Glossary

Constitutional AI

Constitutional AI is an approach to training and deploying AI systems in which model behavior is guided by an explicit written set of principles — a "constitution" — rather than only by reinforcement from human feedback.

The term was popularized by Anthropic, whose training method uses a constitution to guide model self-critique and improvement. In enterprise deployment, the concept generalizes: a deployed agent's behavior is bounded by a written policy document that defines scope, prohibitions, escalation rules, and tone.

Training-time constitutional AI and deployment-time agent constitutions are complementary. The model provides a safety floor; the deployment-time constitution adds application-specific rules that the base model cannot know about — your product policies, your compliance posture, your brand voice.

In practice, the deployment-time constitution is enforced at runtime by a policy layer, not just via system prompts, because prompts drift while policies can be audited and versioned.

See also
  • Agent Constitution— An agent constitution is the written policy that defines what an AI agent is authorized to do, what it must refuse, how it escalates, and how it speaks — enforced at runtime by a policy layer.
  • AI Agent Governance— AI agent governance is the set of controls, policies, and audit mechanisms that keep deployed AI agents operating inside defined boundaries.
  • AI Agent— An AI agent is a software system that uses a large language model to perceive its environment, reason about tasks, and take actions in external systems on behalf of a user.
Guide: Agent governance & constitution

More terms in the glossary

AI Agent

An AI agent is a software system that uses a large language model to perceive its environment, reason about tasks, and take actions in external systems on behalf of a user.

AI Voice Agent

An AI voice agent is an AI agent that interacts with users through voice — answering inbound calls, placing outbound calls, and conversing in real time.

AI Chatbot (AI Chat Agent)

An AI chatbot — more accurately, an AI chat agent — is an AI agent that interacts with users through text: web chat, WhatsApp, SMS, Slack, Teams, or social messaging.

Retrieval-Augmented Generation (RAG)

Retrieval-augmented generation (RAG) is an architecture that grounds a language model's responses in a specific knowledge base by retrieving relevant passages at inference time and conditioning the response on them.

Multi-Agent Orchestration

Multi-agent orchestration is the practice of coordinating multiple specialized AI agents to accomplish a task that is too complex or too broad for a single agent.

Model Context Protocol (MCP)

Model Context Protocol (MCP) is an open standard for connecting AI agents to the tools, data sources, and prompts they need, through a consistent client-server protocol.

See the full glossary

Related pages

Enterprise AI Agents

How GrowTK builds and ships these concepts for clients.

Guides

Long-form walkthroughs that go deeper than definitions.

Scope a deployment

Ready to talk to someone about your specific use case?