data.
Prompt Registry
A versioned store of production prompts with their model bindings, parameters and evaluation results, so a prompt change is a reviewable, traceable, reversible deployment.
Prompt Versioning
Treating prompts as versioned, reviewed, tested artefacts rather than as strings edited in place.
Retrieval-Augmented Generation
Retrieving relevant documents at query time and putting them in the model's context, so answers are grounded in your data rather than in training data.
Semantic Cache
Caching model responses keyed by the meaning of the request rather than by its exact text, so near-duplicate questions are served without a model call.
Service Mesh
An infrastructure layer of sidecar proxies that handles service-to-service networking — mTLS, retries, timeouts, routing, telemetry — outside the application.
Shopify's Pods and Modular Monolith
Shopify handles Black Friday scale with isolated pods — complete stacks each serving a subset of merchants — while keeping the application itself a deliberately modular monolith.
Sidecar
Deploying a helper process alongside the main application in the same unit, to supply cross-cutting behaviour without changing the application.
TOGAF
An enterprise architecture framework whose central element is the ADM, an iterative cycle from vision through business, data, application and technology architecture to implementa…
Application Discovery
Establishing what applications exist, what they depend on, who owns them and whether anyone uses them — the step whose absence makes every later step a guess.
Application Performance Monitoring
Instrumentation inside the application that attributes latency and errors to specific code paths, queries and dependencies.
Architecture Cost Model
A calculation, made during design, of what an architecture will cost to run at expected and at peak volume.
Architecture Decision Log
The ordered, immutable collection of a system's decision records, read as a history rather than as a specification.
Architecture Decision Record
A short, immutable document capturing one architectural decision, its context, the alternatives, and its consequences.
Architecture Principle
A durable, agreed rule that constrains design decisions in advance, stated with its rationale and its implications.
Architecture Review Board
A forum that reviews significant designs against standards, risks and strategy before commitment.
An LLM feature that worked last week now gives worse answers. Nothing was deployed. How do you find out what changed, and what should have been in place?
What the interviewer is testing Whether you treat an AI feature as a system with configuration and dependencies, or as a black box that mysteriously drifts. Wha
A client wants an assistant that answers questions from 50,000 internal documents which change weekly. RAG or fine-tuning? What actually determines the quality?
What the interviewer is testing Whether you understand what each technique actually does, and whether you know that RAG quality is a retrieval problem. Why RAG
LLM Application Architecture
The shape of a production system with a model in the request path.
Application Architecture
The application estate as a designed portfolio rather than an accumulation.
Application Portfolio Management
Inventory, ownership, cost and health for every application.
Application Rationalisation
Retire, consolidate, replatform — and why retirement is under-applied.
LLM Evaluation
Held-out sets, rubric judging, CI gates and production sampling.
Cloud Migration
Per-application disposition, sequencing and the capability change underneath.
EA Domains
Business, application, data and technology architecture as viewpoints.
Encryption
At rest, in transit, and at the application layer — three different threats.
AI-Era Architecture
General material on architecting systems that include models.
Application Decomposition
Finding seams in a monolith, starting from the data.
Application Performance Monitoring
Attributing latency to code paths, queries and dependencies.
Architecture Communication
General material on communicating architecture.
Architecture Cost Modelling
Pricing a design before building it, at expected and at ten times volume.
Architecture Decision Records
One decision, its context, alternatives and consequences, kept immutable.
Architecture Decision-Making
General material on making and recording architectural decisions.
Architecture Diagrams
Choosing an audience and refusing to mix levels of abstraction.
Architecture Documentation
What to write down, at what altitude, and what nobody will ever read.
Architecture Fundamentals
General material on what solution architecture is and what an architect is accountable for.
Architecture Governance
Preventive, automated controls rather than review meetings.
Architecture Patterns
General material on architectural patterns and their trade-offs.
Architecture Principles
Durable agreed rules that rule options out, stated with rationale and implications.
Architecture Review Boards
Thresholds, early engagement and a real route to accept deviation.
Architecture Reviews
Reviewing early enough to influence rather than to veto.
Architecture Roadmaps
Sequencing change across an estate with dependencies and funding.
AI-Era Architecture
AI workloads meeting security, data, networking, reliability and cost.
API & Integration Architecture
Contracts between systems, and the compatibility discipline that keeps them working.
Architecture Communication
Explain the same architecture to a CEO, an engineering manager and an engineer.
Architecture Decision-Making
Where senior engineer becomes architect: evaluate, choose, write it down.
Architecture Fundamentals
What architecture actually is: drivers, constraints, trade-offs and the principles behind them.
Architecture Patterns
Patterns as tools for recurring problems, with forces and consequences.