AB-620 key terms

A pattern where a model's answer is grounded by first retrieving relevant documents or records from a data source and inserting them into the prompt, reducing hallucination and keeping responses current without retraining.

Anchoring model output to verifiable source content, such as retrieved documents or system records, so answers cite or reflect real data rather than relying only on pretrained knowledge.

Splitting large documents into smaller passages before embedding and indexing, balancing chunk size so retrieved context is specific enough to be relevant yet large enough to be meaningful.

A numeric vector representation of text or other content that captures semantic meaning, letting systems compare items by similarity for search, clustering, or recommendation.

A data structure that stores embeddings and supports fast approximate nearest-neighbor lookup, enabling semantic retrieval over large document collections at query time.

Retrieval based on meaning similarity between a query and stored content rather than exact keyword matches, typically powered by embeddings and a vector index.

A retrieval approach that combines keyword matching with vector similarity and merges the ranked results, improving recall for exact terms while preserving semantic relevance.

Instructions configured ahead of user input that define an agent's role, tone, constraints, and available tools, shaping behavior across every conversation turn.

An AI component that receives a goal, reasons about next steps, invokes tools or models, and iterates until it produces a result or reaches a stopping condition.

A mechanism where a model requests that an external function, API, or service be executed with specific arguments, then uses the returned result to continue its reasoning.

A structured description of a callable tool, including its name, purpose, and typed parameters, that tells the model when and how to invoke it correctly.

The coordination of multiple steps, models, or agents in a defined sequence or branching flow, managing state, retries, and handoffs between stages.

A predefined sequence of automated steps, triggers, and conditions that processes inputs and produces outputs, often combining model calls with deterministic business logic.

A design where a person reviews, approves, or corrects an AI output at a defined checkpoint before the process continues, used for high-risk or low-confidence actions.

A reusable prompt with placeholders that are filled at runtime with user input, retrieved context, or variables, keeping prompts consistent and maintainable across calls.

Including a small number of worked examples in a prompt so the model can infer the desired format, tone, or reasoning pattern for the current task.

A configured integration that lets an AI solution read from or write to an external system such as a database, file store, or SaaS application using that system's protocol and credentials.

A specific network address and method through which a service exposes operations, used by agents or workflows to send requests and receive structured responses.

A control that caps how many requests a client may send in a time window, protecting downstream services and keeping integrations within provider quotas.

Rules governing how failed calls are reattempted, including maximum attempts, delay between tries, and which error types qualify, often using exponential backoff.

A property where repeating the same request produces the same effect as sending it once, preventing duplicate records or actions when retries occur.

The origin system or store that supplies content to an AI solution, such as a database, document library, or message queue, along with its access rules.

An automated process that ingests source content, extracts and chunks text, generates embeddings, and writes them to a search index on a schedule or on change.

A curated set of representative inputs paired with expected outputs or grading criteria, used to measure solution quality and compare changes objectively.

A score measuring how well a generated answer is supported by the provided source content, flagging responses that assert facts absent from the evidence.

Re-running an evaluation dataset after a change to prompts, models, or data to confirm quality has not degraded and previously passing cases still succeed.

A human-reviewed reference answer treated as the expected result for a test case, used as a baseline when scoring model output.

Confidently stated output that is factually wrong or unsupported by available evidence, often caused by missing context or overgeneralization from training data.

A unit of text, roughly a word fragment, that models process and bill against; token counts determine context limits and cost per request.

The maximum number of tokens a model can consider in a single request, spanning system instructions, conversation history, retrieved content, and the response.

The elapsed time between sending a request and receiving a usable response, influenced by model choice, output length, retrieval steps, and network overhead.

Storing previously computed responses or retrieved results so repeated or similar requests can be served faster and at lower cost.

A cutoff on a model or classifier score that determines whether an output is accepted automatically, escalated for review, or rejected.

A configured control that constrains AI behavior, such as blocking harmful content, restricting topics, or validating outputs before they reach users or downstream systems.

A screening layer that detects and blocks or annotates harmful, unsafe, or disallowed material in prompts and responses according to policy categories and severity levels.

A set of principles and practices for building AI that is fair, transparent, accountable, and safe, guiding design decisions about harms, disclosure, and oversight.

A platform-issued identity assigned to a workload that obtains credentials automatically, letting the solution access protected resources without storing secrets in code.

An authorization model that grants permissions based on assigned roles rather than individual accounts, simplifying least-privilege management across users and services.

A secured service for storing and auditing secrets, keys, and certificates so applications retrieve them at runtime instead of embedding credentials in configuration files.

The requirement that data be stored and processed only in approved geographic regions, affecting where models, indexes, and logs may be deployed.