# Builder Path - Beginner

## Beginner builder path

Build a basic workflow. Deploy it to end users. Troubleshoot common issues.

### Outcomes

By the end, you will be able to:

* Build a workflow that runs end-to-end in the builder.
* Pass data between nodes using inputs and outputs.
* Add a knowledge base and retrieve context in a workflow.
* Deploy a workflow as a Chat Assistant or Form.
* Use run traces to debug failures.

### Quick jumps

<table data-view="cards"><thead><tr><th>Topic</th><th>Start here</th><th data-hidden data-card-cover data-type="image">Cover image</th></tr></thead><tbody><tr><td><strong>Learn the canvas</strong><br>Nodes, runs, publishing, and data flow.</td><td><a href="/spaces/FSlso1Kjob5CLDrh0dVn/pages/IW7bYbSsnOtcAIy96ME0">Get Started with Workflow Builder</a></td><td><a href="/files/uwZpQXt7aAJwnSfPU25m">/files/uwZpQXt7aAJwnSfPU25m</a></td></tr><tr><td><strong>Build an agent end-to-end</strong><br>Follow a full deployment checklist.</td><td><a href="/spaces/FSlso1Kjob5CLDrh0dVn/pages/8e6P9XDM92OYr6usOXZm">Deploying Your First Agent</a></td><td><a href="/files/th9ozFPuP2qpYAX1jxNn">/files/th9ozFPuP2qpYAX1jxNn</a></td></tr><tr><td><strong>Wire data between nodes</strong><br>Define inputs, map variables, shape outputs.</td><td><ul><li><a href="/spaces/FSlso1Kjob5CLDrh0dVn/pages/5wzH56PF45e9ni8OBCDA">Inputs</a></li><li><a href="/spaces/FSlso1Kjob5CLDrh0dVn/pages/1rzYB3SPYsCw4gQ4M4Wx">Outputs</a></li></ul></td><td><a href="/files/OYKa4sO5MAmiZtiBe2sp">/files/OYKa4sO5MAmiZtiBe2sp</a></td></tr><tr><td><strong>Knowledge bases (RAG)</strong><br>Add documents and retrieve relevant context.</td><td><ul><li><a href="/spaces/FSlso1Kjob5CLDrh0dVn/pages/IyHE7n42v7FygdPABjeO">Knowledge Bases</a></li><li><a href="/spaces/FSlso1Kjob5CLDrh0dVn/pages/yfOs804Ic7R1v63oPRAj">How to Use Knowledge Bases</a></li></ul></td><td><a href="/files/5ISkLW6a7BK7oRsiMwkI">/files/5ISkLW6a7BK7oRsiMwkI</a></td></tr><tr><td><strong>Deploy to users</strong><br>Chat, form, or API.</td><td><a href="/spaces/FSlso1Kjob5CLDrh0dVn/pages/A4DkSfXnyfPvWzO4wHlt">Deploy with the Export View</a></td><td><a href="/files/OHtUNBg2UvNznLx3AgXg">/files/OHtUNBg2UvNznLx3AgXg</a></td></tr><tr><td><strong>Debug your first run</strong><br>Traces, logs, and common failure modes.</td><td><a href="/spaces/FSlso1Kjob5CLDrh0dVn/pages/iUrAo2e5tc0hKLRGMYYw">Troubleshoot a Workflow</a></td><td><a href="/files/kILZ5vGqhr6rqSd6NJKJ">/files/kILZ5vGqhr6rqSd6NJKJ</a></td></tr></tbody></table>

### The path

{% stepper %}
{% step %}

### 1) Orientation

Review the platform and builder workflow. Focus on node wiring, runs, and publishing.

* [Platform Overview](/welcome-to-stackai/overview/platform-overview.md)
* [Get Started with Workflow Builder](/getting-started/start-here/get-started-with-workflow-builder.md)
  {% endstep %}

{% step %}

### 2) Build a tiny workflow

Build `Input → LLM → Output`. Run it with a few representative test inputs.

* [Inputs](/workflow-builder/inputs.md)
* [LLM Node](/workflow-builder/core-nodes/ai-agent-node.md)
* [Outputs](/workflow-builder/outputs.md)
  {% endstep %}

{% step %}

### 3) Improve response consistency

Add structure to the LLM prompt. Use explicit instructions and an expected output format.

* [Instruction vs Prompt](/getting-started/core-ai-concepts/instruction-vs-prompt.md)
* [Prompt Engineering](/getting-started/core-ai-concepts/prompt-engineering.md)
  {% endstep %}

{% step %}

### 4) Add a knowledge base (RAG)

Create a knowledge base from a small document set. Use it to retrieve relevant context during a run.

* [Knowledge Bases](/workflow-builder/core-nodes/knowledge-bases.md)
* [How to Use Knowledge Bases](/workflow-builder/core-nodes/knowledge-bases/how-to-use-knowledge-bases.md)
* [Creating a Knowledge Base](/workflow-builder/core-nodes/knowledge-bases/creating-a-knowledge-base.md)
  {% endstep %}

{% step %}

### 5) Deploy and troubleshoot

Deploy to an interface. Use the run trace to identify failures and incorrect outputs.

* [Deploy with the Export View](/interface-and-deployment/end-user-interfaces/deploy-with-the-export-view.md)
* [Chat Assistant](/interface-and-deployment/end-user-interfaces/chat-assistant.md)
* [Form](/interface-and-deployment/end-user-interfaces/form.md)
* [Troubleshoot a Workflow](/guides-and-tips/stackai-hacks/troubleshooting-a-workflow.md)
  {% endstep %}
  {% endstepper %}


---

# Agent Instructions: 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:

```
GET https://docs.stackai.com/getting-started/learning/stack-ai-curriculum/builder-path-beginner.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
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.