> ## Documentation Index > Fetch the complete documentation index at: https://www.voiceflow.com/docs/llms.txt > Use this file to discover all available pages before exploring further. # Agent setup and guardrails > Definitions for agent setup and guardrails, with explanations of how each term fits into Voiceflow and links to the related documentation. ## Agent layers ### Global prompt The always-on layer shaping identity, tone and guardrails on every turn. It runs regardless of which playbook or workflow is active, and is written in four default sections: `#Role`, `#Goal`, `#Tone` and `#Guardrails`. **Also asked as:** - the instructions that apply to every single reply - set the bot's personality and house rules once - the system prompt for the whole assistant **Related:** [Instructions](#instructions) · [Guardrails](#guardrails) · [System prompt](/docs/resources/glossary/ai-terms#system-prompt) **Documented in:** [Global prompt › What is the global prompt?](/docs/documentation/build/global-prompt#what-is-the-global-prompt) · [Global prompt › Best practices](/docs/documentation/build/global-prompt#best-practices) · [Global prompt › #Role](/docs/documentation/build/global-prompt#%23role) · [Global prompt › #Goal](/docs/documentation/build/global-prompt#%23goal) · [Global prompt › #Tone](/docs/documentation/build/global-prompt#%23tone) ### Instructions The routing layer: which playbook or workflow handles what. Where the global prompt defines how the agent behaves, instructions define what it does with a request. **Also asked as:** - tell the assistant which skill handles which kind of request - the decision layer that picks a playbook - where the agent's routing rules live **Related:** [Global prompt](#global-prompt) · [Trigger](#trigger) · [Reference](/docs/resources/glossary/build/editor#reference) **Documented in:** [Instructions › What are agent instructions?](/docs/documentation/build/instructions#what-are-agent-instructions) · [Instructions › Writing agent instructions](/docs/documentation/build/instructions#writing-agent-instructions) ### Start message The first thing the agent says. An agentic start message is written under a `# Starting Message` heading in the instructions; a fixed greeting is a Message step in the initialization workflow with *Wait for user input* turned on. **Also asked as:** - the greeting the bot sends before the visitor types anything - open every chat with the same welcome line - make the assistant speak first **Related:** [Instructions](#instructions) · [Initialization workflow](/docs/resources/glossary/build/playbooks-workflows#initialization-workflow) **Documented in:** [Instructions › Adding a start message](/docs/documentation/build/instructions#adding-a-start-message) · [Initialization workflow › Static start message](/docs/documentation/build/framework/initialization-workflow#static-start-message) ### Trigger What tells the agent when a playbook or workflow applies. Older material calls this the "LLM Description"; the current name is Trigger. System tools carry one too, describing what the tool does and when to use it. **Also asked as:** - describe when a skill should be used - how does the model know which playbook to pick - the description the router reads **Related:** [Instructions](#instructions) · [Playbook](/docs/resources/glossary/build/playbooks-workflows#playbook) · [System tools](/docs/resources/glossary/build/tools#system-tools) **Documented in:** [Playbooks › Creating playbooks](/docs/documentation/build/playbooks#creating-playbooks) · [Querying the knowledge base › Trigger](/docs/documentation/build/querying-the-knowledge-base#trigger) ### Behaviour The model, voice and memory settings an agent runs under: default model, memory, timezone, voice output and input, session timeouts, chat persistence, events and the global no-match and no-reply responses. **Also asked as:** - the settings page for the model, the voice and memory - where do I change what the agent runs on - agent-wide settings rather than per-playbook ones **Related:** [Default model](/docs/resources/glossary/build/behaviour#default-model) · [Memory](/docs/resources/glossary/build/behaviour#memory) · [Voice output](/docs/resources/glossary/build/behaviour#voice-output) **Documented in:** [Behaviour](/docs/documentation/build/behaviour) ### Agent tools The tools attached to the agent itself rather than to one playbook. Also called global tools: APIs, integrations, MCP servers and functions added at the agent level, so every playbook can use them without adding each one individually. They apply in agentic contexts only: a workflow calls tools through its own steps. **Also asked as:** - make one tool available in every playbook - attach a tool at the agent level - share a tool across all skills **Related:** [Tool](/docs/resources/glossary/build/tools#tool) · [System tools](/docs/resources/glossary/build/tools#system-tools) · [Playbook](/docs/resources/glossary/build/playbooks-workflows#playbook) **Documented in:** [Global tools › Adding a global tool](/docs/documentation/build/tools/global-tools#adding-a-global-tool) · [Global tools › When are global tools available](/docs/documentation/build/tools/global-tools#when-are-global-tools-are-available-for-my-agent-to-use) ### Global tools The tools added at the agent level — APIs, integrations, MCP servers and functions — so every playbook can use them without adding each one