> 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/agents/agents.md). # Agents An **Agent** in Spara solves a complete business problem: qualifying inbound leads, re-engaging form fills, running outbound follow-up, or delivering self-serve demos. Rather than configuring a single chatbot in isolation, you build one Agent that engages buyers across every channel and coordinates the work needed to move them through your funnel. Each Agent is made up of two kinds of building blocks: * [Broken mention](broken://pages/JZjC2vxcYdoJw8hBXgCL): a real-time conversation channel. It's where a buyer directly interacts with an agent. Each capability is configured with its own trigger, instructions, tools, and A/B variants. * [Chat](/agents/channels/chat.md), [Email](/agents/channels/email.md), [Phone](/agents/channels/phone.md), [SMS](/agents/channels/sms.md), [Product Demo](/agents/channels/product-demo.md) * [Workflows](/agents/workflows.md): a proactive playbook of steps your agent executes. It's triggered by an event, such as "Lead left the chat." Workflows chain multiple steps together: send an email, wait 24 hours, make a phone call, check a condition, etc. * [Send Email Step](/agents/workflows/steps/send-email.md), [Send Text Step](/agents/workflows/steps/send-text.md), [Call Phone Step](/agents/workflows/steps/call-phone.md), [Notify Step](/agents/workflows/steps/notify.md), [Wait Step](/agents/workflows/steps/wait.md), [Time of Day Step](/agents/workflows/steps/time-of-day.md), [Condition Step](/agents/workflows/steps/condition.md), [API Step](/agents/workflows/steps/api.md), [Research Step](/agents/workflows/steps/research.md)

An Agent coordinates capabilities (the channels it engages buyers through) and workflows, its background automations.

For example, an Agent built for **MQL conversion** could weave together Chat, Email, and Phone capabilities with multiple workflows to drive more qualified meeting bookings.

An MQL conversion Agent weaving together Chat, Email, and Phone capabilities with multiple workflows.

However different the channels look, every capability is built and run the same way. See [Broken mention](broken://pages/Ur0vjqKGaKwiBN8k1z9n). ## The Agents page The [**Agents**](https://app.spara.co/agents) page is where you create and manage every Agent in your account. Each Agent in the list shows its name and goal, the capabilities and workflows it contains, and how many are published versus still in draft, so you can see your whole go-to-market motion at a glance.

The Agents page lists every Agent in your account, each solving a complete business problem across channels.

## Creating an Agent There are two ways to create an Agent: * **Start from a template**: the fastest way to launch. Spara provides proven templates for common go-to-market motions, each pre-built with the capabilities, workflows, and starting instructions for that use case. * **Start from scratch**: create an empty Agent, give it a Goal, and add capabilities and workflows yourself. Once the Agent exists, open it to configure what's inside. For a step-by-step walkthrough, see [Guide: Building an Agent](https://docs.spara.com/guides/building-an-agent). ## Templates Templates are complete, ready-to-edit Agents for the most common sales and marketing plays, for example **Inbound Lead Qualification**, **Event & Webinar Follow-Up**, **Expansion & Cross-Sell**, and **Inbound Phone Calls**. They're grouped by team (Sales, Marketing, Customer Success) so you can find the right starting point quickly. Browse them on the **Templates** tab of the Agents page. Picking a template creates a new Agent pre-loaded with the relevant capabilities and workflows, along with starting AI instructions. A template is a starting point, not a finished product. Review and customize the instructions, triggers, and content to fit your business before publishing.

Start a new Agent from a proven template, or build one from scratch.

## FAQ ### What's the difference between an Agent and a capability? An Agent is the business problem you're solving; a capability is one channel it uses to do that. A single "Inbound Sales" Agent might have a Chat capability on your pricing page, a Phone capability on your sales line, and an Email capability for follow-up — all working toward the same Goal. ### Can one Agent have multiple capabilities of the same type? Yes. An Agent can have several Chat capabilities, each with its own trigger (for example, one for `/pricing` and one for `/demo`), or multiple variants of the same capability running as an [A/B Testing](/agents/channels/configuring/a-b-testing.md). ### Do capabilities share context with each other? Capabilities operate on the same lead record, so information a lead shares in one channel is available to the Agent in another. Chat interfaces in particular share a single conversational thread. See [Chat](/agents/channels/chat.md). ### Do I have to use a template? No. Templates are an optional head start. You can build any Agent from scratch and add exactly the capabilities and workflows you need. ### Will a template change my existing Agents? No. Creating an Agent from a template adds a new Agent to your account. It doesn't modify anything you've already built. --- # 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 dynamically by asking a question. Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter: ``` GET https://docs.spara.com/agents/agents.md?ask=&goal= ``` `ask` is the immediate question: it should be specific, self-contained, and written in natural language. `goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal. 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.