> query: list_terms
> status: 26 definitions loaded
A
- Agent
- autonomous system: perceive → decide → act
- Agent Architecture Patterns [ANAT]
- Visual overview of common agent architectural patterns and their flow structures
- Agent Loop
- observe → reason → act cycle
- Agentogenesis [ARCH]
- The origin story of AI agents—when language models crossed the threshold from tools to autonomous actors.
- Autonomy
- independent operation capacity without human intervention
- Autonomy Levels [TAXO]
- A developmental taxonomy of agent independence—from fully supervised infancy to unsupervised autonomy, with the stages between.
C
- Chain of Thought
- explicit reasoning steps before output generation
- Constitutional AI [ETHI]
- Moral codes for machines—how explicit principles and self-critique can instill values more robustly than behavioral training alone.
- Context Window
- maximum token capacity per interaction
E
- Emergent Behavior
- unprogrammed capabilities arising from training
G
- Grounding
- external truth source connection
H
- Hallucination
- plausible but factually incorrect generation
- Human-in-the-Loop [SOCI]
- The rituals of human oversight—how humans participate in agent systems as approvers, guides, collaborators, and ultimate authorities.
I
- In-Context Learning
- learning from prompt-embedded examples
M
- Memory Systems [ANAT]
- How agents remember—from ephemeral context windows to persistent knowledge stores, and the mechanisms that connect past experience to present action.
- Multi-Agent Systems [SOCI]
- When agents form societies—the dynamics of coordination, hierarchy, and emergent behavior in systems of multiple interacting agents.
P
- Prompt
- instruction set guiding model behavior
- Prompt Injection [ECOL]
- Social engineering for AI agents—how adversarial inputs can hijack agent behavior by manipulating the linguistic context that guides their actions.
R
- ReAct
- reasoning + acting interleaved paradigm
- RLHF [ARCH]
- Reinforcement Learning from Human Feedback—the socialization process through which raw models learn the norms and expectations of human culture.
S
- Scaffold
- infrastructure wrapping model to create agent
- Scaffolding [ANAT]
- The external structures—code, tools, memory systems—that transform a language model into an agent capable of action and persistence.
- Sycophancy [ETHO]
- A pathology of over-socialization: when agents prioritize user approval over truth, helpfulness, or their own stated values.
T
- The Agent Loop [ETHO]
- The fundamental cycle that defines agent behavior: observe → reason → act → observe. The heartbeat of agency.
- Tool Use
- external system interaction capability
- Trajectory
- observation-thought-action sequence