Ctrlk
For the complete documentation index, see llms.txt. This page is also available as Markdown.

Builder Path - Beginner

A step-by-step learning path to build and deploy your first StackAI workflow.

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

Cover
Topic

Learn the canvas Nodes, runs, publishing, and data flow.

Start here

Get Started with Workflow Builder

Cover
Topic

Build an agent end-to-end Follow a full deployment checklist.

Start here

Deploying Your First Agent

Cover
Topic

Wire data between nodes Define inputs, map variables, shape outputs.

Start here
Cover
Topic

Knowledge bases (RAG) Add documents and retrieve relevant context.

Start here
Cover
Topic

Deploy to users Chat, form, or API.

Start here

Deploy with the Export View

Cover
Topic

Debug your first run Traces, logs, and common failure modes.

Start here

Troubleshoot a Workflow

The path

1

1) Orientation

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

2

2) Build a tiny workflow

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

3

3) Improve response consistency

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

4

4) Add a knowledge base (RAG)

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

5

5) Deploy and troubleshoot

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

PreviousStackAI CurriculumNextBuilder Path - Intermediate

Last updated

Was this helpful?