vibe-engines

Reference

Glossary.

The vocabulary of AI engineering and system design, in plain English — each term defined, then linked to a hands-on lab, challenge, or handbook so you can actually learn it.

A

AgentA model wrapped in a loop that lets it call tools, read the results, and act until a task is done.AI & LLMs AttentionThe operation that lets each token look at every other token and weight how much to listen to each.AI & LLMs

B

BackpressureSignaling upstream to slow down when a system can’t keep up, instead of collapsing.Systems & Backend Bloom FilterA tiny probabilistic set that answers “maybe present” or “definitely absent” — no false negatives.Data & Retrieval

C

Cache InvalidationKeeping cached data correct as the underlying source changes — famously one of the hard problems.Systems & Backend CAP TheoremDuring a network partition a distributed store must choose consistency or availability, not both.Systems & Backend Chain of ThoughtPrompting a model to reason step by step before answering, improving hard multi-step tasks.AI & LLMs Consistent HashingMapping keys and nodes onto a ring so adding a node moves only ~K/N keys, not all of them.Systems & Backend Context WindowThe maximum number of tokens a model can consider in one request — a hard, shared budget.AI & LLMs Cosine SimilarityHow aligned two vectors are, ignoring their length — 1 identical, 0 unrelated, −1 opposite.Data & Retrieval Cross-Entropy LossThe training loss that measures how surprised the model was by the correct answer.AI & LLMs

E

EmbeddingA vector that places a piece of text in space so that nearby vectors mean similar things.Data & Retrieval Eventual ConsistencyReplicas may briefly disagree but converge to the same value once writes stop.Systems & Backend

F

Fine-TuningContinuing to train a pretrained model on your data to specialize its behavior.AI & LLMs

H

HallucinationWhen a model states something fluent and confident that is simply not true.AI & LLMs

I

IdempotencyA property where doing an operation twice has the same effect as doing it once.Systems & Backend

L

LLM-as-a-JudgeUsing a strong model with a rubric to score other models’ outputs, at scale.AI & LLMs

M

Mixture of Experts (MoE)A model that routes each token to a few specialist sub-networks instead of the whole network.AI & LLMs Model Context Protocol (MCP)An open standard for connecting models to tools and data through a common server interface.AI & LLMs

P

p99 LatencyThe response time your worst 1% of requests exceed — the tail users actually feel.Systems & Backend Prompt CachingReusing the processed prefix of a prompt so you don’t re-pay to encode it every turn.AI & LLMs Prompt InjectionAn attack where malicious text in the input overrides the developer’s instructions.AI & LLMs

Q

Quorum (N/R/W)Requiring a minimum number of replicas to agree on a read or write to tune consistency.Systems & Backend

R

Rate LimitingCapping how many requests a client may make, protecting a service from overload and abuse.Systems & Backend Retrieval-Augmented Generation (RAG)Fetching relevant documents and putting them in the prompt so the model answers from real sources.Data & Retrieval

S

ShardingSplitting data across many machines so no single node holds — or bottlenecks on — all of it.Systems & Backend SoftmaxTurns a vector of raw scores (logits) into a probability distribution that sums to 1.AI & LLMs

T

TemperatureThe decoding dial that flattens or sharpens the next-token distribution.AI & LLMs TokenThe unit a model actually reads and writes — a sub-word chunk, not a character or a word.AI & LLMs TokenizationSplitting text into tokens, usually with byte-pair encoding that merges frequent character pairs.AI & LLMs Tool CallingHow a model reaches beyond text: it emits a structured call and your code runs the function.AI & LLMs TransformerThe neural-network architecture behind virtually every modern language model.AI & LLMs

V

Vector DatabaseA store built to index and search embeddings by nearest-neighbor similarity at scale.Data & Retrieval