For the complete documentation index, see llms.txt. This page is also available as Markdown.
Create an agent
Describe, plan, build, and deploy an AI agent in the Agent Builder.
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
You need access to a Qore workspace with the Agent Builder.
Optionally, prepare source content and skill credentials.
Steps
1
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
2
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
3
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
4
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.
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.
5
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.
6
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.
7
Deploy
When it behaves correctly, Deploy the agent. It can then run in a host application or be invoked in production.
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.
