> ## Documentation Index > Fetch the complete documentation index at: https://docs.tavus.io/llms.txt > Use this file to discover all available pages before exploring further. # Overview > Define how your PAL behaves, responds, and speaks by configuring layers and pipeline modes. A **PAL** (Personified Application Layer) is what you build in CVI. Configure its **Face** to define how it looks, its **Voice** to define how it sounds, and its behavior, knowledge, objectives, guardrails, tools, and pipeline layers to shape how it thinks and acts. **Terminology update:** Tavus now uses **PAL** for what you build, **Face** for how it looks, and **Voice** for how it sounds in the API and docs. Legacy names **persona** and **replica** still work on existing endpoints and request fields (`/v2/personas`, `/v2/replicas`, `persona_id`, `replica_id`, and related aliases) for backward compatibility. **At a glance** * **PAL** - How it thinks and acts: name, behavior, **pipeline mode**, **default face**, **layers**, **documents** (Knowledge Base), **objectives**, and **guardrails**. Select a **Voice** in the TTS layer; if none is set, CVI uses the Face's default Voice. * **Relationship to CVI** - PALs hold the settings that drive a real-time CVI session; see **[What Is CVI?](/sections/conversational-video-interface/overview-cvi)** for the full stack (WebRTC, layers, Phoenix, and latency characteristics on the default path). * **Layers (order of guides below)** - Perception → STT → Conversational Flow → LLM → TTS; each has its own configuration page. ## PAL Customization Options Each PAL includes configurable fields. Here's what you can customize: * **PAL Name**: Display name shown when the PAL joins a call. * **System Prompt**: Instructions sent to the language model to shape the PAL's tone, personality, and behavior. * **Pipeline mode**: Controls which CVI pipeline layers are active and how input/output flows through the system. See [Pipeline modes](/sections/conversational-video-interface/quickstart/pipeline-modes) for how the full pipeline, Echo, integrations, and custom LLM paths differ. * **Default face**: Sets the photorealistic face associated with the PAL (`default_face_id` on `POST /v2/pals`; required). * **Layers**: Perception, STT, conversational flow, LLM, and TTS - each processes part of the interaction and can be tuned independently (see [Layers](#layers) below). * **Documents**: A set of documents that the PAL has access to via the **Knowledge Base** (retrieval-augmented generation, RAG). * **Objectives**: The goal-oriented instructions your PAL will adhere to throughout the conversation. * **Guardrails**: Conversational boundaries that can be used to strictly enforce desired behavior. * **AI disclosure** (`disclosure_type`, `verbal_disclosure`, `visual_disclosure`): Spoken and on-screen notice that the participant is talking to an AI. See [EU AI Act](/sections/onboarding-guide/eu-ai-act) for product guidance. ## Objectives & Guardrails Provide your PAL with robust workflow management tools, curated to your use case The sequence of goals your PAL will work to achieve throughout the conversation - for example, gathering a piece of information from the user. Conversational boundaries that can be used to strictly enforce desired behavior. ## Layers Explore our in-depth guides to customize each layer to fit your specific use case: Defines how the PAL interprets visual input like facial expressions and gestures. Transcribes user speech into text using the configured speech-to-text engine. Controls turn-taking, interruption handling, and active listening behavior for natural conversations. Generates PAL responses using a language model. Supports Tavus-hosted or custom LLMs. Converts text responses into speech using Tavus or supported third-party TTS engines. Gives the PAL an email identity so it can be invited to Google Meet, Zoom, or Microsoft Teams calls via a calendar invite and join automatically - including meetings already in progress. This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.