> For the complete documentation index, see [llms.txt](https://docs-conversational-ai.syntphony.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs-conversational-ai.syntphony.com/project/create-a-project.md). # Create a Project A project brings together everything needed to build a conversational solution in Syntphony CAI. This guide walks you through its creation and setup. ## What is a project? A **Project** is the main structure where a conversational solution is built and configured. It defines how conversations are orchestrated and brings together components such as the **Supervisor, Agents, NLU Flows, Actions, Knowledge**, and integrations. Depending on the selected **governance type**, these components work together to interpret user requests, route conversations, and execute the appropriate actions. **Learn more about** [**Governance Types**](/project/governance-types.md) *** ## How to create a project The project creation process guides you through the initial settings required to configure your conversational experience. Depending on the selected **governance type**, the process includes **three or four steps**: 1. **General Info** 2. **Integrations** 3. **Language** 4. **Persona** - available when the selected Governance supports Agentics. {% hint style="info" %} **Important:** Projects using **NLU-only Governance** have three creation steps. **Persona** is not available because it applies to Agentic experiences. {% endhint %}

Create Project page

### Step 1: General Info Defines the core attributes of the Project, establishing identity, governance type and organizational context: * **Name:** Name used to identify the project. * **Industry:** Industry or sector in which the project operates, such as Automotive, Insurance, or Healthcare. * **Channel:** Main communication channel for the project, such as WhatsApp, Alexa, Slack, or Telegram. * **Governance type:** Defines how conversations are orchestrated: * **Agentic** * **Composite: Agentic - first** * **Composite: NLU - first** * **NLU.** * **External analytics integration:** Enables integration with an external analytics platform. An API key is required when enabled. * **Company:** Name of the company associated with the project. * **Company Overview:** Brief description of the company, its business, and main objectives. {% hint style="info" %} **Context used by AI:** **Industry, Company, and Company Overview** provide organizational context for the system prompt. When Agentics is used, this context helps the Supervisor and Agents generate more relevant, company-aware responses, including in general conversational interactions. {% endhint %} ### Step 2: Integrations Configure the technologies used to interpret and process conversations. The available options depend on the **governance type** selected in the previous step. * Governance types that support **Agentics** allow you to configure an **LLM**. * Governance types that support **NLU Flows** provide the integrations required for **LLM** or **NLU** processing. When an LLM is configured, the selected model can affect response quality, reasoning capabilities, latency, instruction adherence, and operational costs. **Learn more about** [**Language Models**](/language-models/overview.md) {% hint style="info" %} **Consider performance and cost:** LLMs have different capabilities and consumption profiles. Choose a model that provides the appropriate balance between your use case, expected performance, and cost. {% endhint %} ### Step 3: Language Define the project's **primary language** and, when required, enable multilingual interactions. * **Primary Language:** The project's reference language for processing and generating responses. * **Multilingual Support:** Allows the project to interact with users in languages other than the primary language. When multilingual support is enabled, Syntphony CAI identifies the user's language and applies the project's multilingual processing to return the response in the appropriate language. **Learn more about** [**Multilanguage**](/resources/advanced-resources/multilingual-agent.md) ### Step 4: Persona Define the **Persona** that guides how the Supervisor communicates with users. It shapes the tone, communication style, and identity applied to user-facing responses. {% hint style="info" %} **Note:** This step is only available when the selected Governance type supports **Agentics**. {% endhint %} Configure the following attributes: * **Name:** Identifies the Persona and can be used in Supervisor responses. * **Communication style:** Defines how information is structured and presented, including clarity, directness, and organization. * **Personality:** Defines how the Persona expresses itself, including tone, formality, and vocabulary. * **Backstory:** Provides contextual background that helps maintain a consistent identity, particularly during chit-chat or identity-related interactions. **Learn more about** [**Persona**](/studio/ai-agents/persona.md) --- # Agent Instructions This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com. ## Querying This Documentation If you need additional information that is not directly available in this page, you can query the documentation by asking a question. Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters: ``` GET https://docs-conversational-ai.syntphony.com/project/create-a-project.md?ask=&goal= ``` `ask` is the immediate question: it should be specific, self-contained, and written in natural language. `goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case. 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.