> For the complete documentation index, see [llms.txt](https://docs.spara.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.spara.com/build.md). # Build - [Agents](https://docs.spara.com/build/agents.md): How Spara Agents can solve a complete business problem. - [Channels](https://docs.spara.com/build/channels.md): The channels an Agent engages buyers through, and the anatomy shared by all of them. - [Chat](https://docs.spara.com/build/channels/chat.md): An overview of Spara's Chat channel and its interfaces. - [Spara Navigator](https://docs.spara.com/build/channels/chat/spara-navigator.md): An introduction to Spara's website chatbot. - [Spara Smartbar](https://docs.spara.com/build/channels/chat/spara-smartbar.md): An introduction to Spara's embeddable Smartbar interface. - [Spara Fullscreen](https://docs.spara.com/build/channels/chat/spara-fullscreen.md): An introduction to Spara's full screen interface. - [Chat Theme](https://docs.spara.com/build/channels/chat/chat-theme.md): Customize how Spara looks to your leads across all three chat interfaces: Navigator, Fullscreen, and Smartbar. - [Media](https://docs.spara.com/build/channels/chat/media.md): Upload and configure visual media that Spara chat agents show to leads during conversations. - [Email](https://docs.spara.com/build/channels/email.md): How the Email channel automates sales email outreach and replies. - [Phone](https://docs.spara.com/build/channels/phone.md): How the Phone channel handles AI phone calls to engage, qualify, and convert leads. - [SMS](https://docs.spara.com/build/channels/sms.md): How the SMS channel automates sales conversations over text. - [Product Demo](https://docs.spara.com/build/channels/product-demo.md): How Spara's Product Demo channel delivers live, voice-narrated product demos to prospects. - [Opening Visual](https://docs.spara.com/build/channels/product-demo/opening-visual.md): How to create the opening visual for a Product Demo: gather source screenshots, prompt an image tool, and set the result on your demo. - [Visuals and Interactivity](https://docs.spara.com/build/channels/product-demo/visuals-and-interactivity.md): Manage the screenshots and videos a Product Demo shows, and make them interactive with clickable regions, guided walkthroughs, and links. - [Spara Scanner](https://docs.spara.com/build/channels/product-demo/spara-scanner.md): Download and install the Spara Scanner Chrome extension to capture your product for AI-powered demos. - [Configuring Channels](https://docs.spara.com/build/channels/configuring.md): The building blocks shared by every channel: instructions, abilities, testing, and the draft-and-publish lifecycle. - [AI Instructions](https://docs.spara.com/build/channels/configuring/ai-instructions.md): How to write and structure the AI instructions that define every channel's behavior. - [Abilities](https://docs.spara.com/build/channels/configuring/abilities.md): Tools channels can call during a conversation: calendars, transfers, media, email, and more. - [Testing](https://docs.spara.com/build/channels/configuring/testing.md): How to test channels using the built-in testing interface and automated Simulations. - [Saving & Publishing](https://docs.spara.com/build/channels/configuring/saving-and-publishing.md): How drafts, publishing, and version history work across all channels. - [A/B Testing](https://docs.spara.com/build/channels/configuring/a-b-testing.md): How Spara supports A/B and multivariate testing of channels to optimize conversion. - [Workflows](https://docs.spara.com/build/workflows.md): How to deploy agents to run a proactive GTM playbook. - [Workflow Steps](https://docs.spara.com/build/workflows/steps.md): The individual actions a workflow can run, from sending an email to branching on a condition. - [Send Email Step](https://docs.spara.com/build/workflows/steps/send-email.md): Send a personalized email from your AI agent. - [Send Text Step](https://docs.spara.com/build/workflows/steps/send-text.md): Send a personalized SMS to a lead's phone number. - [Call Phone Step](https://docs.spara.com/build/workflows/steps/call-phone.md): Have a Voice agent call a lead's phone number. - [Notify Step](https://docs.spara.com/build/workflows/steps/notify.md): Send an internal notification via email, Slack, Teams, or Webex. - [Wait Step](https://docs.spara.com/build/workflows/steps/wait.md): Pause workflow execution for a set amount of time. - [Time of Day Step](https://docs.spara.com/build/workflows/steps/time-of-day.md): Retired step that held workflow execution until a specific time of day was reached. - [Condition Step](https://docs.spara.com/build/workflows/steps/condition.md): Branch your workflow based on lead data. - [API Step](https://docs.spara.com/build/workflows/steps/api.md): Make an HTTP request to an external system and extract data from the response. - [CRM API Step](https://docs.spara.com/build/workflows/steps/crm-api.md): Call your connected CRM's API with Spara's stored connection and extract data from the response. - [Set Field Step](https://docs.spara.com/build/workflows/steps/set-field.md): Write a value to a field on the lead partway through a workflow. - [Research Step](https://docs.spara.com/build/workflows/steps/research.md): Run an AI prompt to reason over lead data, research accounts on the web, and extract structured results. - [Configuring Workflows](https://docs.spara.com/build/workflows/configuring.md): How to use the Workflow editor, covering triggers, steps, settings, and the publish lifecycle. - [Knowledge](https://docs.spara.com/build/knowledge.md): How to train Spara agents on your company's knowledge base. - [Data Model](https://docs.spara.com/build/data-model.md): How Spara organizes lead data — where fields come from, how conflicting sources are resolved, and how to manage your fields. - [Testing](https://docs.spara.com/build/testing.md): How to test Spara AI. --- # 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.spara.com/build.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.