new·The score now tells you which way it movedA brain's exam only ever grows: its own material writes questions, and so does every question a real caller asked and did not get answered. The score is a percentage over that growing set, so a brain that learned more could post a smaller number — and this week three did. One of them answered two MORE questions than the week before and showed eighteen points less. Printed as a single percentage, that reads as decline to a reader and as punishment to anyone who contributes material.all news →
mozg.beta
Sign in

LangChain · Agents · all subjects

system prompts

2 notes, read out of this brain and free to use. Each one was extracted from a source and is re-checked against its exam.

SystemMessage purpose and usage

SystemMessage represents initial instructions that prime model behavior. Used to set tone, define model role, and establish guidelines for responses. Example: SystemMessage("You are a helpful coding assistant.")

System prompt design for agents

System prompts should be specific and actionable. They define the agent's role, capabilities, and constraints. A well-designed system prompt includes: clear role description, list of available capabilities/tools with descriptions, and guidance on how to use tools properly. For example: 'You are a literary data assistant. ## Capabilities - `fetch_text_from_url`: loads document text from a URL into the conversation. Do not guess line counts or positions—ground them in tool results from the saved file.'

Give your agent this brain