individually. The same thing as [Agent tools](#agent-tools); the Studio page is titled Global tools. **Also asked as:** - add a tool once for every playbook - the agent-level tools list **Related:** [Agent tools](#agent-tools) · [Tool](/docs/resources/glossary/build/tools#tool) **Documented in:** [Global tools › Adding a global tool](/docs/documentation/build/tools/global-tools#adding-a-global-tool) ## Guardrails ### Guardrails Non-negotiable rules the agent must always follow, written under a `# Guardrails` heading in the global prompt. Models are tuned to pay extra attention to that section. Good guardrails are specific and actionable; "be professional" is a tone instruction, not a guardrail. **Also asked as:** - rules the bot must never break - hard limits on what the assistant may say or do - where do I put the things the agent is not allowed to do **Related:** [Global prompt](#global-prompt) · [Preventing hallucination](#preventing-hallucination) · [Staying in scope](#staying-in-scope) · [Transaction safety](#transaction-safety) **Documented in:** [Global prompt › #Guardrails](/docs/documentation/build/global-prompt#%23guardrails) ### Preventing hallucination A guardrail pattern: the agent says it does not have the information instead of guessing, never combines partial knowledge base results with assumptions, and never invents a plausible reply when a tool call fails. **Also asked as:** - the assistant invents facts that are nowhere in our content - keep replies to what the knowledge base actually says - the bot confidently gives wrong information - the assistant invents answers our documents never gave - stop the assistant from guessing - only answer from the documents we uploaded **Related:** [Guardrails](#guardrails) · [Hallucination](/docs/resources/glossary/ai-terms#hallucination) · [Grounding](/docs/resources/glossary/ai-terms#grounding) **Documented in:** [Global prompt › #Guardrails](/docs/documentation/build/global-prompt#%23guardrails) ### Protecting sensitive data A guardrail pattern: never reveal internal pricing logic, margins or cost structures, never share one customer's information with another, never read back full card numbers, SSNs or passwords. **Also asked as:** - stop the assistant from leaking private details - make sure the bot never reads out a card number - keep internal pricing out of replies **Related:** [Guardrails](#guardrails) · [PII redaction](/docs/resources/glossary/knowledge-and-data#pii-redaction) **Documented in:** [Global prompt › #Guardrails](/docs/documentation/build/global-prompt#%23guardrails) ### Staying in scope A guardrail pattern that keeps the agent to its domain: no legal, medical or financial advice, no comments on competitors, and an offer to connect with the right team when the conversation drifts outside it. **Also asked as:** - keep the assistant on topic - refuse questions unrelated to our product - the bot answers things it has no business answering - the assistant answers questions that have nothing to do with our business - keep the bot from going off topic - refuse unrelated requests politely **Related:** [Guardrails](#guardrails) · [Global no-match](/docs/resources/glossary/build/behaviour#global-no-match) **Documented in:** [Global prompt › #Guardrails](/docs/documentation/build/global-prompt#%23guardrails) ### Transaction safety A guardrail pattern for actions with consequences: no refund, cancellation or account change without explicit customer confirmation, business rules never overridden, identity verified before account data is touched. **Also asked as:** - make the bot ask before it does anything irreversible - require an explicit yes before a refund goes through - verify who the customer is before changing their account - the bot confirmed a refund without double-checking - ask the customer to confirm before acting **Related:** [Guardrails](#guardrails) · [Initialization workflow](/docs/resources/glossary/build/playbooks-workflows#initialization-workflow) **Documented in:** [Global prompt › #Guardrails](/docs/documentation/build/global-prompt#%23guardrails) ### Writing a strong global prompt The practices the docs recommend: keep it short (100–1000 words; every word runs on every turn), be direct (declarative rules, not hedging), keep it static so the model can reuse its cache, and keep step-by-step procedures out of it — those belong in instructions, a playbook or a workflow. **Also asked as:** - how long should the global prompt be - my prompt is huge and replies got slower - what belongs in the global prompt versus a playbook **Related:** [Global prompt](#global-prompt) · [Instructions](#instructions) · [Playbook](/docs/resources/glossary/build/playbooks-workflows#playbook) **Documented in:** [Global prompt › Keep it short](/docs/documentation/build/global-prompt#keep-it-short) · [Global prompt › Be direct](/docs/documentation/build/global-prompt#be-direct) · [Global prompt › Variable Consistency](/docs/documentation/build/global-prompt#variable-consistency) · [Global prompt › Common mistakes](/docs/documentation/build/global-prompt#common-mistakes) · [Global prompt › How long should my global prompt be?](/docs/documentation/build/global-prompt#how-long-should-my-global-prompt-be) ### Agent runtime Combines instructions, tools, knowledge, and conversation state to decide how to respond. **Documented in:** [Agent runtime](/docs/documentation/build/how-agents-work)