Terminology

2185 terms, tools, patterns and metrics an architect is expected to use precisely. Each one gets a short explanation of what it is, and — where it matters — what it is commonly confused with. Search filters as you type; the column headers sort.

All areas2185 Architecture Fundamentals77 Distributed Systems107 Data Architecture110 Cloud Architecture89 Networking88 API & Integration Architecture82 Reliability & Resilience75 Observability70 Performance & Capacity Engineering72 Security Architecture81 Cost Architecture & FinOps66 Business Architecture67 Architecture Communication67 Enterprise Architecture66 Legacy Modernization66 AI-Era Architecture69 Software Architecture & Engineering71 Architecture Patterns71 Architecture Decision-Making63 The Architect's Meta-Skills61 Delivery & Release Engineering66 Platform Engineering & Developer Experience70 Testing & Quality Architecture66 Data Platform Architecture64 Streaming & Real-Time Data69 Data Governance & Semantics69 Frontend & Experience Architecture66 Edge, Mobile & IoT68 Regulatory & Data Protection Architecture65 Assurance, Audit & Model Risk64

Kind Any concept785 practice729 pattern362 metric125 case-study77 tool62 protocol45

19 terms shown.

Term	Kind	Topic	What it is
Agent Loop	concept	Agent Architectures	The cycle in which a model observes state, selects an action, executes a tool and observes the result, repeating until a goal or a limit is reached.
Approximate Nearest Neighbour Index ANN	concept	Vector Databases	An index that trades exactness for speed when finding similar vectors, making large-scale semantic search feasible.
Automation Ratchet Residual Difficulty, Hard-Case Concentration	concept	Human in the Loop	The effect where improving automation makes the cases reaching humans systematically harder, so reviewer throughput falls and error rates rise even as the overall system improves.
Capability Confinement Least-Privilege Agents, Trust Domain Separation, Action Authorisation	concept	Prompt Injection Defence	Limiting what an agent is authorised to do rather than trying to prevent it from being misled - because a model cannot reliably distinguish instructions from data, so the security boundary must sit outside it.
Context Window	concept	AI-Era Architecture	The maximum number of tokens a model can attend to in one request, holding the system prompt, history, retrieved context, tools and the answer.
Context Window Budget	concept	LLM Application Architecture	The finite token allowance per request, treated as an engineering resource to be allocated deliberately between system instructions, retrieved context, history and output.
Embedding	concept	AI-Era Architecture	A dense numeric vector representing a piece of content, positioned so that semantically similar content sits nearby.
Embedding Table Collision Hashing Trick Collision, ID Bucket Collision	concept	Embeddings	Two unrelated identifiers mapped to the same row of a fixed-size embedding table, so their learned representations are averaged together and the model quietly treats distinct items as one.
Embeddings	concept	Embeddings	Dense numeric representations of content that place similar things close together — the substrate of semantic search and retrieval.
Indirect Prompt Injection	concept	Prompt Injection Defence	An attack in which malicious instructions are placed in content the model will later retrieve, rather than typed by the user.
Inference Request Path	concept	LLM Application Architecture	The sequence of stages an LLM application request passes through, each with distinct latency, cost and failure characteristics.
KV Cache Attention Cache, Key-Value Cache, Prefix Cache	concept	LLM Application Architecture	The per-session key and value tensors a transformer must hold in GPU memory to generate each subsequent token - the resource that limits concurrent sessions, and whose reuse across turns is the difference betw…
ML Platform	concept	ML Platform	The infrastructure that makes machine learning repeatable — data, features, training, deployment, monitoring — where the model is the small part.
Prompt Injection	concept	AI-Era Architecture	An attack in which text from an untrusted source is interpreted by the model as instructions rather than as data.
Retrieval Grounding Grounded Generation	concept	RAG Architecture	Constraining a model's answer to content retrieved from an authoritative corpus, with citations and an abstention path - so that output quality becomes a retrieval problem rather than a model problem.
Serving Path Divergence Per-Pool Quality Drift, Heterogeneous Fleet Skew	concept	AI Observability	One configuration in a fleet of otherwise identical inference paths behaving differently from its peers - detectable by comparing paths against each other, and invisible to any metric averaged across them.
Subagent Context Isolation Parallel Context Windows, Context Partitioning Across Agents	concept	Multi-Agent Systems	The property that makes multi-agent systems worth their cost - each subagent explores with its own context window and returns only a condensed result, so the system reads far more than one context could hold.
Tool Authorisation Boundary Model as Untrusted Proposer, Authorise Outside the Model	concept	Prompt Injection Defence	Authorising every tool invocation against the initiating user's own permissions, outside the model - because the model cannot distinguish instructions from data and no prompt-level defence is reliable.
Training-Serving Skew Online-Offline Skew, Feature Skew	concept	ML Platform	A divergence between the features a model was trained on and the features computed at serving time - producing a model that performs well offline and worse in production, with nothing erroring.