AI & ML Tech Glossary

Agent evaluation measures how well an AI agent completes real tasks over multiple steps, including planning, tool use, reliability, safety, latency, and cost, not just...

Agent memory is the short- and long-term storage an AI agent uses to retain user preferences, past actions, and task context across steps or sessions,...

Agent permissioning enforces least-privilege access for tool-using AI agents by controlling which tools and actions are allowed, what data scopes apply, and when human approvals...

An agent runtime is the execution layer that runs an AI agent’s loop, manages state and memory, integrates tools, and enforces policies, logging, and guardrails...

Chain-of-thought prompting is a technique that encourages an LLM to write intermediate reasoning steps before the final answer, which can improve multi-step problem solving and...

Constitutional AI is an alignment method that uses a written set of principles to guide an LLM’s self-critique and revision during training, helping it follow...

Constrained decoding restricts an LLM’s token generation to outputs that satisfy a formal constraint such as valid JSON, a schema, a grammar, or a fixed...

A context window is the token limit a language model can attend to in a single request. It determines how much conversation and document text...

A DAG-based agent workflow represents agent tasks as a directed acyclic graph of dependent steps, enabling parallel tool calls, predictable retries, caching, and structured orchestration...

Direct Preference Optimization (DPO) aligns LLMs using preference pairs (chosen vs. rejected responses) with a direct training objective. It avoids training a separate reward model...

Embedding drift is a change over time in the distribution or meaning of embedding vectors due to data, model, or pipeline changes. It can silently...

An embedding model converts text (or other data) into vectors where semantic similarity maps to vector proximity. These embeddings power semantic search and RAG by...

Evals are systematic tests for LLMs and LLM apps that score quality, safety, and reliability using datasets, rubrics, automated checks, and sometimes human review. They...