Glossary
Key terms and definitions for the Akios ecosystem and AI development.
Agent
An autonomous entity that uses an LLM as a "brain" to perceive context, reason about a problem, and take actions via Tools.
Chain of Thought (CoT)
A prompting technique that encourages the model to generate intermediate reasoning steps before providing the final answer.
Context Window
The maximum amount of text (measured in tokens) that the LLM can consider at one time. Includes system prompt, history, and current query.
Embeddings
Vector representations of text. Used to measure semantic similarity between two pieces of text, enabling "semantic search".
Few-Shot
Providing a few examples (shots) in the prompt to demonstrate the desired behavior or format.
Guardrail
A safety layer that intercepts inputs or outputs to check for violations (PII, toxicity, topic drift) and can block or sanitize content.
Hallucination
When an LLM generates plausible-sounding but factually incorrect information.
RAG (Retrieval-Augmented Generation)
A pattern where the agent fetches relevant documents from a knowledge base (usually a Vector DB) and injects them into the prompt before answering.
Temperature
A parameter controlling the randomness of the model output. Low (0.0) is deterministic/focused; High (1.0) is creative/random.
Tool (Function Calling)
A deterministic function (API, script, database query) exposed to the LLM. The LLM can decide to "call" the tool by outputting a structured JSON payload.
Zero-Shot
Asking the model to perform a task without providing any examples.