LLM Knowledge Base · Promptmetheus

A

AI Programming Interface (AIPI)

Agent Evaluation

Agent Guardrail

Agent Orchestration

Agent Trace and Observability

Agent2Agent Protocol (A2A)

Agentic Workflow

Artificial General Intelligence (AGI)

Artificial Intelligence (AI)

B

C

Chain-of-thought Prompting

Coding Agent (Agentic Coding)

Compound Prompt

Computer-Using Agent (CUA)

Context Compaction

Context Engineering

D

Deep Research Agent

Direct Preference Optimization (DPO)

Dynamic Tool Discovery (Tool Search)

E

Evaluation-driven Development

F

Few-shot Prompt

Foundation Model

Frequency Penalty

G

Generative Pre-trained Transformer (GPT)

Group Relative Policy Optimization (GRPO)

H

I

In-context Learning

Inference-Time Scaling (Test-Time Compute)

Integrated Prompting Environment (IPE)

J

L

LLM API Provider

Language Processing Unit (LPU)

Large Language Model (LLM)

Lost-in-the-Middle Effect

M

Machine Learning (ML)

Mixture of Agents (MoA)

Mixture of Experts (MoE)

Mixture of Models (MoM)

Model Context Protocol (MCP)

Model Distillation

N

Natural Language Processing (NLP)

O

One-shot Prompt

Open-source Model

Open-weights Model

P

Presence Penalty

Prompt Chaining

Prompt Engineering

Prompt Injection Attack

Prompt Optimization

Proprietary Model

Proximal Policy Optimization (PPO)

Q

R

Reasoning Model

Reinforcement Learning from Human Feedback (RLHF)

Reinforcement Learning with Verifiable Rewards (RLVR)

Retrieval-Augmented Generation (RAG)

S

Small Language Model (SLM)

Structured Output

Supervised Fine-Tuning (SFT)

T

Tensor Processing Unit (TPU)

Tool Calling (Function Calling)

V

Vector Embedding

Vision-Language Model (VLM)

W

Z

Zero-shot Prompt

Promptmetheus © 2023-present