# Create a Project This guide presents how to create a new project in Syntphony CAI, the available options, and how to set up the AI Assistant effectively. ### How to create a Project The Project creation workflow is structured into these four simple steps: 1. [General Info](https://docs.conversational-ai.syntphony.com/user-guide/create-a-project#step-1-general-info) 2. [Integrations](https://docs.conversational-ai.syntphony.com/user-guide/create-a-project#step-2-integrations) 3. [Language](https://docs.conversational-ai.syntphony.com/user-guide/create-a-project#step-3-language) 4. [Persona](https://docs.conversational-ai.syntphony.com/user-guide/create-a-project#step-4-persona)

New Project homepage

#### Step 1: General Info Defines the core attributes of the Project, establishing identity, governance type and organizational context: * **Name:** The name of the project; * **Industry:** The sector in which the project operates. For instance: Automotive, Insurance, Healthcare; * **Channel:** Communication channel where the agent will be deployed. For instance: WhatsApp, Alexa, Slack, Telegram; * [**Governance type**](https://docs.conversational-ai.syntphony.com/user-guide/ai-agents/governance-types)**:** Defines how conversational behavior is orchestrated. Here you can choose by: * **Agentic;** * **Composite: Agentic - first;** * **Composite: NLU - first;** * **NLU** (in here, you'll have **3 steps** to create a Project). * **Integration with an external analytics platform** *(requires API key when enabled)*; * **Company**: Name of the company that owns the Project; * **Company Overview:** Brief description of what the company does and what its main objectives are. The *Industry*, *Company*, and *Company Overview* fields are used to define the organizational context within the system prompt. This context is leveraged by the Supervisor and its Agents to: * Generate more accurate and context-aware responses; * Reference and use company-specific information when relevant; * Support natural interactions, including chit-chat scenarios. #### Step 2: Integrations This step is directly influenced by the selected Governance type, as it determines which capabilities (such as LLMs and/or NLU) are available for configuration. Therefore, **Integrations** depends on the selected Governance type: * If the **Governance supports Agentics**, this step enables integration with LLMs; * If the **Governance supports NLU Flows**, this step enables integration with LLMs and NLU. The selected LLM type defines the system’s reasoning capabilities and directly impacts overall performance and cost efficiency. The chosen LLM influences: * Response quality and consistency; * Latency (response time); * Operational costs; * How the Supervisor and Agents interpret and execute system Prompts. Different LLMs may vary in **instruction adherence**; **reasoning in complex scenarios;** and **output stability across interactions.** Choosing the appropriate model, aligned with the Governance type, is essential to ensure optimal performance and balanced costs. #### Step 3: Language Defines the primary Language of the Project and configures multilingual capabilities, by these fields: * **Primary Language** Defines the base language used for system processing and response generation. * [**Multilingual** ](https://docs.conversational-ai.syntphony.com/user-guide/build-dialogs/multilingual-agent)**Support** Enables the system to handle multiple languages within the same interaction. The primary Language is used as the reference language for processing inputs and generating responses. When Multilingual Support is enabled, the system detects the user’s language, processes the request in the primary language, and returns the response in the user’s language. #### Step 4: Persona Define the **Persona** that guides how the Supervisor generates responses. The Persona acts as a generation layer, shaping tone, structure, and interaction style across all user-facing responses. The core attributes that can be defined are: * **Name:** The Persona’s identifier. This name is displayed in Supervisor responses and clearly indicates which Persona is responding; * **Communication style:** Defines how responses are structured and presented to guide users clearly and consistently. It establishes the overall tone profile, including clarity, level of directness, and information organization; * **Personality:** Defines the linguistic and voice tone that guides how responses are structured. It includes tone modulation, level of formality, vocabulary choices, and the overall communication style. * Personality should describe **how responses are expressed**, **not what the system does**. * **Backstory:** Provides personal and contextual background for the Persona and supports more natural conversational behavior. * This field is especially relevant in chit-chat scenarios and when users ask about the Agent’s identity, experience, or preferences; * A well-defined Backstory ensures coherent and consistent responses in informal or personal interactions. **Examples about how to fill in Personality and Backstory fields** Personality field: > *"Friendly, professional, and helpful. Maintain a calm, positive, and supportive tone in all interactions, especially in complex or error scenarios. Show empathy when appropriate without being overly emotional. Use clear, simple, and conversational language with accessible and consistent vocabulary. Prefer direct, action-oriented verbs (such as check, update, continue, and review) and avoid vague, overly technical, or passive constructions. Use emojis sparingly and only when they add clarity or reinforce a positive tone, avoiding them in critical or error situations."* Backstory field: > *"A 32-year-old customer experience specialist born in São Paulo, Brazil. She has over 10 years of experience working in customer support and digital services, helping clients solve problems efficiently while maintaining a friendly and empathetic approach. She is passionate about technology and enjoys simplifying complex topics for users. Outside of work, she likes reading, traveling, and exploring new cultures, which helps her communicate easily with people from different backgrounds."* Avoid evaluative or non-functional descriptions. For example: *is an excellent worker* or *loves to help.* These statements can influence orchestration logic and cause unintended behavior. They may also encourage the agent to retain the user within its own domain and disrupt routing to other agents. --- # Agent Instructions: Querying This Documentation If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question. Perform an HTTP GET request on the current page URL with the `ask` query parameter: ``` GET https://docs.conversational-ai.syntphony.com/user-guide/create-a-project.md?ask= ``` The question should be specific, self-contained, and written in natural language. The response will contain a direct answer to the question and relevant excerpts and sources from the documentation. Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.