Agent System Prompts

System prompts are crucial for defining an agent's behavior, persona, and operational guidelines within an agent-architecture. They establish the initial instructions for a large language model (LLM), setting its role, constraints, and how it should process subsequent inputs. As a core component of context-engineering, system prompts significantly influence agent performance, reliability, and robustness.

Prompt Design and Optimization

System prompts can be systematically improved through automated optimization, specific techniques, and structured frameworks.

Automated and Online Optimization

Prompting Techniques and Frameworks

Subtle Cues and Algorithm Steering

Safety Alignment via Prompting

Prompt Fidelity and Artifacts

Persona and Role Design

Model Capabilities and Calibration

Skill Portability and Security

Security and Robustness: Prompt Injection

Memory Poisoning Attacks

Key References