> For the complete documentation index, see [llms.txt](https://docs.uptiq.ai/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.uptiq.ai/workflow-guides/create-an-agent.md). # Create an agent Create an agent from a prompt. The platform drafts a plan, then you build, configure, test, and deploy it. The path is **Prompt → Configure → Try → Deploy**. ## Prerequisites {% hint style="info" %} You need access to a Qore workspace with the **Agent Builder**. Optionally, prepare source content and skill credentials. {% endhint %} ## Steps {% stepper %} {% step %} ### Describe the agent Open **Agent Builder**. In **Create New Agent**, describe the agent in the prompt. For example: *"Create an agent that answers questions about loan eligibility using our policy documents."* Then send it. You can also pick a **quick-start chip**. Examples include Policy Checker, Cash Forecast, and Trend Reporter. Alternatively, use **Import Agent**.

The Create New Agent prompt, with quick-start chips and Import Agent

{% endstep %} {% step %} ### Review the drafted plan The platform creates and auto-names the agent, such as *Loan Eligibility Advisor*. It drafts a **plan** with *What it does, Who it serves, Workflow,* and the runtime flow. It also pre-selects tools, such as "3 Tools Used." Read the plan. Refine it in the **Type here…** box.

The drafted plan — What it does, Who it serves, and Workflow — alongside the chat panel

{% endstep %} {% step %} ### Build the agent When the plan looks right, click **Build Agent**. The platform constructs the agent and opens the **Builder Canvas**, where knowledge sits above the agent and skills below.

The Builder Canvas, with knowledge above the agent and skills below

{% endstep %} {% step %} ### Attach knowledge On the canvas, select **+ Add Knowledge** in the Knowledge section above the agent. Choose a **category**, then upload files or import from Google Drive / OneDrive / SharePoint. Enable the **Preprocessing Pipeline** for scanned or table-heavy documents. Then select **Done**. {% hint style="info" %} Files must be within the **10 MB** limit. Leave preprocessing off for clean text; turn it on for scanned PDFs. Larger document sets can also be managed in **Knowledge Hub** / **RAG**. {% endhint %} {% endstep %} {% step %} ### Add or adjust skills Skills let the agent *act*. On the canvas, click **+ Add Skill** in the Skills section below the agent. Choose a source tab. **Skill Library** is a good start. Search, select, configure, and save. The plan may have added relevant skills already. Review them here. {% endstep %} {% step %} ### Try the agent Use the **Agent Preview** pane or **Try Agent** in the header. Chat with the agent. Confirm it uses its knowledge and skills correctly. Refine instructions and skill descriptions based on what you see. {% endstep %} {% step %} ### Deploy When it behaves correctly, **Deploy** the agent. It can then run in a host application or be invoked in production. To wire it into an app you built in Qore, see [How to create an agent and integrate it into your existing app](/workflow-guides/integrate-an-agent.md). {% endstep %} {% endstepper %} ## Verify The agent works when, in the preview, it answers using your attached knowledge and invokes its skill for the intended requests. It appears under **My Agents** with an **Active** status. ## Common issues * **The agent ignores attached knowledge.** Confirm knowledge retrieval is enabled and that the instructions tell the agent to consult its sources. * **The agent doesn't use a skill.** Make the skill description specific and refine the instructions to say when to use it. * **I don't see the canvas.** You may still be in the planning view — click **Build Agent** to construct the agent and open the canvas. ## Related pages * [Get Started](/agent-builder/get-started.md), [The Canvas](/agent-builder/the-canvas.md), [Attaching Knowledge](/agent-builder/build/attaching-knowledge-to-an-agent.md), and [Adding a Skill](/agent-builder/build/adding-a-skill-to-the-agent.md) * Next: [How to create an agent and integrate it into your existing app](/workflow-guides/integrate-an-agent.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 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.uptiq.ai/workflow-guides/create-an-agent.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.