Key terminology from “From Blueprint to Application”
Agent - An AI system that can take actions autonomously, make decisions, and work toward goals without constant human direction.
API (Application Programming Interface) - The interface through which applications communicate with AI models.
Chain-of-Thought (CoT) - A prompting technique that encourages the AI to show its reasoning process step by step.
Context Window - The maximum amount of text (measured in tokens) that an AI model can process in a single interaction.
Context Engineering - The practice of designing and managing the information provided to AI systems to optimize their outputs.
Few-Shot Learning - Providing examples in the prompt to help the AI understand the desired output format or style.
Fine-Tuning - Customizing a pre-trained AI model with additional training data for specific use cases.
Hallucination - When an AI generates false or fabricated information that appears plausible.
MCP (Model Context Protocol) - A standardized protocol for connecting AI models to external tools and data sources.
Multi-Agent System - Multiple AI agents working together, each with specialized roles and capabilities.
Prompt - The input text or instructions given to an AI model.
Prompt Engineering - The systematic practice of designing, optimizing, and refining prompts to achieve desired AI outputs.
Prompt Injection - A security vulnerability where malicious instructions are hidden within input to manipulate AI behavior.
Prompt Library - A centralized collection of tested, optimized prompts for organizational use.
RAG (Retrieval-Augmented Generation) - A technique that enhances AI responses by retrieving relevant information from external sources.
Role Prompting - Assigning a specific persona or expertise to the AI (e.g., “You are an expert technical writer”).
System Prompt - Instructions that define the AI’s behavior across an entire conversation, typically set by the application developer.
Temperature - A parameter controlling the randomness/creativity of AI outputs (lower = more deterministic, higher = more creative).
Token - The basic unit of text processing for AI models. Roughly 4 characters or 3/4 of a word in English.
Tool Use - The ability of AI models to call external functions or APIs to accomplish tasks.
Zero-Shot - Asking an AI to perform a task without providing examples in the prompt.