← Learning

Langflow

A linear, one-concept-per-lesson path through Langflow, the visual low-code layer for building LLM flows, from your first drag-and-drop flow to graduating a prototype into production code. 22 lessons · 3 tiers.

Prerequisites: Completion of LangChain & Agent Building, or already comfortable with .invoke(), prompts, and tools - the model/prompt lessons assume this.

Lessons use Google's Gemini free tier (gemini-3.5-flash-lite), the same model as every other course, no prepaid API credits needed.

Built on Langflow, the open-source framework this course teaches.

Course source

Every lesson's README and lesson.py for this course live in the ai-agent-engineering repo.

View on GitHub →
Langflow

Beginner

Building and testing a flow by hand, then headlessly.

  1. 01What Is LangflowGitHub
  2. 02First FlowGitHub
  3. 03Components as ContractsGitHub
  4. 04Prompt TemplatesGitHub
  5. 05Connecting and ReorderingGitHub
  6. 06Testing in the PlaygroundGitHub
  7. 07Global Variables and SecretsGitHub
  8. 08Session ID and MemoryGitHub
  9. 09Checkpoint: A Small Q&A Flow, Built End to EndGitHub

Intermediate

The code surface, agents, and branching.

  1. 10run_flow_from_json in DepthGitHub
  2. 11REST API and AuthGitHub
  3. 12Custom Component BasicsGitHub
  4. 13Custom Component as ToolGitHub
  5. 14Agent ComponentGitHub
  6. 15Branching and Conditional RoutingGitHub
  7. 16Checkpoint: An Agent Flow With a Custom Tool, Callable Over RESTGitHub

Advanced

Production concerns and the prototype-to-code trade-off.

  1. 17lfx Headless ExecutionGitHub
  2. 18Screenshotting the Canvas With PlaywrightGitHub
  3. 19Exporting and Versioning FlowsGitHub
  4. 20Deploying a Flow as a ServiceGitHub
  5. 21Webhooks and External TriggersGitHub
  6. 22Capstone: The Same Small Agent, Langflow vs. Raw LangGraphGitHub
Start at Lesson 1

Contact

Book a Call