The COMPEL Glossary Graph visualizes relationships between framework terminology, showing how concepts interconnect across domains, stages, and pillars. Term nodes cluster by pillar affiliation while cross-references reveal semantic dependencies — for example, how risk appetite connects to control effectiveness, model governance, and assurance requirements. This network representation helps practitioners navigate the framework vocabulary and understand that COMPEL terminology forms a coherent conceptual system rather than isolated definitions.
COMPEL Glossary / react
ReAct
An agentic prompt pattern interleaving reasoning steps (Thought) and action steps (Act — typically a tool call) over multiple turns, with observations from each action feeding the next reasoning step.
What this means in practice
Foundation pattern for modern tool-using agents; inappropriate for short, single-step tasks because the overhead dominates.
Synonyms
ReAct pattern , Reason-and-Act
See also
- Tool use / function calling — A prompt pattern authorizing the model to request named functions with structured arguments — searching the web, reading a database, calling a calculator, triggering an API — rather than generating all answers from its weights.
- Reflection — An agentic prompt pattern where the model critiques and revises its own output — typically after tool-call feedback or detected error — before returning a final answer.
- Chain-of-thought (CoT) — A prompt pattern that elicits intermediate reasoning steps before the final answer — either zero-shot ("Let's think step by step") or few-shot with example reasoning chains.
- Agentic AI — Agentic AI refers to artificial intelligence systems capable of taking autonomous actions in the world, making decisions, using external tools, and pursuing multi-step goals with minimal or no human intervention at each step.