"Think of context as the complete memory that an LLM has available during a conversation. The context grows with each interaction: it is built from different messages, and there are different message types. These are like individual cards in a strictly ordered stack. Each card has its specific role and position. When you use GenAI apps like ChatGPT, Claude, or GitHub Copilot, you're actually seeing this context displayed through their chat interface. Each message, response, and action appears in the order it was added to the context."
"The system prompt is the first message that sets up everything before any conversation begins. It's usually configured by the developers of the AI app and remains hidden from users. (Remember the analogy of a strictly ordered card stack? This is the first card.) It has three key parts: 1. Chat agent description: Defines how the chat agent should behave. It improves accuracy and adjusts the voice and tone of the agent. For example, that it needs to support development, and it can contain various security rules (e.g. protecting sensitive information; "Don't bypass authentication systems")."
Context is the complete memory available to a large language model during a conversation. Context grows with each interaction and comprises different message types arranged as strictly ordered cards, each with a specific role and position. The system prompt is the first card and establishes the agent's behavior, environment details, and available tools. The chat agent description defines tone, role, goals, and security guardrails. Environment information supplies operating details like workspace and shell, while tool descriptions enumerate available tools and their expected inputs, enabling accurate, contextual responses.
Read at Medium
Unable to calculate read time
Collection
[
|
...
]